borderline personality disorder research articles

REVIEW article

Twenty years of research on borderline personality disorder: a scientometric analysis of hotspots, bursts, and research trends.

• 1 Department of Psychology, School of Humanities and Social Sciences, Anhui Agricultural University, Hefei, China
• 2 College of Computing & Informatics, Drexel University, Philadelphia, PA, United States
• 3 Department of Psychology, School of Education, China University of Geosciences, Wuhan, China
• 4 Department of Information Management, Anhui Vocational College of Police Officers, Hefei, China

Borderline personality disorder (BPD), a complex and severe psychiatric disorder, has become a topic of considerable interest to current researchers due to its high incidence and severity of consequences. There is a lack of a bibliometric analysis to visualize the history and developmental trends of researches in BPD. We retrieved 7919 relevant publications on the Web of Science platform and analyzed them using software CiteSpace (6.2.R4). The results showed that there has been an overall upward trend in research interest in BPD over the past two decades. Current research trends in BPD include neuroimaging, biological mechanisms, and cognitive, behavioral, and pathological studies. Recent trends have been identified as “prevention and early intervention”, “non-pharmacological treatment” and “pathogenesis”. The results are like a reference program that will help determine future research directions and priorities.

1 Introduction

Borderline personality disorder (BPD) is a complex and severe psychiatric disorder characterized by mood dysregulation, interpersonal instability, self-image disturbance, and markedly impulsive behavior (e.g., aggression, self-injury, suicide) ( 1 ). In addition, people with BPD may have chronic, frequent, random feelings of emptiness, fear, and so on. These symptoms often lead them to use unhealthy coping mechanisms in response to negative emotions, such as alcohol abuse ( 2 ). BPD has a long course, which makes treatment difficult and may have a negative impact on patients’ quality of life ( 3 ). Due to its clinical challenge, BPD is by far the most studied category of personality disorder ( 4 ). This disorder is present in 1−3% of the general population as well as in 10% of outpatients, 15−20% of inpatients, and 30−60% of patients with a diagnosed personality disorder, and has a suicide rate of up to 10% ( 5 , 6 ). Families of individuals with serious mental illness often experience distress, and those with relatives diagnosed with BPD tend to carry a heavier burden compared to other mental illnesses ( 7 , 8 ). As early as the 20th century, scholars began describing BPD and summarizing its symptoms. However, there was some debate regarding the precise definition of BPD.

In the past few decades, the research community has made remarkable progress in the study of BPD, equipping us with a wider range of perspectives and tools for understanding this intricate condition. However, numerous challenges still remain to be tackled by researchers. Diagnosing BPD is inherently challenging and often more difficult than anticipated. The symptoms of BPD are complex, diverse, and often overlap with those of other mental health conditions. For example, individuals with BPD may experience extreme mood swings similar to those observed in individuals with bipolar disorder ( 9 ); At the same time, they may also be entrenched in long-term depression, making it easy for doctors to initially misdiagnose them with depression ( 10 ). Because these symptoms overlap and interfere with each other, doctors often face the risk of misdiagnosing or overlooking the condition during initial diagnosis. Therefore, researchers are working to develop more accurate and comprehensive diagnostic tools and methods.

According to the “Neuro-behavioral Model” proposed by Lieb ( 1 ), the process of BPD formation is very complex and is determined by the interaction of several factors. The interaction between different factors can be complex and dynamic. Genetic factors and adverse childhood experiences may contribute to emotional disorders and impulsivity, leading to dysfunctional behaviors and inner conflicts. These, in turn, can reinforce emotional dysregulation and impulsivity, exacerbating the preexisting conditions. Genetic factors are an important factor in the development of BPD ( 11 ). Psychosocial factors, including adverse childhood experiences, have also been strongly associated with the development of BPD ( 12 ). Emotional instability and impulsive behavior are even more common in patients with BPD ( 13 ). The current study is based on the “Neuro-behavioral Model” and conducts a literature review of previous scientific research on BPD through bibliometric analysis to reorganize the influencing factors. Through large-sample data analysis, the association between BPD and other diseases is explored, which contributes to further refining this theory’s explanation of the common neurobiological mechanisms among various mental illnesses.

It is worth noting that with the development of BPD, some scholars have conducted bibliometrics studies on BPD to provide insights into this academic field. To date, the current study has identified two published bibliometric studies on the field: One is Ilaria M. A. Benzi and her colleagues’ 2020 metrological analysis of the literature in the field of BPD pathology for the period 1985−2020 ( 14 ). The other is a bibliometric analysis by Taylor Reis and his colleagues of the growth and development of research on personality disorders between 1980 and 2019 ( 15 ). Ilaria M. A. Benzi and her colleagues integrated and sorted out the research results of borderline personality pathology, and revealed the research results and development stages in this field through the method of network and cluster analysis. The results of the study clearly demonstrate that the United States and European countries are the main contributors, that institutional citations are more consistent, and that BPD research is well developed in psychiatry and psychology. At the same time, the development of research in borderline personality pathology is demonstrated from the initial development of the construct, through studies of treatment effects, to the results of longitudinal studies. Taylor Reis and his colleagues used a time series autoregressive moving average model to analyze publishing trends for different personality disorders to reveal their historical development patterns, and projected the number of publications for the period 2024 to 2029. The study finds a trend towards diversity in the research and development of personality disorders, with differences in publication rates for different types of personality disorders, and summarizes the reasons that influence these differences. This may ultimately determine which personality disorders will remain in future psychiatric classifications. These studies have provided valuable insights into the evolution of BPD, focusing primarily on its pathology or a broader personality disorder perspective. While basic bibliometric analyses of these studies have been conducted, there is a need for more in-depth investigations of specific trends in the evolution of BPD and a clearer delineation of emerging research foci. Therefore, in order to enhance the current study, this study extends the analysis to 2022 and utilizes a comprehensive structural variation analysis of the literature using scientometric methods. Building on previous bibliometric studies, we expect to provide new insights and additions to research in this area. At the same time, the research trends and hot topics in the field of BPD are further explored. In addition, several cocitation-based analyses are also carried out in order to better understand citation performance.

2.1 Objectives

One of our goals was to understand the current status and progress of researches on BPD, and to summarize the latest developments and research findings in BPD, such as new treatment methods and disease mechanisms. Through the intuitive presentation of knowledge graphs and other images or data, we aimed to provide clinical practice and research guidance for clinicians, researchers, and policymakers.

Our second goal was to help identify future research directions and priorities, and provide more scientific and systematic research guidance for researchers. For example, by identifying hotspots and associations in certain research areas, we can determine the fields and issues that require further investigations, thus providing clearer directions and focus for researches. Additionally, through bibliometric analysis, we can provide researchers with more targeted and practical research strategies and methods, improving research efficiency and the quality of research outcomes.

2.2 Search strategy and data collection

The selection of appropriate methods and tools in the process of analyzing research information is crucial. Web of Science (WOS) is a popular database for bibliometric analysis that includes numerous respectable and high-impact academic journals. In addition, data information, such as references and citations, is more extensive than other academic databases ( 16 ). Data collection took place on the date of May 10, 2023. The search strategy included the following: topic=“Neuro-behavioral Model” or “borderline characteristics” or “borderline etiology” or “borderline personality disorder”, database selected=WOS Core Collection, time span=2003−2022, index=Science Citation Index Expanded (SCI-EXPENDED) and Social Sciences Citation Index (SSCI). The “Neuro-behavioral Model” serves as a theoretical framework that is useful for explaining the development and pathophysiology of BPD; “borderline characteristics” can describe the related symptoms and features of BPD; “borderline etiology” helps to understand the factors that contribute to the development of BPD; “borderline personality disorder” is the most commonly used terms in relevant research. Using these as keywords in title searches can help researchers find researches related to BPD more accurately, facilitating deeper understanding of the characteristics, pathophysiology, etiology, and other aspects of BPD. In the current study, we focused only on two types of literature: articles and review articles, and limited the language to English. After removing all literature unrelated to BPD, a total of 7919 records met the criteria. They were exported in record and reference formats, and saved in plain text file format.

2.3 Data analysis and tools

Bibliometrics was first proposed by Alan Pritchard in 1969, as a method that combines data visualization to analyze publications statistically and quantitatively in specific fields and journals ( 17 ). Bibliometric analysis is a good way to analyze the trend of knowledge structure and research activities in scientific fields over time, and has been widely used in various fields since it was first used ( 18 ). Scientometrics is the application of bibliometrics in scientific fields, and it focuses on the quantitative characteristics and features of science and scientific researches ( 19 ). Compared to traditional literature review studies, visualized knowledge graphs can accurately identify key articles from many publications, comprehensively and systematically combing existing research in a field ( 20 ).

Currently, two important academic indicators are included in research. The impact factor (IF) is used as an indicator of a publication’s impact to assess the quality and importance of the publication ( 21 ). However, some researchers believe that IF has defects such as inaccuracy and misuse ( 22 ). Although many researchers have proposed to replace the impact factor with other indicators, IF is still one of the most effective ways to measure the impact of a journal ( 23 ). The IF published in the 2021 Journal Citation Reports were used. Another indicator is the H-index, which is an important measure of a scholar’s academic achievements. Some researchers consider it as a correction or supplement to the traditional IF ( 24 ).

All data were imported into CiteSpace (6.2.R4) and Scimago Graphica (1.0.30) for analysis. CiteSpace was used to obtain collaboration networks and impact networks. Scimago Graphica was used to construct a network graph of country collaboration. CiteSpace is a Java-based software developed in the context of scientometrics and data visualization ( 25 ). It combines scientific knowledge mapping with bibliometric analysis to determine the progress and current research frontiers in a particular field, as well as predict the development trends in that field ( 26 ). Scimago Graphica is a no-code tool. It can not only perform visualization analysis on communication data but also explore exploratory data ( 27 ). Currently, it is used for visual analysis of national cooperation relationships, displaying the geographic distribution of countries and publication trends.

3.1 Analysis of publication outputs, and growth trend prediction

Annual publications can provide an overview of the evolution of a research area and its progress ( 28 ). We retrieved 7919 articles from the WOS database on BPD between 2003 and 2022, including 6834 research articles and 1085 reviews ( Figure 1 ). As of the search date, these articles had received a total of 289,958 citations, equating to an average of 14,498 citations per year. Over the past two decades, the number of research articles published on BPD has shown a fluctuating upward trend. In addition, citations to these publications have increased significantly. A polynomial curve fit of the literature on BPD clearly indicates a strong correlation between the year of publication and the number of publications ( R 2 = 0.973). The number of research articles on BPD has indeed fluctuated and increased over the past two decades. This observation does, to some extent, indicate an upward trend, probably due to increasing interest in BPD. However, there are other factors to consider as well. For example, the accumulation of data or technological advances, government policies and corporate investment may also affect the direction of BPD research development.

Figure 1 Annual publications, citation counts, and the fitting equation for annual publications in BPD.

3.2 Analysis of co-citation references: clusters and timeline of research

Co-cited references, which are cited by multiple papers concurrently, are considered a crucial knowledge base in any given field ( 28 ). In the current study, CiteSpace clustering was utilized to identify common themes within BPD-related literature. Figure 2 presented a co-citation network of highly cited references between 2003 and 2022, comprising 1163 references. A time slice of 1 was used, with the g -index was set at k =25, which resulted in the identification of 14 clusters representing distinct research themes in BPD. The significant cluster structure is denoted by a modularity value ( Q value) of 0.7974, and the high confidence level in the clusters by an average profile value ( S value) of 0.9176.

Figure 2 Reference co-citation network with cluster visualization in BPD. Trend 1 clinical researches, sub-trend clinical characteristics includes clusters #1, #2, #4, #10, #12; biological mechanisms include clusters #3, #7; nursing treatments includes clusters #0, #8, #13. Trend 2 associations and complications includes clusters #5, #6, #9, #11, #14.

Cluster analysis is performed through CiteSpace. Related clusters are classified into the same trend based on the knowledge of related fields and whether the clusters show similar trends. At the same time, based on the analysis of time series, to identify the movement of one cluster to another. Based on the cluster map of co-cited references on BPD, several different research trends were identified. The first major research trend is clinical research on BPD, which in turn consists of three sub-trends: clinical characterization of BPD, biological mechanisms, and nursing treatment. Of the data obtained, the earliest research on the clinical characterization of BPD began in 1992 with cluster #12, “borderline personality disorder and suicidal behavior” ( S =0.979; 1992). Paul H. Soloff and his colleagues conducted a comparative study of suicide attempts between major depressives and patients with BPD. The aim of this study was to develop more effective intervention strategies for suicide prevention ( 29 ). This cluster was further developed in cluster #4, “nonsuicidal self-injury and suicide” ( S =0.96; 2004). Thomas A. Widiger and Timothy J. Trull proposed a more flexible dimension-based categorization model to overcome the previous drawbacks of personality disorder categorization ( 30 ). Next in cluster #10 “borderline personality disorder and impulsivity” ( S =0.93; 2000), Jim H. Patton and his colleagues revised the Barratt Impulsivity Scale to measure impulsivity to facilitate practical clinical research ( 31 ). Related research continues to evolve into cluster #1 “borderline personality disorder and emotions” ( S =0.87; 2007) and cluster #2 “borderline personality disorder and social cognition” ( S =0.911; 2009), researchers have focused on understanding the causal relationship between BPD traits and factors such as social environment, emotion regulation, and interpersonal evaluative bias, as well as their potential impact ( 32 , 33 ). In the sub-trend of biological mechanisms, two main clusters are involved: cluster #7 “borderline personality disorder and gene-environment interactions” ( S =0.871; 2002) and cluster #3 “borderline personality disorder and neuroimaging” ( S =0.938; 2007). In the related cluster, researchers have found a relationship between BPD and genetic and environmental factors ( 34 ). Researchers have also utilized various external techniques to explore the degree of correlation between the risk of developing BPD and its biological mechanisms, aiming to reveal the complex mechanisms that influence the emergence and development of BPD ( 35 ). In nursing treatment, cluster #8 “treatment of borderline personality disorder “ ( S =0.968; 2001), Silvio Bellino and his colleagues systematically analyzed the current publications on BPD pharmacotherapy research and summarized relevant clinical trials and findings ( 36 ). However, due to the complexity of BPD, there is still a lack of information on the exact efficacy of pharmacotherapy in BPD, and therefore pharmacotherapy remains an area of ongoing development and research. This trend continues to be developed in cluster #0 “borderline personality disorder treatment” ( S =0.887; 2006), which emphasizes the development of novel pharmacotherapies for BPD. Cluster #13 “borderline personality disorder care” ( S =0.997; 2013) mainly focuses on the comprehensive care of people with borderline personality disorder and the education of patients and families. The goal is to improve patients’ quality of life, reduce self-injury and suicidal behavior, and promote full recovery.

The second major research trend is association and comorbidity. This trend first began in cluster #9 “comorbidity and differentiation of disorders” ( S =0.946; 1999). Mary C Zanarini and his colleagues explored the comorbidity of BPD with other psychiatric disorders on Axis I ( 37 ). Cluster #14 “borderline personality disorder and psychosis” ( S =0.966; 2003) also explored symptoms associated with BPD ( 38 ). This trend continues, with researchers studying BPD research in cluster #11 “borderline personality disorder” ( S =0.935; 2004) and cluster #5 “borderline personality disorder research” ( S =0.881; 2007) ( 39 , 40 ). In addition, cluster #6 “borderline personality disorder in adolescents” ( S =0.894; 2011) points out that the focus of BPD research is increasingly shifting towards adolescents ( 41 ).

Figure 3 showed the time span and research process of the developmental evolution of these different research themes. The temporal view reveals the newest and most active clusters, namely #0 “dialectical behavior therapy”, #1 “daily life”, and #2 “social cognition”, which have been consistently researched for almost a decade. Cluster #0 “dialectical behavior therapy” has the largest number and the longest duration, lasting almost 10 years. Similarly, this article by Rebekah Bradley and Drew Westen on understanding the psychodynamic mechanisms of BPD from the perspective of developmental psychopathology has the largest node ( 34 ).

Figure 3 Reference co-citation network with timeline visualization in BPD.

3.3 Most cited papers

The top 10 highly cited papers on BPD research were presented in Table 1 . The most cited paper, by Marsha M. Linehan and colleagues, focus on the treatment of suicidal behavior in BPD ( 42 ). The transition between suicidal and non-suicidal self-injurious behavior in individuals with BPD has attracted researchers’s attention, mainly in cluster #4 “nonsuicidal self-injury and suicide” ( 52 ). The second is the experimental study by Josephine Giesen-Bloo and his colleagues on the psychotherapy of BPD ( 43 ). In cluster #0 “borderline personality disorder treatment” and Cluster #8 “treatment of borderline personality disorder”, researchers strive to find non-pharmacological approaches with comparable or enhanced therapeutic effects. This was followed by Sheila E. Crowell and her colleagues’ study of the biological developmental patterns of BPD ( 44 ). Research on the biological mechanisms and other contributing factors of BPD, including #7 “borderline personality disorder and gene-environment interactions” have been closely associated with the development of BPD ( 53 ).

Table 1 Top 10 cited references that published BPD researches.

3.4 Burst analysis and transformative papers

The “citation explosion” reflects the changing research focus of a field over time and indicates that certain literature has been frequently cited over time. Figure 4 showed the top 9 references with the highest citation intensity. The three papers with the greatest intensity of outbursts during the period 2003−2022 are: The first is the American Psychiatric Association’s Diagnostic and Statistical Manual of Mental Disorders ( 54 ). In the second article, Vijay A. Mittal and Elaine F. Walker discuss key issues surrounding dyspraxia, tics, and psychosis that are likely to appear in an upcoming edition of the Diagnostic and Statistical Manual of Mental Disorders ( 39 ). In addition, Ioana A. Cristea and colleagues conducted a systematic review and meta-analysis to evaluate the effectiveness of psychotherapy for borderline personality disorder ( 55 ).

Figure 4 References with the strongest occurrence burst on BPD researches. Article titles correspond from top to bottom: Mittal VA et al. Diagnostic and Statistical Manuel of Mental Disorders; Linehan MM et al. Two-year randomized controlled trial and follow-up of dialectical behavior therapy vs therapy by experts for suicidal behaviors and borderline personality disorder; Giesen-Bloo J et al. Outpatient psychotherapy for borderline personality disorder: Randomized trial of schema-focused therapy vs transference-focused psychotherapy; Clarkin Jf et al. Evaluating three treatments for borderline personality disorder: A multiwave study; Grant BF et al. Prevalence, correlates, disability, and comorbidity of DSM-IV borderline personality disorder: Results from the Wave 2 National Epidemiologic Survey on Alcohol and Related Conditions; Leichsenring F et al. Borderline personality disorder; American Psychiatric Association, DSM-5 Task Force. Diagnostic and statistical manual of mental disorders: DSM-5™ (5th ed.); Cristea IA et al. Efficacy of psychotherapies for borderline personality disorder: A systematic review and meta-analysis; Gunderson JG et al. Borderline personality disorder.

Structural variation analysis can be understood as a method of measuring and studying structural changes in the field, mainly reflecting the betweenness centrality and sigma of the references. The high centrality of the reference plays an important role in the connection between the preceding and following references and may help to identify critical points of transformation, or intellectual turning points. Sigma values, on the other hand, are used to measure the novelty of a study, combining a combination of citation burst and structural centrality ( 56 ). Table 2 listed the top 10 structural change references that can be considered as landmark studies connecting different clusters. The top three articles with high centrality are the studies conducted by Milton Z. Brown and his colleagues on the reasons for suicide attempts and non-suicidal self-injury in BPD women ( 57 ); the research by Nelson H. Donegan and his colleagues on the impact of amygdala on emotional dysregulation in BPD patients ( 59 ); and the fMRI study by Sabine C. Herpertz and her colleagues on abnormal amygdala function in BPD patients ( 61 ). In addition, publications with high sigma values are listed. They are Larry J. Siever and Kenneth L. Davis on psychobiological perspectives on personality disorders ( 58 ); Ludger Tebartz van Elst and his colleagues on abnormalities in frontolimbic brain functioning ( 60 ); and Marsha M. Linehan on therapeutic approaches in BPD research ( 62 ). These works are recognized as having transformative potential and may generate some new ideas.

Table 2 Top 7 betweenness centrality and stigma references.

3.5 Analysis of authors and co-authors

Figure 5 showed a map of the co-authorship network over the last two decades. In total, 10 different clusters are shown, each of which gathers co-authors around the same research topic. For example, the main co-authors of cluster #0 “remission” are Christian Schmahl, Martin Bohus, Sabine C. Herpertz, Timothy J. Trull and Stefan Roepke. More recently, the three authors with the greatest bursts of research have been Mary C. Zanarini, Erik Simonsen, and Carla Sharp. As shown in Table 3 , the three most published authors are Martin Bohus (145 publications; 1.83%; H-index=61), Mary C. Zanarini (144 publications; 1.82%; H-index=80) and Christian Schmahl (142 publications; 1.79%; H-index=54).

Figure 5 Top 10 clusters of coauthors in BPD (2003–2023). Selection Criteria: Top 10 per slice. Clusters labeled by keywords. The five authors with the highest number of publications in each cluster were labeled.

Table 3 Top 10 authors that published BPD researches.

3.6 Analysis of cooperation networks across countries

The top 10 countries in terms of number of publications in the BPD are added in Table 4 . With 3,440 published papers, or nearly 43% of all BPD research papers, the United States is the leading contributor to BPD research. This is followed by Germany (1196 publications; 15.10%) and the United Kingdom (1020 publications; 9.32%). Centrality refers to the degree of importance or centrality of a node in a network and is a measure of the importance of a node in a network ( 69 ). In Table 4 the United States is also has the highest centrality (0.43). Figure 6 shows the geographic collaboration network of countries in this field, with 83 countries contributing to BPD research, primarily from the United States and Europe.

Table 4 Top 10 countries that published BPD researches.

Figure 6 Map of the distribution of countries/regions engaged in BPD researches.

3.7 Analysis of the co-author’s institutions network

Table 5 listed the top 10 institutions ranked by the number of publications. The current study shows that Research Libraries Uk is the institution with the highest number of publications, with 766 publications (9.67%). The subsequent institutions are Harvard University and Ruprecht Karls University Heidelberg with 425 (5.37%) and 389 (4.91%) publications respectively. As can be seen from Table 4 , six of the top 10 institutions in terms of number of publications are from the United States. In part, this reflects the fact that the United States institutions are at the forefront of the BPD field and play a key role in it.

Table 5 Top 10 institutions that published BPD researches.

3.8 Analysis of journals and cited journals

If the more papers are published in a particular journal and at the same time it has a high number of citations, then it can be considered that the journal is influential ( 70 ). The top 10 journals in the field of BPD in terms of number of publications are listed in Table 6 . Journal of Personality Disorders from the Netherlands published the most literature on BPD with 438 (5.53%; IF=3.367) publications. This was followed by two journals from the United States: Psychiatry Research and Personality Disorders Theory Research and Treatment , with 269 (3.40%, IF=11.225) and 232 (2.93%; IF=4.627) publications, respectively. Among the top 10 journals in terms of number of publications published, Psychiatry Research has the highest impact factor.

Table 6 Top 10 journals that published BPD researches.

3.9 Analysis of keywords and keywords co-occurrence

Keyword co-occurrence analysis can help researchers to understand the research hotspots in a certain field and the connection between different research topics. As shown in Figure 7 , all keywords can be categorized into 9 clusters: cluster #0 “diagnostic interview”, cluster #1 “diagnostic behavior therapy”, cluster #3 “social cognition”, cluster #4 “emotional regulation”, cluster #5 “substance use disorders “, cluster #6 “posttraumatic stress disorder”, cluster #7 “suicide” and cluster #8 “double blind”. These keywords have all been important themes in BPD research during the last 20 years.

Figure 7 The largest 9 clusters of co-occurring keywords. The top 5 most frequent keywords in each cluster are highlighted.

Keyword burst is used to identify keywords with a significant increase in the frequency of occurrence in a topic or domain, helping to identify emerging concepts, research hotspots or keyword evolutions in a specific domain ( 71 ). Figure 8 presented the top 32 keywords with the strongest citation bursts in BPD from 2003−2023. Significantly, the keywords “positron emission tomography” (29.63), “major depression” (27.93), and “partial hospitalization” (27.1) had the highest intensity of outbreaks.

Figure 8 Keywords with the strongest occurrence burst on BPD researches.

4 Discussion

4.1 application of the “neuro-behavioral model” to bpd research.

In this study, we chose specific search terms, particularly “Neuro-behavioral Model”, to efficiently collect and analyze BPD research literature related to this emerging framework. This choice of keyword helped narrow the research scope and ensure its relevance to our objectives. However, it may have excluded some studies using different terminology, thus limiting comprehensiveness. In addition, the ‘Neuro-behavioral Model’, as an interdisciplinary field, encompasses a wide range of connotations and extensions, which also poses challenges to our research. This undoubtedly adds to the complexity of the study, yet it enhances our understanding of the field’s diversity.

4.2 Summary of the main findings

This current study utilized CiteSpace and Scimago Graphic software to conduct a comprehensive bibliometric analysis of the research literature on BPD. The study presented the current status of research, research hotspots, and research frontiers in BPD over the past 20 years (2003–2022) through knowledge mapping. The scientific predictions of future trends in BPD provided by this study can guide researchers interested in this field. This study also uses bibliometrics analysis method to show the knowledge structure and research results in the field of BPD, as well as the scientific prediction of the future trend of BPD research.

4.3 Identification of research hotspots

Previous studies have indicated an increasing trend in the number of papers focused on BPD, with the field gradually expanding into various areas. The first major research trend involves clinical studies on BPD. This includes focusing on emotional recognition difficulties in BPD patients, as well as studying features related to suicide attempts and non-suicidal self-injury. Clinical recognition and confirmation of BPD remains low, mainly related to the lack of clarity of its biological mechanisms ( 72 ). The nursing environment for BPD patients plays an important role in the development of the condition, which has become a focus of research. Researchers are also exploring the expansion of treatment options from conventional medication to non-pharmacological approaches, particularly cognitive-behavioral therapy. Another major research trend involves the associations and complications of BPD, including a greater focus on the adolescent population to reduce the occurrence of BPD starting from adolescence. Additionally, many researchers are interested in the comorbidity of BPD with various clinical mental disorders.

4.4 Potential trends of future research on BPD

Based on the results of the above studies and the results of the research trends in the table of details of the co-citation network clusters in 2022 ( Table 7 ), several predictions are made for the future trends in the field of BPD. In Table 7 , there were some trends related to previous studies, including #1”dialectical behavior therapy”, #7 “dialectical behavior therapy” ( 73 ), #5 “mentalization” ( 74 ), and #9 “non-suicidal self-injury” ( 75 ). The persistence of these research trends is evidence that they have been a complex issue in this field and a focus of researchers. The recently emerged turning point paper provides a comprehensive assessment about BPD, offering practical information and treatment recommendations ( 76 ). New research is needed to improve standards and suggest more targeted and cost-effective treatments.

Table 7 The references co-citation network cluster detail (2022).

BPD symptoms in adolescents have been shown to respond to interventions with good results, so prevention and intervention for BPD is warranted ( 77 ). This trend can be observed in #3 “youth” ( 78 ). Mark F. Lenzenweger and Dante Cicchetti summarized the developmental psychopathology approach to BPD, one of the aims of which is to provide information for the prevention of BPD ( 79 ). Prevention and early intervention of BPD has been shown to provide many benefits, including reduced occurrence of secondary disorders, improved psychosocial functioning, and reduced risk of interpersonal conflict ( 80 ). However, there are differences between individuals, and different prevention goals are recommended for adolescents at risk for BPD. Therefore, prevention and early intervention for BPD has good prospects for the future.

The etiology of BPD is closely related to many factors, and its pathogenesis is often ignored by clinicians. The exploration of risk factors has been an important research direction in the study. Some studies have found that BPD is largely the product of traumatic childhood experiences, which may lead to negative psychological effects on children growing up ( 81 ). It has also been found that the severity of borderline symptoms in parents is positively associated with poor parenting practices ( 82 ). Future researches need to know more about the biological-behavioral processes of parents in order to provide targeted parenting support and create a good childhood environment.

Because pharmacotherapy is only indicated for comorbid conditions that require medication, psychotherapy has become one of the main approaches to treating BPD. The increasingly advanced performance and availability of contemporary mobile devices can help to take advantage of them more effectively in the context of optimizing the treatment of psychiatric disorders. The explosion of COVID-19 is forcing people to adapt to online rather than face-to-face offline treatment ( 83 ). The development of this new technology will effectively advance the treatment of patients with BPD. Although telemedicine has gained some level of acceptance by the general public, there are some challenges that have been reported, so further research on the broader utility of telemedicine is needed in the future.

4.5 The current study compares with a previous bibliometric review of BPD

As mentioned earlier, there have been previous bibliometric studies conducted by scholars in the field of BPD. This paper focuses more on BPD in personality disorders than the extensive study of personality disorders as a category by Taylor Reis et al. ( 15 ). The results of both studies show an increasing trend in the number of publications in the field of BPD, suggesting positive developments in the field. Taylor Reis et al. focused primarily on quantifying publications on personality disorders and did not delve into other specific aspects of BPD. Ilaria M.A. Benzi et al. focused on a bibliometric analysis of the pathology of BPD ( 14 ). They give three trends for the future development of BPD pathology: first, the growing importance of self-injurious behavior research; second, the association of attention deficit hyperactivity disorder with BPD and the influence of genetics and heritability on BPD; and third, the new focus on the overlap between fragile narcissism and BPD. The study in this paper also concludes that there are three future development directions for BPD: first, the prevention and early intervention of BPD; second, the non-pharmacological treatment of BPD; and third, research into the pathogenesis of BPD. Owing to variations in research backgrounds and data sources, the outcomes presented in the two studies diverge significantly. Nevertheless, both contributions hold merit in advancing the understanding of BPD. In addition to this, this paper also identifies trends in BPD over the past 20 years: the first trend is the clinical research of BPD, which is specifically subdivided into three sub-trends; the second trend is association and comorbidity. The identification of these trends is important for understanding the disorder, improving diagnosis and treatment, etc. Structural variant analysis also features prominently in the study. The impact of literature in terms of innovativeness is detected through in-depth mining and analysis of large amounts of literature data. This analysis is based on research in the area of scientific creativity, especially the role and impact of novel reorganizations in creative thinking. Structural variation analysis is precisely designed to find and reveal embodiments of such innovative thinking in scientific literature, enabling researchers to more intuitively grasp the dynamics and cutting-edge advances in the field of science.

5 Limitations

However, it must be admitted that our study has some limitations. The first is the limited nature of data resources. The data source for our study came from only one database, WOS. Second, the limitation of article type. Search criteria are limited to papers and reviews in SCI and SSCI databases. Third, the effect of language type. In the current study, only English-language literature could be included in the analysis, which may lead us to miss some important studies published in other languages. Fourth, limitations of research software. Although this study used well-established and specialized software, the results obtained by choosing different calculation methods may vary. Finally, the diversity of results interpretation. The results analyzed by the software are objective, but there is also some subjectivity in the interpretation and analysis of the research results. While we endeavor to be comprehensive and accurate in our research, the choice of search terms inevitably introduces certain limitations. Using “Neuro-behavioral Model” as the search term enhances the study’s relevance, but it may also cause us to miss significant studies in related areas. This limits the generalizability and replicability of our results. Furthermore, the inherent complexity and diversity of neurobehavioral models might introduce subjectivity and bias in our interpretation and application of the literature. Although we endeavored to reduce bias via multi-channel validation and cross-referencing, we cannot entirely eliminate its potential impact on our findings.

6 Conclusion

Overall, a comprehensive scientometrics analysis of BPD provides a comprehensive picture of the development of this field over the past 20 years. This in-depth examination not only reveals research trends, but also allows us to understand which areas are currently hot and points the way for future research efforts. In addition, this method provides us with a framework to evaluate the value of our own research results, which helps us to more precisely adjust the direction and strategy of research. More importantly, this in-depth analysis reveals the depth and breadth of BPD research, which undoubtedly provides valuable references for researchers to have a deeper understanding of BPD, and also provides a reference for us to set future research goals. In short, this scientometrics approach gives us a window into the full scope of BPD research and provides valuable guidance for future research.

Author contributions

YL: Data curation, Formal analysis, Investigation, Methodology, Software, Visualization, Writing – original draft, Writing – review & editing. CC: Conceptualization, Data curation, Formal analysis, Investigation, Methodology, Project administration, Resources, Software, Supervision, Validation, Visualization, Writing – original draft, Writing – review & editing. YZ: Validation, Visualization, Writing – review & editing. NZ: Conceptualization, Data curation, Formal analysis, Investigation, Methodology, Project administration, Software, Supervision, Validation, Visualization, Writing – original draft, Writing – review & editing. SL: Conceptualization, Data curation, Formal analysis, Funding acquisition, Investigation, Methodology, Project administration, Resources, Software, Supervision, Validation, Visualization, Writing – original draft, Writing – review & editing.

The author(s) declare that financial support was received for the research, authorship, and/or publication of this article. SL is supported by the Outstanding Youth Program of Philosophy and Social Sciences in Anhui Province (2022AH030089) and the Starting Fund for Scientific Research of High-Level Talents at Anhui Agricultural University (rc432206).

Conflict of interest

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Publisher’s note

All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article, or claim that may be made by its manufacturer, is not guaranteed or endorsed by the publisher.

1. Lieb K, Zanarini MC, Schmahl C, Linehan MM, Bohus M. Borderline personality disorder. Lancet (2004) 364:453–61. doi: 10.1016/S0140-6736(04)16770-6

PubMed Abstract | CrossRef Full Text | Google Scholar

2. Chugani CD, Byrd AL, Pedersen SL, Chung T, Hipwell AE, Stepp SD. Affective and sensation-seeking pathways linking borderline personality disorder symptoms and alcohol-related problems in young women. J Pers Disord . (2020) 34:420–31. doi: 10.1521/pedi_2018_32_389

3. Bagge CL, Stepp SD, Trull TJ. Borderline personality disorder features and utilization of treatment over two years. J Pers Disord . (2005) 19:420–39. doi: 10.1521/pedi.2005.19.4.420

4. Paris J. Suicidality in borderline personality disorder. Medicina . (2019) 55:223. doi: 10.3390/medicina55060223

5. Lenzenweger MF, Lane MC, Loranger AW, Kessler RC. DSM-IV personality disorders in the National Comorbidity Survey Replication. Biol Psychiatry . (2007) 62:553–64. doi: 10.1016/j.biopsych.2006.09.019

6. Skodol AE, Gunderson JG, Pfohl B, Widiger TA, Livesley WJ, Siever LJ. The borderline diagnosis I: Psychopathology, comorbidity, and personality structure. Biol Psychiatry . (2002) 51:936–50. doi: 10.1016/s0006-3223(02)01324-0

7. Bailey RC, Grenyer BF. Burden and support needs of carers of persons with borderline personality disorder: A systematic review. Harvard Rev Psychiatry . (2013) 21:248–58. doi: 10.1097/HRP.0b013e3182a75c2c

CrossRef Full Text | Google Scholar

8. Weimand BM, Hedelin B, Sällström C, Hall-Lord M-L. Burden and health in relatives of persons with severe mental illness: A Norwegian cross-sectional study. Issues Ment Health Nursing . (2010) 31:804–15. doi: 10.3109/01612840.2010.520819

9. Saccaro LF, Schilliger Z, Dayer A, Perroud N, Piguet C. Inflammation, anxiety, and stress in bipolar disorder and borderline personality disorder: A narrative review. Neurosci Biobehav Rev . (2021) 127:184−192. doi: 10.1016/j.neubiorev.2021.04.017

10. Dixon-Gordon KL, Laws H. Emotional variability and inertia in daily life: Links to borderline personality and depressive symptoms. J Pers Disord . (2021) 35:162−171. doi: 10.1521/pedi_2021_35_504

11. Torgersen S. Genetics of patients with borderline personality disorder. Psychiatr Clinics North A . (2000) 23:1–9. doi: 10.1016/S0193-953X(05)70139-8

12. Quenneville AF, Kalogeropoulou E, Küng AL, Hasler R, Nicastro R, Prada P, et al. Childhood maltreatment, anxiety disorders and outcome in borderline personality disorder. Psychiatry Res . (2020) 284:112688. doi: 10.1016/j.psychres.2019.112688

13. Antoine SM, Fredborg BK, Streiner D, Guimond T, Dixon-Gordon KL, Chapman AL, et al. Subgroups of borderline personality disorder: A latent class analysis. Psychiatry Res . (2023) 323:115131. doi: 10.1016/j.psychres.2023.115131

14. Benzi IMA, Di Pierro R, De Carli P, Cristea IA, Cipresso P. All the faces of research on borderline personality pathology: Drawing future trajectories through a network and cluster analysis of the literature. J Evidence-Based Psychotherapies . (2020) 20:3–30. doi: 10.24193/jebp.2020.2.9

15. Reis T, Gekker M, Land MGP, Mendlowicz MV, Berger W, Luz MP, et al. The growth and development of research on personality disorders: A bibliometric study. Pers Ment Health . (2022) 16:290–9. doi: 10.1002/pmh.1540

16. Singh VK, Singh P, Karmakar M, Leta J, Mayr P. The journal coverage of Web of Science, Scopus and Dimensions: A comparative analysis. Scientometrics . (2021) 126:5113–42. doi: 10.1007/s11192-021-03948-5

17. Pritchard A. Statistical bibliography or bibliometrics. J Documentation . (1969) 25:348.

Google Scholar

18. Price DJ. Networks of scientific papers. Science . (1965) 149:510–5. doi: 10.1126/science.149.3683.510

19. Sabe M, Chen C, Perez N, Solmi M, Mucci A, Galderisi S, et al. Thirty years of research on negative symptoms of schizophrenia: A scientometric analysis of hotspots, bursts, and research trends. Neurosci Biobehav Rev . (2023) 144:104979. doi: 10.1016/j.neubiorev.2022.104979

20. Shen Z, Ji W, Yu S, Cheng G, Yuan Q, Han Z, et al. Mapping the knowledge of traffic collision reconstruction: A scientometric analysis in CiteSpace, VOSviewer, and SciMAT. Sci Justice . (2023) 63:19–37. doi: 10.1016/j.scijus.2022.10.005

21. Wu H, Wang Y, Tong L, Yan H, Sun Z. Global research trends of ferroptosis: A rapidly evolving field with enormous potential. Front Cell Dev Biol . (2021) 9:646311. doi: 10.3389/fcell.2021.646311

22. Brody S. Impact factor: Imperfect but not yet replaceable. Scientometrics . (2013) 96:255–7. doi: 10.1007/s11192-012-0863-x

23. Kaldas M, Michael S, Hanna J, Yousef GM. Journal impact factor: A bumpy ride in an open space. J Invest Med . (2020) 68:83–7. doi: 10.1136/jim-2019-001009

24. Schubert A, Glänzel W. A systematic analysis of Hirsch-type indices for journals. J Informetrics . (2007) 1:179–84. doi: 10.1016/j.joi.2006.12.002

25. Chen C. CiteSpace II: Detecting and visualizing emerging trends and transient patterns in scientific literature. J Am Soc Inf Sci Technol . (2006) 57:359–77. doi: 10.1002/asi.20317

26. Cheng K, Guo Q, Shen Z. Bibliometric analysis of global research on cancer photodynamic therapy: Focus on nano-related research. Front Pharmacol . (2022) 13:927219. doi: 10.3389/fphar.2022.927219

27. Hassan-Montero Y, De-Moya-Anegón F, Guerrero-Bote VP. SCImago Graphica: A new tool for exploring and visually communicating data. Profesional la Información . (2022) 31:e310502. doi: 10.3145/EPI

28. Wang Y, Li D, Jia Z, Hui J, Xin Q, Zhou Q, et al. A bibliometric analysis of research on the links between gut microbiota and atherosclerosis. Front Cardiovasc Med . (2022) 9:941607. doi: 10.3389/fcvm.2022.941607

29. Soloff PH, Lynch KG, Kelly TM, Malone KM, Mann JJ. Characteristics of suicide attempts of patients with major depressive episode and borderline personality disorder: a comparative study. Am J Psychiatry . (2000) 157:601–8. doi: 10.1176/appi.ajp.157.4.601

30. Widiger TA, Trull TJ. Plate tectonics in the classification of personality disorder: shifting to a dimensional model. Am Psychol . (2007) 62:71–83. doi: 10.1037/0003-066X.62.2.71

31. Patton JH, Stanford MS, Barratt ES. Factor structure of the Barratt impulsiveness scale. J Clin Psychol . (1995) 51:768–74. doi: 10.1002/1097-4679(199511)51:6<768::aid-jclp2270510607>3.0.co;2-1

32. Bartow S, Stopsack M, Grabe HJ, Meinke C, Spitzer C, Kronmüller K, et al. Interpersonal evaluation bias in borderline personality disorder. Behav Res Ther . (20092009) 47:359–65. doi: 10.1016/j.brat.2009.02.003

33. Cheavens JS, Rosenthal MZ, Daughters SB, Nowak J, Kosson D, Lynch TR, et al. An analogue investigation of the relationships among perceived parental criticism, negative affect, and borderline personality disorder features: The role of thought suppression. Behav Res Ther . (2005) 43:257–68. doi: 10.1016/j.brat.2004.01.006

34. Bradley R, Westen D. The psychodynamics of borderline personality disorder: a view from developmental psychopathology. Dev Psychopathol . (2005) 17:927–57. doi: 10.1017/s0954579405050443

35. Tzourio-Mazoyer N, Landeau B, Papathanassiou D, Crivello F, Etard O, Delcroix N, et al. Automated anatomical labeling of activations in SPM using a macroscopic anatomical parcellation of the MNI MRI single-subject brain. NeuroImage . (2002) 15:273–89. doi: 10.1006/nimg.2001.0978

36. Bellino S, Rinaldi C, Bozzatello P, Bogetto F. Pharmacotherapy of borderline personality disorder: a systematic review for publication purpose. Curr Medicinal Chem . (2011) 18:3322–9. doi: 10.2174/092986711796504682

37. Zanarini MC, Frankenburg FR, Dubo ED, Sickel AE, Trikha A, Levin A. Axis I comorbidity of borderline personality disorder. Am J Psychiatry . (1998) 155:1733–9. doi: 10.1176/ajp.155.12.1733

38. Yee L, Korner AJ, McSwiggan S, Meares RA, Stevenson J. Persistent hallucinosis in borderline personality disorder. Compr Psychiatry . (2005) 46:147–54. doi: 10.1016/j.comppsych.2004.07.032

39. Mittal VA, Walker EF. Diagnostic and statistical manual of mental disorders. Psychiatry Res . (2011) 189:158–9. doi: 10.1016/j.psychres.2011.06.006

40. Torgersen S, Kringlen E, Cramer V. The prevalence of personality disorders in a community sample. Arch Gen Psychiatry . (2001) 58:590–6. doi: 10.1001/archpsyc.58.6.590

41. Crick NR, Murray-Close D, Woods K. Borderline personality features in childhood: A short-term longitudinal study. Dev Psychopathol . (2005) 17:1051–70. doi: 10.1017/S0954579405050492

42. Linehan MM, Comtois KA, Murray AM, Brown MZ, Gallop RJ, Heard HL, et al. Two-year randomized controlled trial and follow-up of dialectical behavior therapy vs therapy by experts for suicidal behaviors and borderline personality disorder. Arch Gen Psychiatry . (2006) 63:757–66. doi: 10.1001/archpsyc.63.7.757

43. Giesen-Bloo J, van Dyck R, Spinhoven P, van Tilburg W, Dirksen C, van Asselt T, et al. Outpatient psychotherapy for borderline personality disorder: Randomized trial of schema-focused therapy vs transference-focused psychotherapy. Arch Gen Psychiatry . (2006) 63:649–58. doi: 10.1001/archpsyc.63.6.649

44. Crowell SE, Beauchaine TP, Linehan MM. A biosocial developmental model of borderline personality: Elaborating and extending Linehan's theory. psychol Bulletin . (2009) 135:495–510. doi: 10.1037/a0015616

45. Leichsenring F, Leibing E, Kruse J, New AS, Leweke F. Borderline personality disorder. Lancet (2011) 377(9759):74–84. doi: 10.1016/S0140-6736(10)61422-5

46. Whiteside SP, Lynam DR, Miller JD, Reynolds SK. Validation of the UPPS impulsive behaviour scale: A four-factor model of impulsivity. Eur J Pers (2005) 19(7):559–74. doi: 10.1002/per.556

47. Clarkin JF, Levy KN, Lenzenweger MF, Kernberg OF. Evaluating three treatments for borderline personality disorder: A multiwave study. Am J Psychiatry (2007) 164(6):922–8. doi: 10.1176/ajp.2007.164.6.922

48. Bateman A, Fonagy P. Randomized controlled trial of outpatient mentalization-based treatment versus structured clinical management for borderline personality disorder. Am J Psychiatry (2009) 166(12):1355–64. doi: 10.1176/appi.ajp.2009.09040539

49. Fonagy P, Luyten P. A developmental, mentalization-based approach to the understanding and treatment of borderline personality disorder. Dev Psychopathol (2009) 21(4):1355–81. doi: 10.1017/S0954579409990198

50. Levy KN, Meehan KB, Kelly KM, Reynoso JS, Weber M, Clarkin JF, et al. Change in attachment patterns and reflective function in a randomized control trial of transference-focused psychotherapy for borderline personality disorder. J Consulting Clin Psychol (2006) 74(6):1027–40. doi: 10.1037/0022-006X.74.6.1027

51. Carr DS, Francis A. Childhood familial environment, maltreatment and borderline personality disorder symptoms in a non-clinical sample: A cognitive behavioural perspective. Clin Psychol (2009) 13(1):28–37. doi: 10.1080/13284200802680476

52. Selby EA, Kranzler A, Fehling KB, Panza E. Nonsuicidal self-injury disorder: The path to diagnostic validity and final obstacles. Clin Psychol Review . (2015) 38:79–91. doi: 10.1016/j.cpr.2015.03.003

53. Skoglund C, Tiger A, Rück C, Petrovic P, Asherson P, Hellner C, et al. Familial risk and heritability of diagnosed borderline personality disorder: A register study of the Swedish population. Mol Psychiatry . (2021) 26:999–1008. doi: 10.1038/s41380-019-0442-0

54. American Psychiatric Association, DSM-5 Task Force. Diagnostic and statistical manual of mental disorders: DSM-5™ . 5th ed. Washington: American Psychiatric Publishing, Inc., (2013). doi: 10.1176/appi.books.9780890425596

55. Cristea IA, Gentili C, Cotet CD, Palomba D, Barbui C, Cuijpers P. Efficacy of psychotherapies for borderline personality disorder: A systematic review and meta-analysis. JAMA Psychiatry . (2017) 74:319–28. doi: 10.1001/jamapsychiatry.2016.4287

56. Chen C. Predictive effects of structural variation on citation counts. J Am Soc Inf Sci Technol . (2012) 63:431–49. doi: 10.1002/asi.21694

57. Brown MZ, Comtois KA, Linehan MM. Reasons for suicide attempts and non-suicidal self-injury in women with borderline personality disorder. J Abnormal Psychol . (2002) 111:198–202. doi: 10.1037//0021-843x.111.1.198

58. Siever LJ, Davis KL. A psychobiological perspective on the personality disorders. Am J Psychiatry . (1991) 148:1647–58. doi: 10.1176/ajp.148.12.1647

59. Donegan NH, Sanislow CA, Blumberg HP. Amygdala hyperreactivity in borderline personality disorder: Implications for emotional dysregulation. Biol Psychiatry . (2003) 54:1284–93. doi: 10.1016/S0006-3223(03)00636-X

60. Tebartz van Elst L, Hesslinger B, Thiel T, Geiger E, Haegele K, Lemieux L, et al. Frontolimbic brain abnormalities in patients with borderline personality disorder: A volumetric magnetic resonance imaging study. Biol Psychiatry . (2003) 54:163–71. doi: 10.1016/s0006-3223(02)01743-2

61. Herpertz SC, Dietrich TM, Wenning B, Krings T, Erberich SG, Willmes K, et al. Evidence of abnormal amygdala functioning in borderline personality disorder: A functional MRI study. Biol Psychiatry . (2001) 50:292–8. doi: 10.1016/S0006-3223(01)01075-7

62. Linehan MM. Cognitive-behavioral treatment of borderline personality disorder . New York: Guilford Press (1993).

63. Black DW, Blum N, Pfohl B, Hale N. Suicidal behavior in borderline personality disorder: Prevalence, risk factors, prediction, and prevention. J Pers Disord (2004) 18(3):226–39. doi: 10.1521/pedi.18.3.226.35445

64. Brambilla P, Soloff PH, Sala M, Nicoletti MA, Keshavan MS, Soares JC. Anatomical MRI study of borderline personality disorder patients. Psychiatry Res (2004) 131(2):125–33. doi: 10.1016/j.pscychresns.2004.04.003

65. Stiglmayr CE, Grathwol T, Linehan MM, Ihorst G, Fahrenberg J, Bohus M. Aversive tension in patients with borderline personality disorder: A computer-based controlled field study. Acta Psychiatrica Scandinavica (2005) 111(5):372–9. doi: 10.1111/j.1600-0447.2004.00466.x

66. Silbersweig D, Clarkin JF, Goldstein M, Kernberg OF, Tuescher O, Levy KN, et al. Failure of frontolimbic inhibitory function in the context of negative emotion in borderline personality disorder. Am J Psychiatry (2007) 164(12):18321841. doi: 10.1176/appi.ajp.2007.06010126

67. Bohus M, Haaf B, Stiglmayr C, Pohl U, Böhme R, Linehan M. Evaluation of inpatient dialectical-behavioral therapy for borderline personality disorder–a prospective study. Behav Res Ther (2000) 38(9):875887. doi: 10.1016/s0005-7967(99)00103-5

68. Rossouw TI, Fonagy P. Mentalization-based treatment for self-harm in adolescents: a randomized controlled trial. J Am Acad Child Adolesc Psychiatry (2012) 51(12):13041313. doi: 10.1016/j.jaac.2012.09.018

69. Zhang S, Wang S, Liu R. A bibliometric analysis of research trends of artificial intelligence in the treatment of autistic spectrum disorders. Front Psychiatry . (2022) 13:967074. doi: 10.3389/fpsyt.2022.967074

70. Dzikowski P. A bibliometric analysis of born global firms. J Business Res . (2018) 85:281–94. doi: 10.1016/j.jbusres.2017.12.054

71. Chen C, Ibekwe-SanJuan F, Hou J. The structure and dynamics of cocitation clusters: A multiple-perspective cocitation analysis. J Am Soc Inf Sci Technol . (2010) 61:1386–409. doi: 10.1002/asi.21309

72. Gunderson JG, Herpertz SC, Skodol AE, Torgersen S, Zanarini MC. Borderline personality disorder. Nat Rev Dis Primers . (2018) 4:18029. doi: 10.1038/nrdp.2018.29

73. Tan MYL, McConnell B, Barlas J. Application of Dialectical Behaviour Therapy in treating common psychiatric disorders: Study protocol for a scoping review. BMJ Open . (2002) 12:e058565. doi: 10.1136/bmjopen–2021–058565

74. Quevedo Y, Booij L, Herrera L, Hernández C, Jiménez JP. Potential epigenetic mechanisms in psychotherapy: A pilot study on DNA methylation and mentalization change in borderline personality disorder. Front Hum Neurosci . (2022) 16:955005. doi: 10.3389/fnhum.2022.955005

75. Uhlmann C, Tschöke S, Steinert T, Schmid P. Can you see and hear how bad I feel right now? Self–injury and suicidal communication in borderline personality disorder-A secondary analysis. Psychiatrische Praxis . (2022) 49:329–33. doi: 10.1055/a–1820–0438

76. Bohus M, Stoffers-Winterling J, Sharp C, Krause-Utz A, Schmahl C, Lieb K. Borderline personality disorder. Lancet (2022) 398:1528–40. doi: 10.1016/S0140–6736(21)00476–1

77. Schuppert HM, Giesen-Bloo J, van Gemert TG, Wiersema HM, Minderaa RB, Emmelkamp PMG, et al. Effectiveness of an emotion regulation group training for adolescents—A randomized controlled pilot study. Clin Psychol Psychother . (2009) 16:467–78. doi: 10.1002/cpp.637

78. American Psychiatric Association. Diagnostic and statistical manual of mental disorders, text revision . 4th ed. Washington: American Psychiatric Association (2000).

79. Lenzenweger MF, Cicchetti D. Toward a developmental psychopathology approach to borderline personality disorder. Dev Psychopathol . (2005) 17:893–8. doi: 10.1017/S095457940505042X

80. Chanen AM, Jovev M, McCutcheon LK, Jackson HJ, McGorry PD. Borderline personality disorder in young people and the prospects for prevention and early intervention. Curr Psychiatry Rev . (2008) 4:48–57. doi: 10.2174/157340008783743820

81. Pohl S, Steuwe C, Mainz V, Driessen M, Beblo T. Borderline personality disorder and childhood trauma: Exploring the buffering role of self-compassion and self-esteem. J Clin Psychol . (2021) 77:837–45. doi: 10.1002/jclp.23070

82. Bartsch DR, Roberts R, Proeve M. Relationships between parental borderline symptom severity, empathy, parenting styles and child psychopathology. Clin Psychol . (2022) 26:211–21. doi: 10.1080/13284207.2022.2031947

83. Lakeman R, Hurley J, Campbell K, Hererra C, Leggett A, Tranter R, et al. High fidelity dialectical behaviour therapy online: Learning from experienced practitioners. Int J Ment Health Nursing . (20222022) 31:1405–16. doi: 10.1111/inm.13039

Keywords: neuro-behavioral model, borderline personality disorder, BPD, bibliometric, Scimago Graphica

Citation: Liu Y, Chen C, Zhou Y, Zhang N and Liu S (2024) Twenty years of research on borderline personality disorder: a scientometric analysis of hotspots, bursts, and research trends. Front. Psychiatry 15:1361535. doi: 10.3389/fpsyt.2024.1361535

Received: 12 January 2024; Accepted: 19 February 2024; Published: 01 March 2024.

Reviewed by:

Copyright © 2024 Liu, Chen, Zhou, Zhang and Liu. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

*Correspondence: Shen Liu, [email protected] ; Chaomei Chen, [email protected] ; Na Zhang, [email protected]

Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.

Featured Clinical Reviews

• Screening for Atrial Fibrillation: US Preventive Services Task Force Recommendation Statement JAMA Recommendation Statement January 25, 2022
• Evaluating the Patient With a Pulmonary Nodule: A Review JAMA Review January 18, 2022
• Download PDF
• CME & MOC
• Share X Facebook Email LinkedIn
• Permissions

Borderline Personality Disorder : A Review

• 1 Department of Psychosomatics and Psychotherapy, University of Giessen, Giessen, Germany
• 2 Department of Psychosomatics and Psychotherapy, University of Rostock, Rostock, Germany
• 3 International Psychoanalytic University, Berlin, Germany
• 4 Weill Cornell Medical College, Personality Disorders Institute, New York, New York
• JAMA Patient Page Patient Information: Borderline Personality Disorder Jill Jin, MD, MPH JAMA
• Original Investigation Association of Borderline Personality Disorder Criteria With Suicide Attempts Shirley Yen, PhD; Jessica R. Peters, PhD; Shivani Nishar, ScB; Carlos M. Grilo, PhD; Charles A. Sanislow, PhD; M. Tracie Shea, PhD; Mary C. Zanarini, EdD; Thomas H. McGlashan, MD; Leslie C. Morey, PhD; Andrew E. Skodol, MD JAMA Psychiatry
• Original Investigation Effect of 3 Forms of Early Intervention for Young People With Borderline Personality Disorder Andrew M. Chanen, MBBS(Hons), PhD; Jennifer K. Betts, DPsych(Clin); Henry Jackson, PhD; Sue M. Cotton, MAppSc(Statistics), PhD; John Gleeson, PhD; Christopher G. Davey, MBBS(Hons), PhD; Katherine Thompson, PhD; Sharnel Perera, PhD; Victoria Rayner, BBSci(Hons); Holly Andrewes, PhD; Louise McCutcheon, DPsych(Clin) JAMA Psychiatry

Importance   Borderline personality disorder (BPD) affects approximately 0.7% to 2.7% of adults in the US. The disorder is associated with considerable social and vocational impairments and greater use of medical services.

Observations   Borderline personality disorder is characterized by sudden shifts in identity, interpersonal relationships, and affect, as well as by impulsive behavior, periodic intense anger, feelings of emptiness, suicidal behavior, self-mutilation, transient, stress-related paranoid ideation, and severe dissociative symptoms (eg, experience of unreality of one’s self or surroundings). Borderline personality disorder is typically diagnosed by a mental health specialist using semistructured interviews. Most people with BPD have coexisting mental disorders such as mood disorders (ie, major depression or bipolar disorder) (83%), anxiety disorders (85%), or substance use disorders (78%). The etiology of BPD is related to both genetic factors and adverse childhood experiences, such as sexual and physical abuse. Psychotherapy is the treatment of choice for BPD. Psychotherapy such as dialectical behavior therapy and psychodynamic therapy reduce symptom severity more than usual care, with medium effect sizes (standardized mean difference) between −0.60 and −0.65. There is no evidence that any psychoactive medication consistently improves core symptoms of BPD. For discrete and severe comorbid mental disorders, eg, major depression, pharmacotherapy such as the selective serotonin reuptake inhibitors escitalopram, sertraline, or fluoxetine may be prescribed. For short-term treatment of acute crisis in BPD, consisting of suicidal behavior or ideation, extreme anxiety, psychotic episodes, or other extreme behavior likely to endanger a patient or others, crisis management is required, which may include prescription of low-potency antipsychotics (eg, quetiapine) or off-label use of sedative antihistamines (eg, promethazine). These drugs are preferred over benzodiazepines such as diazepam or lorazepam.

Conclusions and Relevance   Borderline personality disorder affects approximately 0.7% to 2.7% of adults and is associated with functional impairment and greater use of medical services. Psychotherapy with dialectical behavior therapy and psychodynamic therapy are first-line therapies for BPD, while psychoactive medications do not improve the primary symptoms of BPD.

Read More About

Leichsenring F , Heim N , Leweke F , Spitzer C , Steinert C , Kernberg OF. Borderline Personality Disorder : A Review . JAMA. 2023;329(8):670–679. doi:10.1001/jama.2023.0589

Manage citations:

© 2024

Artificial Intelligence Resource Center

Cardiology in JAMA : Read the Latest

Browse and subscribe to JAMA Network podcasts!

Others Also Liked

Select your interests.

Customize your JAMA Network experience by selecting one or more topics from the list below.

• Academic Medicine
• Acid Base, Electrolytes, Fluids
• Allergy and Clinical Immunology
• American Indian or Alaska Natives
• Anesthesiology
• Anticoagulation
• Art and Images in Psychiatry
• Artificial Intelligence
• Assisted Reproduction
• Bleeding and Transfusion
• Caring for the Critically Ill Patient
• Challenges in Clinical Electrocardiography
• Climate and Health
• Climate Change
• Clinical Challenge
• Clinical Decision Support
• Clinical Implications of Basic Neuroscience
• Clinical Pharmacy and Pharmacology
• Complementary and Alternative Medicine
• Consensus Statements
• Coronavirus (COVID-19)
• Critical Care Medicine
• Cultural Competency
• Dental Medicine
• Dermatology
• Diabetes and Endocrinology
• Diagnostic Test Interpretation
• Drug Development
• Electronic Health Records
• Emergency Medicine
• End of Life, Hospice, Palliative Care
• Environmental Health
• Equity, Diversity, and Inclusion
• Facial Plastic Surgery
• Gastroenterology and Hepatology
• Genetics and Genomics
• Genomics and Precision Health
• Global Health
• Guide to Statistics and Methods
• Hair Disorders
• Health Care Delivery Models
• Health Care Economics, Insurance, Payment
• Health Care Quality
• Health Care Reform
• Health Care Safety
• Health Care Workforce
• Health Disparities
• Health Inequities
• Health Policy
• Health Systems Science
• History of Medicine
• Hypertension
• Images in Neurology
• Implementation Science
• Infectious Diseases
• Innovations in Health Care Delivery
• JAMA Infographic
• Law and Medicine
• Leading Change
• Less is More
• LGBTQIA Medicine
• Lifestyle Behaviors
• Medical Coding
• Medical Devices and Equipment
• Medical Education
• Medical Education and Training
• Medical Journals and Publishing
• Mobile Health and Telemedicine
• Narrative Medicine
• Neuroscience and Psychiatry
• Notable Notes
• Nutrition, Obesity, Exercise
• Obstetrics and Gynecology
• Occupational Health
• Ophthalmology
• Orthopedics
• Otolaryngology
• Pain Medicine
• Palliative Care
• Pathology and Laboratory Medicine
• Patient Care
• Patient Information
• Performance Improvement
• Performance Measures
• Perioperative Care and Consultation
• Pharmacoeconomics
• Pharmacoepidemiology
• Pharmacogenetics
• Pharmacy and Clinical Pharmacology
• Physical Medicine and Rehabilitation
• Physical Therapy
• Physician Leadership
• Population Health
• Primary Care
• Professional Well-being
• Professionalism
• Psychiatry and Behavioral Health
• Public Health
• Pulmonary Medicine
• Regulatory Agencies
• Reproductive Health
• Research, Methods, Statistics
• Resuscitation
• Rheumatology
• Risk Management
• Scientific Discovery and the Future of Medicine
• Shared Decision Making and Communication
• Sleep Medicine
• Sports Medicine
• Stem Cell Transplantation
• Substance Use and Addiction Medicine
• Surgical Innovation
• Surgical Pearls
• Teachable Moment
• Technology and Finance
• The Art of JAMA
• The Arts and Medicine
• The Rational Clinical Examination
• Tobacco and e-Cigarettes
• Translational Medicine
• Trauma and Injury
• Treatment Adherence
• Ultrasonography
• Users' Guide to the Medical Literature
• Vaccination
• Venous Thromboembolism
• Veterans Health
• Women's Health
• Workflow and Process
• Wound Care, Infection, Healing
• Register for email alerts with links to free full-text articles
• Access PDFs of free articles
• Manage your interests
• Save searches and receive search alerts

• Study protocol
• Open access
• Published: 05 February 2022

Towards optimal treatment selection for borderline personality disorder patients (BOOTS): a study protocol for a multicenter randomized clinical trial comparing schema therapy and dialectical behavior therapy

• Carlijn J. M. Wibbelink 1 ,
• Arnoud Arntz 1 ,
• Raoul P. P. P. Grasman 1 ,
• Roland Sinnaeve 2 ,
• Michiel Boog 3 , 4 ,
• Odile M. C. Bremer 5 ,
• Eliane C. P. Dek 6 ,
• Sevinç Göral Alkan 7 ,
• Chrissy James 8 ,
• Annemieke M. Koppeschaar 9 ,
• Linda Kramer 10 ,
• Maria Ploegmakers 11 ,
• Arita Schaling 12 ,
• Faye I. Smits 13 &
• Jan H. Kamphuis 1  

BMC Psychiatry volume  22 , Article number:  89 ( 2022 ) Cite this article

10k Accesses

7 Citations

14 Altmetric

Metrics details

Specialized evidence-based treatments have been developed and evaluated for borderline personality disorder (BPD), including Dialectical Behavior Therapy (DBT) and Schema Therapy (ST). Individual differences in treatment response to both ST and DBT have been observed across studies, but the factors driving these differences are largely unknown. Understanding which treatment works best for whom and why remain central issues in psychotherapy research. The aim of the present study is to improve treatment response of DBT and ST for BPD patients by a) identifying patient characteristics that predict (differential) treatment response (i.e., treatment selection) and b) understanding how both treatments lead to change (i.e., mechanisms of change). Moreover, the clinical effectiveness and cost-effectiveness of DBT and ST will be evaluated.

The BOOTS trial is a multicenter randomized clinical trial conducted in a routine clinical setting in several outpatient clinics in the Netherlands. We aim to recruit 200 participants, to be randomized to DBT or ST. Patients receive a combined program of individual and group sessions for a maximum duration of 25 months. Data are collected at baseline until three-year follow-up. Candidate predictors of (differential) treatment response have been selected based on the literature, a patient representative of the Borderline Foundation of the Netherlands, and semi-structured interviews among 18 expert clinicians. In addition, BPD-treatment-specific (ST: beliefs and schema modes; DBT: emotion regulation and skills use), BPD-treatment-generic (therapeutic environment characterized by genuineness, safety, and equality), and non-specific (attachment and therapeutic alliance) mechanisms of change are assessed. The primary outcome measure is change in BPD manifestations. Secondary outcome measures include functioning, additional self-reported symptoms, and well-being.

The current study contributes to the optimization of treatments for BPD patients by extending our knowledge on “Which treatment – DBT or ST – works the best for which BPD patient, and why?”, which is likely to yield important benefits for both BPD patients (e.g., prevention of overtreatment and potential harm of treatments) and society (e.g., increased economic productivity of patients and efficient use of treatments).

Trial registration

Netherlands Trial Register, NL7699 , registered 25/04/2019 - retrospectively registered.

Peer Review reports

Borderline personality disorder (BPD) is a complex and severe mental disorder, characterized by a pervasive pattern of instability in emotion regulation, self-image, interpersonal relationships, and impulse control [ 1 , 2 ]. The prevalence in the general population is estimated to be between 1 and 3% [ 3 , 4 , 5 ], and 10 to 25% among psychiatric outpatient and inpatient individuals [ 3 ]. BPD is associated with severe functional impairment, high rates of comorbid mental disorders, and physical health problems [ 5 , 6 , 7 ]. In addition, BPD is characterized by low quality of life; lower compared to other common mental disorders such as depressive disorder, and comparable to that of patients with severe physical conditions, such as Parkinson’s disease and stroke [ 8 ]. Moreover, BPD is related to a high risk of suicide (3–6%, or even up to 10% [ 9 , 10 ]) and suicide attempts or threats (up to 84% [ 11 , 12 ]), and an increased mortality rate [ 13 ]. Besides the detrimental effects of BPD on the individual patient, BPD also poses a high financial burden to society. BPD patients make extensive use of treatment services resulting in markedly higher healthcare costs of people with BPD compared to people with other mental disorders, such as other personality disorders [ 14 ] and depressive disorder [ 15 ]. BPD is also associated with high non-healthcare costs, including costs related to productivity losses, informal care, and out-of-pocket costs [ 16 , 17 ].

Interventions: dialectical behavior therapy and schema therapy

BPD has traditionally been viewed as one of the most difficult mental disorders to treat [ 18 ]. During recent years, a number of promising treatments have been developed and evaluated, including Dialectical Behavior Therapy (DBT) [ 19 , 20 ] and Schema Therapy (ST) [ 21 , 22 ]. DBT is a comprehensive cognitive behavioral treatment for BPD, rooted in behaviorism, Zen and dialectical philosophy [ 19 ]. ST is based on an integrative cognitive therapy, combining cognitive behavior and experiential therapy techniques with concepts derived from developmental theories, including attachment theory, and psychodynamic concepts [ 23 ]. For detailed information about these treatments, the reader is referred to the Methods/design section.

Several studies have demonstrated the effectiveness and the efficacy of DBT and ST for BPD, although the evidence is mostly based on low-to-moderate-quality evidence, and trials focusing on DBT, but especially ST, are limited [ 24 , 25 ]. In addition, substantial reductions in direct and indirect healthcare costs have been found for both treatments [ 26 ]. However, research on the comparative effectiveness and cost-effectiveness of the two interventions is lacking. Moreover, research on mediators and moderators of treatment effects is limited. This gap warrants attention, as treatment effectiveness can be optimized by identifying mechanisms within treatments that are associated with improvement and patient characteristics that predict (differential) treatment response [ 27 ]. Optimizing treatment effectiveness of DBT and ST for BPD is highly needed since a substantial proportion of patients does not respond fully to either DBT or ST. A systematic review found a mean percentage of non-response of 46% among BPD patients treated with specialized psychotherapies, including DBT and ST [ 28 ]. In addition, more than one-third of the patients did not achieve a reliable change in BPD symptoms or even showed an increase in BPD severity after DBT or ST [ 29 , 30 , 31 ]). Finally, dropout rates up to 30% have been found for DBT and ST [ 32 , 33 ]. Individual differences in responses to both ST and DBT have been observed across studies, but the factors driving these differences in treatment response among BPD patients are largely unknown. This state of affairs leaves the principal question “What treatment, by whom, is most effective for this individual with that specific problem, under which set of circumstances?” ([ 34 ], p111), historically one of the key questions dominating the psychotherapy research agenda, fully open in the treatment of BPD individuals [ 35 , 36 ]. Identifying factors that specify which patients will benefit most from which treatment (i.e., treatment selection, or also known as precision medicine or personalized medicine; [ 37 , 38 ]) will lead to fewer mismatches between patients and treatments, and in turn to better outcome and more efficient use of healthcare resources.

• Treatment selection

Several factors predicting treatment response irrespective of type of treatment (i.e., prognostic factors; [ 35 ]) among BPD patients have been reported in the literature. The overwhelming list of candidate variables and the general lack of replication hampers the research among BPD patients on prognostic factors [ 39 ]. Research among BPD patients on prescriptive factors (i.e., factors that predict different outcomes depending on the treatment; moderators) is very scarce indeed. Arntz et al. [ 39 ] examined the effect of several potential predictors of (differential) treatment response across ST and Transference Focused Psychotherapy (TFP) among BPD patients. The authors failed to find prescriptive factors, but it should be noted that the sample size was inadequate to detect subtle differences between treatments. In addition, Verheul et al. [ 40 ] found that patients with a high frequency of self-mutilating behavior before treatment were more likely to benefit from DBT compared to treatment as usual, whereas for patients with a low frequency of self-mutilating behavior effectiveness did not differ.

Historically, research has focused on a single variable to predict treatment response, but often failed to find consistent and clinically meaningful moderators [ 41 , 42 , 43 , 44 ]. However, it is highly unlikely that a single variable is responsible for the differences in treatment response [ 43 , 45 , 46 ]. In recent decades, novel approaches combining multiple predictors to determine the optimal treatment for a particular patient have been introduced, including the methods of Kraemer ([ 47 ]; optimal composite moderator) and DeRubeis and colleagues ([ 35 ]; statistically derived selection algorithm). Several studies have found that a combination of predictors was predictive of differential treatment response (e.g., [ 48 , 49 , 50 ]). For example, by using the method of DeRubeis and colleagues, it was investigated in an effectiveness study among BPD patients which of two different treatments (DBT and General Psychiatric Management; GPM) would have been the optimal treatment option for a particular patient in terms of long term outcome [ 45 ]. The authors found that BPD patients with childhood emotional abuse, social adjustment problems, and dependent personality traits were more likely to benefit from DBT compared to GPM, whereas GPM excelled for patients with more severe problems related to impulsivity. The authors also provided an estimate of the advantage that might be gained if patients had been allocated to the optimal treatment option. The average difference in outcomes between the predicted optimal treatment and non-optimal treatment for all patients was small-to-medium ( d  = 0.36), while the advantage for patients with a relatively stronger prediction increased to a medium-to-large effect ( d  = 0.61). This suggests that treatment allocation based on a treatment selection procedure may substantially improve outcomes for BPD patients.

• Mechanisms of change

Another principal way to improve treatment response is to capitalize on mechanisms underlying change in treatments [ 27 , 45 , 51 , 52 ]. Studying mechanisms of change helps to identify core ingredients of interventions and points the way to enhancing crucial elements, while discarding redundant elements. Presumably, this would maximize (cost-)effectiveness and efficiency as well. Since the 1950s, research on change processes has increased exponentially [ 53 ]. However, the majority of the trials on BPD have focused on outcomes, and only a few addressed how treatments exerted a positive effect on patient outcomes [ 54 , 55 ]. Rudge et al. [ 56 ] reviewed studies on mechanisms of change in DBT. They concluded that there is empirical support for behavioral control, emotion regulation, and skills use as mechanisms underlying change in DBT. Recently, Yakın et al. [ 57 ] examined schema modes as mechanisms of change in ST for cluster C, histrionic, paranoid, and narcissistic personality disorders. They found that a strengthening of a functional schema mode (i.e., healthy adult mode) and weakening of four maladaptive schema modes (i.e., vulnerable child mode, impulsive child mode, avoidant protector mode, and self-aggrandizer mode) predicted improvements in PD symptomatology. However, changes in these schema modes, except for self-aggrandizer mode, also predicted improvements in outcome in treatment-as-usual and clarification-oriented psychotherapy, suggesting that modifying the strength of schema modes might reflect common mechanisms of change. The question of specificity of mechanisms of change is interesting, especially since both DBT and ST have their roots in cognitive behavior therapy and show similarity in certain treatment parameters, but differ substantially in techniques, explanatory model, and terminology [ 58 ]. Clarifying the treatment-specific and non-specific mechanisms of change may be key to furthering the effectiveness of both DBT and ST, and potentially also for psychotherapy in general.

Current study

BPD-tailored treatments, like DBT and ST, are considered treatments of choice for BPD [ 25 ]. However, knowledge on the comparative (cost-)effectiveness of DBT and ST is lacking, as is knowledge on mechanisms of change and patient characteristics that predict (differential) treatment response. We will therefore perform a multicenter randomized clinical trial (RCT) comparing DBT and ST for BPD patients to elucidate the question “Which treatment – DBT or ST – works the best for which BPD patient, and why?”. The main aim of the BOOTS (Borderline Optimal Treatment Selection) study is to improve treatment response of DBT and ST for BPD patients by optimizing treatment selection through the identification of a prediction model based on patient characteristics that predict (differential) treatment response. By doing so, this study is a first step into the development of a treatment selection procedure for BPD patients. Moreover, the results of this study can serve as a starting point for future studies with the ultimate goal of implementing a treatment selection procedure that can be used in clinical practice to guide BPD patients and clinicians in selecting the optimal treatment. In addition, we aim to elucidate the mechanisms by which DBT and ST lead to change, thus pursuing the other main avenue towards improving BPD treatments.

This study has four primary objectives. The first objective of this study is to develop a treatment selection model based on a combination of patient characteristics that predict (differential) treatment response across DBT and ST. Candidate predictors of (differential) treatment response have been selected based on the literature, suggestions of a patient representative of the Borderline Foundation of the Netherlands, and clinicians’ appraisals of BPD patient characteristics that predict (differential) treatment response across DBT and ST. Semi-structured interviews were conducted among 18 expert clinicians to identify patient characteristics they deemed predictive of (differential) treatment response. The extensive investment in the identification of pertinent predictors is a lesson learned from Meehl [ 34 ], who noted that actuarial methods will not outperform clinical judgment when the actuarial method is based on inadequate knowledge of relevant variables. According to Westen and Weinberger [ 59 ], clinical expertise can serve the important function of identifying relevant variables for use in research. In addition, the majority of studies examining predictors of treatment response are based on randomized controlled trials with a primary focus on treatment effectiveness [ 60 ], which could result in the preclusion of potentially relevant predictors due to the lack of instruments assessing these constructs [ 39 , 61 ]. Moreover, findings in the literature may be affected by publication bias, since statistically significant predictors of treatment response are more likely to be published [ 46 ]. Therefore, candidate predictors of (differential) treatment response are not only based on the literature, but also on clinical expertise and experience-based knowledge. We hypothesize that a combination of multiple patient characteristics will predict and moderate treatment effectiveness of DBT and ST. Hypotheses on the effects of single patient characteristics will not be formulated as research among BPD patients often failed to find consistent prognostic factors, while research on prescriptive factors or a combination between factors is scarce. In addition, there was in general a lack of consensus between the 18 expert clinicians on patient characteristics predicting (differential) treatment response across DBT and ST.

Second, we aim to elucidate how DBT and ST exert their effect by gaining a better understanding of the mechanisms of change of DBT and ST. A first step towards more insight into mechanisms of change is the identification of mediators. Mediators are easily confused with mechanisms of change, despite important differences [ 62 ]. A mediator is an intervening variable (partly) accounting for the statistical relationship between the intervention and outcome, and might serve as a statistical proxy for a mechanism of change [ 63 ]. In this study, we will examine potential BPD-treatment-specific, BPD-treatment-generic, and non-specific mediators. Based on empirical research and the presumed mechanisms of change (e.g., [ 55 , 56 , 57 ]), we hypothesize that change in skills use and emotion regulation are the mechanisms underlying change in DBT, and that change in schema modes and beliefs are the mechanisms of change in ST (i.e., BPD-treatment-specific mechanisms of change). In addition, a therapeutic environment characterized by genuineness of the therapists and group members, safety, and equality is considered to be especially important for BPD treatment [ 64 , 65 , 66 , 67 ] and is, therefore, assumed to be a BPD-treatment-generic mechanism of change. Finally, attachment and therapeutic alliance are the presumed non-specific mechanisms of change [ 68 , 69 ].

Third, the comparative effectiveness of DBT and ST will be examined. Accumulating evidence suggests that symptoms and psychosocial functioning are only loosely associated [ 70 , 71 ]. Patients with BPD are characterized by significant impairments in vocational functioning, relationships, and leisure [ 72 ]. In addition, social adjustment of BPD patients is considerably lower than social adjustment seen in other mental disorders, such as major depressive disorder and bipolar I disorder [ 73 ]. Moreover, although several studies found that even as psychopathology after treatment of BPD decreased, impairments in quality of life and functioning often (partly) persist [ 74 , 75 ]. A more comprehensive view of recovery is therefore needed. This notion is underscored by qualitative research that has shown that patients define recovery by personal well-being, social inclusion, and satisfaction with life [ 76 , 77 ]. Therefore, the current trial will track outcomes in multiple domains including symptoms, functioning, and well-being.

Finally, the cost-effectiveness of DBT and ST will be compared. Individual ST seems a cost-effective treatment [ 78 , 79 ]. However, although group ST combined with individual ST is widely used in clinical practice, the cost-effectiveness of this combined program is yet unknown. An international RCT evaluating the (cost-)effectiveness of group ST for BPD is currently in progress [ 80 ]. More economic evaluations of DBT are available and support the cost-effectiveness of DBT. However, the studies vary highly in their design and the number of trials is still somewhat limited [ 26 , 81 , 82 ]. Therefore, an economic evaluation will be performed and a societal perspective will be applied, including indirect and direct healthcare costs.

In addition to these primary objectives, several secondary investigations will be performed, including (but not limited to): 1) the heterogeneity of BPD, 2) substance use (disorders) among patients with BPD, 3) perspectives of patients and therapists in key areas, including predictors, mechanisms of change, the treatments, and the implementation of the results in clinical practice, and 4) psychometric evaluations of several Dutch questionnaires (e.g., Dialectical Behavior Therapy-Ways of Coping Checklist, Ultrashort BPD Checklist).

Methods/design

The study is a multicenter RCT with two active conditions (DBT or ST). The study is set at various Dutch mental healthcare centers accessible through the public health system, including Antes (Rotterdam), GGZ inGeest (Amsterdam), GGZ NHN (Heerhugowaard), GGZ Rivierduinen (Leiden), NPI (Amsterdam), Pro Persona (Ede and Tiel), PsyQ (Rotterdam-Kralingen), and PsyQ/i-psy (Amsterdam). For an overview of the study design, including the enrollment, randomization, interventions, and assessments, see Fig. 1 .

Flow chart of the study design. DBT = Dialectical Behavior Therapy; ST = Schema Therapy. *An extra assessment after wait is included for patients with a waitlist period of more than three months after the baseline assessment

The Medical Ethics Committee of the Academic Medical Center (MEC-AMC) Amsterdam approved the study protocol (registration number NL66731.018.18). The study is registered at the Netherlands Trial Register, part of the Dutch Cochrane Center (registration number NL7699), and complies with the World Health Organization Trial Registration Data Set. Modifications to the protocol require a formal amendment to the protocol which will be examined by the MEC-AMC. The trial adheres to the SPIRIT methodology and guidelines [ 83 ], see Additional file 1 .

Patients are eligible if they 1) are between 18 and 65 years old, 2) have a primary diagnosis of BPD (diagnosed with the Structural Clinical Interview for DSM-5 Personality Disorders; SCID-5-PD), 3) have a BPD severity score > 20 on the Borderline Personality Disorder Severity Index, version 5 (BPDSI-5), 4) have an adequate proficiency in the Dutch language, and 5) are motivated to participate in (group) treatment for a maximum of 25 months and are willing and able to complete the assessments over a period of three years. Patients will be excluded if they 1) fulfill the criteria of a psychotic disorder in the past year (diagnosed with the Structural Clinical Interview for DSM-5 Syndrome Disorders; SCID-5-S), 2) have current substance dependence needing clinical detoxification, 3) have been diagnosed with a bipolar I disorder with at least one manic episode in the past year, 4) have been diagnosed with antisocial personality disorder (diagnosed with the SCID-5-PD), in combination with a history of physical violence against multiple individuals in the past two years, 5) have an IQ below 80, 6) have a travel time to the mental healthcare center longer than 45 min (except when the patient lives in the same city), 7) have no fixed address, and 8) have received ST or DBT in the past year.

Sample size

We aim to include 200 participants. Each center intends to recruit at least 18 patients. For the power analysis, we adopted the minimal statistically detectable effect approach [ 84 ]. A sample size of 200 will be sufficient to have 80% power to detect moderators of treatment effects that have an effect size of Cohen’s f of .20 (small to medium effect size), based on a two-tailed significance level of p  < .05. In addition, the study has 80% power to detect medium effect-sized (i.e., Cohen’s f  = .25) moderators of treatment effects, based on a two-tailed significance level of p  < .01.

Regarding the effectiveness study, with a sample size of N  = 200 the study is powered at 82% to detect a group difference with a medium effect size of Cohen’s d  = .50 at a two-tailed significance level of p  < .05 and assuming a model with center as random effect and an intraclass correlation value of 0.05 corresponding to the center by treatment interaction [ 85 , 86 ].

Finally, a sample size of N  = 200 will be sufficient to have 98% power to detect a medium effect size of the mediation effect ( rr  = .09; [ 87 , 88 , 89 ]), assuming path a (relation between the predictor and mediator) and path b (relation between the mediator and outcome measure) both have a medium effect size ( r  = .30), and based on a simplified trivariate mediation model [ 90 ].

Recruitment

Patients are recruited in the respective participating mental healthcare centers. Patients diagnosed with BPD or for whom this is deemed likely are invited to participate in the screening process. After reading and hearing information about the study and signing an informed consent (see Additional file 2 , Appendix A), patients will start with the screening process. Not only new referrals can be included, but also patients who are already receiving treatment for mental disorders (except patients receiving ST or DBT).

Randomization

A central independent research assistant randomizes the patients per center after a final check of the inclusion and exclusion criteria, and after all baseline measures have been completed. Generally, patients will be randomized using computerized covariate adaptive randomization [ 91 , 92 , 93 ], taking into account gender and severity of BPD (BPDSI-5 score ≤ 24; BPDSI-5 score > 24). By using this method, the imbalance of baseline characteristics between the treatments will be minimized. Patients are allocated to the treatment group that results in the least imbalance between the treatments with an allocation probability of 0.8 to preserve unpredictability [ 94 ]. Groups in both treatments are semi-open which implies that new patients can enter the group if treatment slots are available. Therefore, treatment capacity will be taken into account by using unequal ratios if needed (e.g., 2:1 or 1:3).

In exceptional cases, an alternative randomization method will be used if one or more treatment slots are available in only one condition and there is no available treatment slot in the other condition. To prevent long waiting times for treatment and empty places in the groups, the available treatment slot(s) in one condition will be randomized over 2* k patients whereby k stands for the number of available treatment slots, and randomization is done in the subsample of k patients that wait the longest. Randomization over 2* k patients guarantees unpredictable outcomes. For example, if one treatment slot is available in DBT and there is no available treatment slot in ST at that moment, nor within the foreseeable future, the available treatment slot in DBT will be randomized over two patients waiting for treatment. Sensitivity analyses will be performed by excluding patients that have been randomized using the alternative randomization method.

Procedure and assessments

Patients with BPD or suspected of BPD are invited to the screening process by the research assistant or intake staff member. After providing written informed consent, patients are assessed for eligibility to participate in the study based on the inclusion and exclusion criteria. First, to assess DSM-5 syndrome disorders, the SCID-5-S is administered. The SCID-5-PD will also be administered in case the SCID-5-PD is not part of the standard intake procedure of the mental healthcare center. Second, the BPDSI-5 and a screening interview to assess the motivation and availability of the patient are conducted. A simple “yes” answer to the questions posed by the interviewer (e.g., “Are you motivated and available for treatment, including individual and group sessions?”) is not sufficient. Patients need to elaborate on their answers and follow-up questions are asked if needed. Patients who are eligible for participation will be invited for the baseline assessment, including interviews and computer-based self-report questionnaires, and intake staff members will fill out a questionnaire (i.e., intake questionnaire; see the Measures section) about these patients. After completing the baseline assessment, patients will be randomized as soon as treatment slots become available. Patients will be informed that they have been allocated to one of the treatment conditions, but the name of the treatment will not be communicated to the patient until the first treatment session. If patients cannot be randomized within several months after completing the baseline assessment because of unavailability of treatment slots, the BPDSI-5 will be re-assessed after three months and the BPDSI-5 and cost interview will be re-assessed after six months.

After the treatment phase has started, patients are reassessed every six months during the two years of treatment. These assessments are a combination of interviews and computer-based self-report questionnaires. In addition, a selection of measures are also assessed every three months, by computer-based self-report questionnaires. After end of the treatment, two follow-up assessments (six and 12 months after end of the treatment) will be administered. An overview of the measures is presented in Table 1 . Candidate predictors of (differential) treatment response that are assessed only once at baseline are not included in Table 1 . These measures can be found in the Measures section.

All assessments are performed by trained local research assistants blind to the patients’ treatment condition, with exception of the SCID-5 interviews, demographic interview, and cost interview. The SCID-5 interviews can be administered by trained research assistants as well as trained intake staff members, both blind for condition. The demographic interview and cost interview contain questions on healthcare utilization and are therefore performed by non-blinded local research assistants. Due to the nature of the interventions, blinding of therapists and patients is not possible. All interviews, except for the SCID interviews, are audio-recorded. Participants receive financial compensation for their involvement in the study. Patients who discontinue their treatment or deviate from the treatment protocol will be encouraged to continue the assessments.

For patients of both DBT and ST, treatment has a maximum duration of 25 months and starts with a pretreatment phase of approximately four weeks consisting of several (ST: ± three; DBT: ± five) individual sessions in which patients are prepared for the group sessions and become accustomed to their therapists and the treatment model. After the pretreatment phase, patients receive a combined program of individual sessions and group sessions (i.e., treatment phase). Group sessions of both treatments are offered in a semi-open format. If treatment slots are available, new patients can enter the ST group every 10 weeks and for DBT groups at the start of a mindfulness skills module. In DBT, the treatment phase has a maximum duration of 12 months and consists of weekly group sessions (i.e., skills training groups; 150 min), weekly individual psychotherapy sessions (50 min), and between-session consultation. The between-session consultation, often called telephone consultation although all kinds of technology can be used [ 95 ], is offered to the patient within limitations set by the individual therapist, varying between access to between-session support within working hours to 24/7 access to between-session support, which is officially the standard in DBT. In ST, the treatment phase has a maximum duration of 18 months consisting of weekly group (90 min) and individual (45 min) psychotherapy sessions for a period of 12 months, continued by weekly group psychotherapy sessions and biweekly individual psychotherapy sessions for a period of six months. Following the treatment phase, patients continue their treatment with a maintenance phase. The maintenance phase of DBT is a recently developed blended aftercare program with a maximum duration of 12 months. The blended aftercare program was developed based on results of previous studies (e.g., [ 31 , 96 ]) and recommendations by several authors (e.g., [ 96 , 97 , 98 ]) to extend the duration of DBT to sustain or even enhance treatment effects. The DBT aftercare program consists of monthly individual psychotherapy sessions, three-monthly group sessions, and an eHealth intervention in which patients have online access to DBT handouts and worksheets [ 99 ]. The maintenance phase of ST consists of biweekly individual psychotherapy sessions for a period of three months, continued by three months of one individual session each month. Disregarding the time spent on telephone consultation, homework assignments, and eHealth, and based on 48 working weeks a year, patients will receive about 167 h of treatment if they follow the treatment protocol. Patients who have completed treatment successfully before they reach the maximum number of treatment sessions are allowed to complete treatment earlier, although the assessments will be conducted at the originally planned assessment points. Early termination of treatment requires substantial improvements in the primary and secondary outcomes and is decided in joint decision by the patient and therapist. The treatments are covered by the public health insurance. See Table 2 for an overview of the treatment formats.

Schema therapy (ST)

ST, developed by Jeffrey Young [ 22 , 100 ], is based on an integrative cognitive model, combining cognitive behavior therapy and experiential techniques with insights from developmental theories, including attachment theory, and psychodynamic concepts [ 23 ]. Central concepts are early maladaptive schemas and schema modes. Early maladaptive schemas can be defined as broad, pervasive patterns of thoughts, emotions, memories, and cognitions regarding oneself and relationships with others, developed during childhood [ 22 ]. ST assumes that the frustration of core needs and early traumatic experiences lead to the development of early maladaptive schemas. A schema mode refers to an activated set of schemas and the associated coping response (i.e., overcompensation, avoidance, and surrender), and describes the momentary emotional, cognitive, and behavioral state of the patient. The following schema modes are characteristic of BPD [ 101 ]: 1) vulnerable child mode, associated with a fear of abandonment and strong emotions, such as loneliness, sadness, and helplessness, 2) angry and impulsive child mode, characterized by anger, frustration, hostility, and impulsivity, 3) punitive parent mode, representing the internalized voice of very punitive and critical attachment figures and associated with self-criticism, self-hatred, guilt, and self-denial, 4) detached protector mode, characterized by attempts to cut off the self from needs and feelings, resulting in symptoms of detachment, substance misuse, social withdrawal, and self-harm, and 5) healthy modes, reflecting in functional thoughts, cognitions, and behavior (i.e., healthy adult mode) and the feeling that core needs are been fulfilled (i.e., happy child mode). The first four modes are maladaptive schema modes and central to BPD. The last two modes are functional and often only weakly present at the beginning of the treatment [ 102 ]. Idiosyncratic schema mode models usually cover additional modes, depending on the specific problems and comorbidity of the patient.

ST aims to enable patients to fulfill their needs, reduce maladaptive schema modes, and strengthen adaptive schema modes. In this study, ST is offered in a combined group-individual format developed by Farrell and Shaw [ 103 ]. The group acts as an analogue of a family with the other patients as “siblings” and the two therapists as “parents” [ 103 ]. The group may speed up and amplify the effect of treatment by offering corrective emotional experiences, peer support, opportunities for in vivo practice, and a sense of understanding [ 104 ]. The individual ST follows the protocol as described by Arntz and Van Genderen [ 105 ].

Dialectical behavior therapy (DBT)

DBT is a comprehensive cognitive behaviorally based treatment for BPD, integrating strategies from cognitive and behavioral treatments, Zen-based acceptance strategies, and dialectical strategies [ 19 , 106 ]. Linehan [ 19 , 20 ] proposed a skills deficit model in which emotion regulation is central. More specifically, the model holds that the problematic behaviors associated with BPD (e.g., suicide attempts, self-injury, substance use) are in fact best understood as dysfunctional attempts to regulate emotions. Emotion dysregulation results from the complex transaction between dispositional emotional vulnerabilities and an adverse invalidating environment. Therefore, the treatment involves balancing problem solving strategies with loads of validation. DBT aims to help patients develop new skills, enhance motivation, ensure generalization of skills use, and change their environment if needed. In addition, DBT aims to enhance therapists’ motivation to deliver effective treatment [ 20 ].

DBT involves skills training groups, individual therapy, between-session consultation, and therapist consultation team meetings. DBT skills training groups teach patients behavioral skills in four different, yet inter-related, areas: mindfulness, interpersonal effectiveness, emotion regulation, and distress tolerance / radical acceptance. Individual therapy focuses on motivational issues and the acquisition and use of skills in daily life. A predetermined ordering of treatment targets is used in individual sessions and part of different stages of the treatment. Stage 1 focuses on stabilizing the patient and behavior control. Targets in this stage of the treatment include: life-threatening behavior, therapy-interfering behavior, quality-of-life-interfering behavior, and behavior skills. Stage 2 focuses on reducing posttraumatic stress and requires exposure to trauma-related cues [ 19 ]. Finally, Stages 3 and 4 target self-respect and the sense of incompleteness. However, due to time constraints, some patients might not enter all stages and most studies have focused on Stage 1 DBT [ 107 ]. Individual therapists provide between-session (telephone) consultation if needed. According to the guidelines of DBT, access to between-session consultation outside of office hours, preferably by the individual therapist, is part of DBT [ 19 ]. In this trial, between-session consultation by the individual therapist will be within limitations set by the therapist, which can vary between support provided within working hours to 24/7 access to telephone consultation. As access to between-session (telephone) consultation will vary between centers and individual therapists, the effect of therapist’s availability for between-session support will be examined. Finally, DBT therapists meet weekly in a DBT consultation team to motivate and support each other.

Therapists, training, and supervision

The therapists in this study will be licensed psychologists, psychotherapists, psychiatrists, or psychiatric nurses. Individual and group schema therapists must have completed a basic training in individual ST. Group schema therapists must have also completed a four-day training in the group schema therapy model of Farrell and Shaw [ 103 ]. All schema therapists receive a one-day training in experiential techniques by a certified ST trainer. DBT therapists are required to complete a three-day training in DBT and at least one member of the DBT team must have completed the 10-day intensive DBT training. In addition, DBT therapists receive a two-day kick-off training by certified DBT trainers to expand their knowledge of DBT. Moreover, DBT-therapists were given the opportunity to participate in a one-day training in imaginal exposure. According to Linehan [ 19 ], reducing behaviors and stress response patterns related to traumatic life events is a primary DBT target. Reducing posttraumatic stress is mostly part of Stage 2 of DBT and involves exposure to trauma-associated cues [ 19 , 108 ]. However, some of the DBT therapists expressed concerns about their ability to apply the principles and procedures of exposure to treat traumatic memories in BPD patients. Therefore, the opportunity to participate in a one-day exposure training was offered to the therapists.

Before the start of the study, schema therapists should have received at least 10 individual supervision sessions by a licensed supervisor. There is no requirement for the minimum number of DBT supervision sessions. During the study, therapists receive supervision over a period of two years by certified supervisors. ST supervision is provided through teleconferencing biweekly in the beginning, then (two-)monthly after six to 12 months, depending on the experience of the therapists. DBT therapists receive supervision at location every three months. Moreover, there will be weekly DBT team meetings (i.e., DBT consultation team meetings) and biweekly ST team meetings. All individual ST sessions will be audiotaped, while individual DBT sessions and ST and DBT group sessions will be videotaped. These recordings are used for supervision and treatment adherence ratings. Treatment adherence, a component of treatment integrity (i.e., the extent to which a treatment is implemented as intended; [ 109 ]), refers to the extent to which the therapist utilizes prescribed techniques and procedures and avoids the use of proscribed techniques and procedures [ 110 ]. Adherence will be assessed in a random selection of session recordings by trained raters (master psychology students) blind for condition. Master psychology students will be trained by ST and DBT experts by using session recordings not used in the final adherence rating to practice with the instruments. Individual ST sessions will be rated on an adapted version of the Therapy Adherence and Competence scale for ST for BPD [ 111 ] and group ST sessions will be rated on the Group Schema Therapy Rating Scale – Revised [ 112 ]. Individual DBT sessions will be rated on the Dutch translation of the observer-rated version of the DBT Adherence Checklist for Individual Therapy [ 113 ]. An observer-rated instrument will be developed to assess the skills training groups.

Other treatment

During the treatment, patients are not allowed to engage in any other form of psychological treatment. However, in case of acute crisis, the crisis procedures of the treatments will be followed (e.g., telephone consultation by the therapist, contact a crisis line, visit the emergency room, hospitalization, individual crisis management sessions). Any additional treatment will be recorded and included in the analyses. Patients will only be withdrawn from the study at their request.

Coronavirus disease (COVID-19) pandemic

This study is conducted during the COVID-19 pandemic. The pandemic is expected to have adverse effects on patients with mental health disorders [ 114 ]. In addition, in case face-to-face treatment is restricted in mental healthcare centers because of government and healthcare center policy, the treatment will be delivered via videoconferencing. Consequently, differences between patients will arise regarding the amount of treatment sessions delivered during the pandemic and/or via videoconferencing. We will control for a potential influence of the COVID-19 pandemic by, for example, adding dynamic regression parameters that include the impact of time in treatment during the pandemic. The definition of the indicator variable indicating the COVID-19 pandemic will be decided before start of the data-analyses (e.g., dummy variable indicating pandemic/no pandemic or continuous variable indicating the amount of time in treatment during the pandemic), given the unpredictability of the current situation. Moreover, exploratory analyses may be conducted to investigate the potential influence of the deviating treatment format (i.e., online vs. face-to-face individual sessions and/or group sessions) on the treatment effectiveness.

In addition, the assessments will be conducted via videoconferencing or phone, and the computer-based questionnaires will be completed by participants at home, if face-to-face assessments are not allowed. Before receiving the treatment and/or assessments via videoconferencing, patients will sign an additional informed consent form (see Additional file 2 , Appendix B).

Data management, storage, monitoring, and dissemination

Data is collected with a unique identifier for each patient (i.e., pseudonym) using the online survey software program Qualtrics [ 115 ] and the web tool Lotus, which has been especially developed for longitudinal research by the University of Amsterdam. The list of pseudonyms and personal information of patients within a particular mental healthcare center is securely stored at the center and only accessible for the research assistant and coordinator of this center. A different set of pseudonyms is used for data collected by clinicians (i.e., intake questionnaire and recordings). The list with the combination of both pseudonyms of patients is only accessible for the research assistant and coordinator of the center and the authorized researchers. The data is stored on a secure storage server of the University of Amsterdam, accessible only to authorized researchers.

All (serious) adverse events reported by the patient or observed by clinicians or researchers will be recorded. There is no data monitoring committee and the study will not be audited. The results of the study will be disseminated in scientific journals and presentations at (inter)national scientific conferences.

The instruments include screening measures, measures to assess potential predictors and mediators of treatment response, and outcome measures. The instruments that were not available in Dutch were translated (i.e., Brief Experiential Avoidance Questionnaire, Dialectical Behavior Therapy-Ways of Coping Checklist, Gordon Test of Visual Imagery Control, Positive Mental Health scale, and social problems) by bi-lingual experts. The translations were checked for consistency with the original version. Items, questionnaires, and interviews that have been developed or modified by the authors are available upon request by the first author.

Mental disorders

The SCID-5 is a semi-structured interview used to diagnose DSM-5 disorders. Personality disorders are assessed with the SCID-5-PD [ 116 ] and syndrome disorders are assessed using the SCID-5-S [ 117 ], which is an extended version of the SCID-5 Clinician Version (SCID-5-CV; [ 118 ]). Additional file 3 offers an overview of all syndrome disorders that are assessed by the SCID-5-S. Based on a first psychometric evaluation in a psychiatric patient sample, Somma et al. [ 119 ] found an adequate interrater reliability of the SCID-5-PD. In addition, the SCID-5-CV has demonstrated good psychometric properties [ 120 , 121 , 122 ].

Before administering the SCID-5-S and/or SCID-5-PD, self-report screening questionnaires (SCID-5-SPQ; [ 123 ], and SCID-5-SV; [ 124 ]) may be administered. In accordance with the instructions for administering the SCID, disorders and criteria of disorders not affirmed by the screening questionnaires and not considered as false negatives by the clinician will be assumed to be absent. The SCID-5 will be assessed during the screening phase and 12 months after end of the treatment.

Motivation and availability

A 13-item semi-structured motivation interview is used to assess several exclusion criteria (e.g., no fixed address, have received ST or DBT in the past year) and patient’s motivation and availability.

As mentioned, candidate predictor variables of (differential) treatment response have been selected using a multi-method approach (i.e., literature, suggestions of a patient representative of the Borderline Foundation of the Netherlands, and semi-structured interviews with 18 expert clinicians). Additional file 4 , Table 1 offers an overview of the predictors that have emerged during the semi-structured interviews with clinicians. Additional file 4 , Table 2 offers an overview of the predictors based on the literature and suggestions of a patient representative. The candidate predictors of (differential) treatment response are assessed at baseline. Only the measures that are not part of the screening, mediator or outcome measures will be briefly described in this paragraph.

Autistic traits

Autistic traits are assessed by the abbreviated version of the Autism Spectrum Quotient, the AQ-10 [ 125 ]. The AQ-10 consists of 10 items rated on a four point Likert scale. The AQ-10 has demonstrated acceptable psychometric properties in an adult general population sample [ 126 ].

Patient commitment to treatment is measured with a selection of items of the subscale Motivation to Engage of the Treatment Motivation Scales for forensic outpatient treatment (TMS-F; [ 127 ]). The four items can be rated on a seven point Likert scale.

Experiential avoidance

The Brief Experiential Avoidance Questionnaire (BEAQ; [ 128 ]) is a 15-item scale assessing experiential avoidance across six domains (i.e., behavioral avoidance, distress aversion, suppression, procrastination, repression/denial, and distress endurance). The items can be rated on a six point Likert scale. The BEAQ has shown good psychometric properties among psychiatric outpatients [ 128 ].

Frustration intolerance

Frustration intolerance is assessed by the Frustration Tolerance subscale of the Severity Indices of Personality Problems (SIPP-118; [ 129 ]). This subscale consists of eight 4-point Likert scale items measuring the capacity to cope with setbacks and disappointments. In previous research among Dutch patients with a personality disorder, the subscale demonstrated moderate to good reliability [ 129 ].

A modified version of the Self-Reflection and Insight Scale (SRIS; [ 130 , 131 ]) is used to assess self-reflection and insight. The SRIS contains 20 five point Likert scale items. The SRIS has shown good reliability and validity in student samples [ 130 , 132 ].

Internal locus of control

Internal locus of control, defined as the extent to which a person experiences an outcome as the result of their own behavior or personal characteristics rather than external circumstance, is assessed by the Locus of Control scale (IE; [ 133 ]). The IE contains 10 five point Likert scale items. Previous research has demonstrated adequate psychometric properties [ 133 , 134 ].

Level of personality functioning

The Level of Personality Functioning Scale-Brief Form 2.0 (LPFS-BF 2.0; [ 135 ]) assesses impairment in personality functioning according to the DSM-5 alternative model for personality disorders. The LPFS-BF 2.0 contains 12 four point Likert scale items. Based on a first psychometric evaluation among Dutch patients referred to a specialized mental healthcare center for personality disorders, the LPFS-BF 2.0 has demonstrated satisfactory psychometric properties [ 135 ].

Mental imagery capacity

Mental imagery capacity is assessed with the 12-item Gordon Test of Visual Imagery Control (TVIC; [ 136 ]). The TVIC assesses the ability to visualize and manipulate a given scenario in response to a set of cues. Participants can response on a three point Likert scale. In addition to the 12 Likert scale items, we measure the time it takes the participant to visualize the scenarios. Finally, we have added two 100 mm visual analog scale (VAS) items measuring how well participants see the scenarios that were described and how difficult it was for the participant to visualize the different scenarios. The TVIC has demonstrated fair to satisfactory internal consistency and validity among community samples and undergraduates [ 137 , 138 , 139 , 140 ].

Mentalizing capacity

Mentalizing capacity is measured using an eight-item version of the Reflective Functioning Questionnaire (RFQ-8; [ 141 ]). The RFQ-8 comprises two dimensions: uncertainty about mental states, reflecting hypomentalizing, and certainty about mental states, indicating hypermentalizing. The RFQ-8 uses a seven point Likert scale. In previous research among BPD patients, the questionnaire has demonstrated satisfactory psychometric properties [ 141 , 142 , 143 ].

Perfectionism

The eight-item Frost Multidimensional Perfectionism Scale-Brief (F-MPS-Brief; [ 144 ]) assesses perfectionism across two dimensions (evaluative concerns and striving). Items are rated on a five point Likert scale. Psychometric properties of the F-MPS-Brief were found to be good in clinical and community samples [ 144 ].

Personality traits

Personality traits are measured, among others, with the Ten-Item Personality Inventory (TIPI; [ 145 , 146 ]), which is a brief measure of the Big-Five personality dimensions. The 10 items can be rated on a seven point Likert scale. The TIPI has shown low to moderate internal consistency and adequate validity among students [ 145 , 146 ].

Positive mental health

Positive mental health, often referred to as mental well-being, is assessed using the nine-item Positive Mental Health scale (PMH-scale; [ 147 ]). The items can be rated on a nine point Likert scale. Based on a previous study on the psychometric properties of the PMH-scale in student, patient and general samples, the PMH-scale was found to be a reliable and valid instrument [ 147 ].

Psychopathology and maladaptive personality traits

The Minnesota Multiphasic Personality Inventory-2 Restructured Form (MMPI-2-RF; [ 148 ]) measures a wide range of psychopathology symptoms, personality characteristics, and behavioral proclivities. The MMPI-2-RF consists of 338 true-false items aggregating onto 51 individual scales. The psychometric properties of the MMPI-2-RF varied from inadequate to good among normative, outpatient, and inpatients samples, as documented in detail in the Technical Manual [ 149 ].

Readiness to change

Readiness to change is assessed by two subscales (contemplation and action) of the 24-item version of the University of Rhode Island Change Assessment (URICA; [ 150 , 151 , 152 ]). Both subscales are measured by six 5-point Likert scale items and have demonstrated good reliability across a diversity of studies (e.g., [ 153 , 154 , 155 ]).

Rigidity is measured by the Rigidity subscale of the Computerized Adaptive Test of Personality Disorder-Static Form (CAT-PD-SF; [ 156 ]). The Rigidity subscale contains 10 five point Likert scale items reflecting an unwillingness to consider alternative perspectives and inflexibility in values and beliefs. The subscale has demonstrated good reliability among community adults with current or a history of mental health treatment [ 156 ].

Social problems

By using the social problems list, derived from the Improving Access to Psychological Therapies (IAPT) program [ 157 ], social problems (e.g., financial problems, housing problem, and unemployment) are assessed in direct discussion with the patient.

Social support

The Multidimensional Scale of Perceived Social Support (MSPSS; [ 158 ]) is assessed to investigate perceived support from three sources: significant others, family, and friends. The MSPSS contains 12 items which can be rated on a seven point Likert scale. Psychometric properties of the MSPSS are satisfactory among psychiatric outpatients and BPD patients [ 159 , 160 ]. In addition to the MSPSS, the research assistant rates the patient’s social network taking into account the size of the network and potential pathogenic influences.

Stigma of immutability

BPD has been associated to stigma of immutability [ 161 ]. We have developed five 7-point Likert scale items assessing the extent to which participants believe that BPD is resistant to treatment.

The Traumatic Experience Checklist (TEC; [ 162 ]) is used to assess traumatic experiences, including emotional abuse, emotional neglect, sexual abuse, sexual harassment, physical abuse, and threat to life/ bizarre punishment/ intense pain. The TEC includes 30 descriptions of various traumatic experiences. The TEC has demonstrated favorable psychometric properties in Dutch psychiatric patients [ 162 ].

Verbal intelligence

The Dutch version of the National Adult Reading Test (DART; [ 163 ]) is used as a proxy for verbal intelligence. The DART is a reading test including 50 irregularly spelled words. Based on previous research, the DART yields an adequate estimation of verbal intelligence and has shown adequate psychometric properties across a variety of populations [ 164 ].

Other patient characteristics, collected using a self-report questionnaire

In addition to the questionnaires, participants fill out several questions developed by the authors about the willingness and ability to engage in a therapeutic relationship, perceived suitability of DBT and ST (treatment preference), and the absence or presence of an attachment figure in the past.

Other patient characteristics, collected using a questionnaire filled out by clinicians (intake questionnaire)

Clinicians responsible for the intake assessment will fill out the nine-item intake questionnaire for each participant, including questions about the willingness and ability to engage in a therapeutic relationship, the willingness and ability to examine the link between childhood history and present problems, high vs. low level borderline personality organization [ 165 ], the request for help, the degree to which a syndrome disorder might interfere with treatment response, and perceived suitability of DBT and ST. These questions have been formulated by the authors.

Both treatments include non-specific (attachment and therapeutic alliance), BPD-treatment-generic (therapeutic environment characterized by genuineness, safety, and equality), and BPD-treatment-specific (ST: beliefs and schema modes; DBT: emotion regulation and skills use) mechanisms of change. The proposed mediators are repeatedly measured: at baseline, except for measures requiring information about the therapy (i.e., therapeutic environment, therapeutic alliance, and attachment styles with respect to the most important therapist and group members), and every six months after start of the treatment phase. In addition, a selection of the proposed mediators (i.e., selection of schema modes, skills use, beliefs, and therapeutic environment) are also collected every three months after start of the treatment phase, during the first two years.

The Experience in Close Relationships-Relationship Structures Questionnaire (ECR-RS; [ 166 ]) is a brief version of the Experience in Close Relationships-Revised (ECR-R; [ 167 ]). The ECR-RS measures attachment patterns in different relational domains, such as relationships with parents and friends. The ECR-RS can also be adapted to measure a person’s general attachment style. In this study, three versions of the ECR-RS are used, measuring general attachment style and attachment styles with respect to two targets (i.e., most important therapist and group members). The ECR-RS contains nine items, assessing two attachment dimensions: attachment-related anxiety and avoidance. The items can be rated on a seven point Likert scale. The ECR-RS has shown adequate psychometric properties in a large web-based sample ( N  > 21.000), comparable to the ECR-R [ 166 ]. As experience with the treatment is required in order to be able to complete the questions about the most important therapist and group members, these questions will be filled out three weeks after start of the treatment phase.

Idiosyncratic dysfunctional beliefs were elicited with a semi-structured interview at baseline. Three to five idiosyncratic dysfunctional beliefs related to the self (e.g., “I am worthless”), others (e.g., “People always reject me”), and emotions (e.g., “Expressing emotions is a sign of weakness”) are formulated. Participants rate the degree to which they believe in each statement on a 100 mm VAS at baseline and at every subsequent assessment. This procedure has been used in previous research (e.g., [ 168 , 169 ]). The VAS has found to be useful for assessing variations in intensity of beliefs in patients with a personality disorder [ 169 ]. In addition to the idiosyncratic dysfunctional beliefs, participants rate the credibility of one functional belief (“I consider myself a good person”) on a 100 mm VAS.

Emotion regulation

Emotion regulation is assessed by the Difficulties in Emotion Regulation Scale Short Form (DERS-SF; [ 170 ]), a brief version of the widely used DERS [ 171 ]. The DERS-SF measures non-acceptance of emotional responses, difficulties engaging in goal-directed behavior, impulse control difficulties, limited access to emotion regulation strategies, lack of emotional clarity, and lack of emotional awareness. The awareness subscale is excluded based on recommendations of among others Hallion et al. [ 172 ] and Bardeen et al. [ 173 ]. Lack of emotional awareness is assessed by the Awareness subscale of the Difficulties in Emotion Regulation Scale 18 (DERS-18; [ 174 ]). The DERS-SF, without the awareness subscale, consists of 15 items. The Awareness subscale of the DERS-18 is measured by three items. All items can be rated on a five point Likert scale. Both questionnaires have demonstrated good psychometric properties among outpatients [ 172 ].

Schema mode ratings

The Schema Mode Inventory (SMI; [ 175 ]) measures the extent to which 16 different (dysfunctional as well as functional) schema modes are endorsed. The SMI consists of 143 items that are scored on a six point Likert scale. Previous research using a sample of non-patients and patients with a syndrome disorder and/or personality disorder has demonstrated acceptable psychometric properties [ 176 ]. The five maladaptive schema modes that are central to BPD (i.e., vulnerable child, angry child, impulsive child, detached protector, and punitive parent; [ 101 ]) and one functional schema mode (i.e., healthy adult) are assessed every three months during the first two years.

The 59-item Dialectical Behavior Therapy-Ways of Coping Checklist (DBT-WCCL; [ 177 ]) is an adaptation of the Revised Ways of Coping Checklist (RWCCL; [ 178 ]). The DBT-WCCL measures DBT skills use and maladaptive coping skills use over the previous month. All items are assessed using a four point Likert scale. The DBT-WCCL has shown adequate to excellent reliability and validity among BPD patients [ 177 ].

Therapeutic alliance

The therapeutic alliance is measured with the Working Alliance Inventory-Short (WAI-S; [ 179 , 180 ]). The WAI-S consists of three subscales (agreement on goals, agreement on tasks, and bond between patient and therapist), each consisting of four items which can be scored on a five point Likert scale. Observed psychometric properties of the WAI-S were satisfactory in a patient sample [ 179 , 181 ]. Since experience with the treatment is required in order to be able to complete the WAI-S, the WAI-S will be filled out three weeks after start of the treatment phase.

Therapeutic environment

Key characteristics of a promoting therapeutic environment (i.e., genuineness, safety, and equality) are assessed by 13 items formulated by ST experts (A. Arntz and O. Brand-de Wilde) and rated on a 100 mm VAS. The items measure the extent to which the participant feels a) the individual therapist, group therapists, and group members are genuine with him/her; b) he or she can tell the individual therapist and group therapists everything; c) safe in the individual and group therapy; d) safe to show vulnerability and express negative feelings in the individual and group therapy; e) the individual and group therapists take personal responsibility for their mistakes; and f) the individual and group therapists see him/her as equal. Since experience with the treatment is required in order to be able to complete this questionnaire, this questionnaire will not be assessed at baseline.

Primary outcome

Bpd severity.

The primary outcome measure is the change in severity and frequency of the DSM-5 BPD manifestations between baseline until three-year follow-up, assessed with the total score of the Borderline Personality Disorder Severity Index version 5 (BPDSI-5; [ 182 , 183 ]). The BPDSI-5 is a semi-structured interview consisting of 70 items rating the nine DSM-5 BPD criteria over the prior three months. All items are rated on a 11-point Likert scale (0 = never to 10 = daily), except for the subscale Identity Disturbance which is rated on a 5-point Likert Scale (0 = absent to 4 = dominant, clear, and well-defined) and multiplied by 2.5. The total score consists of the sum of the nine criteria scores and ranges from 0 to 90. The scores on the BPDSI-5 subscales provide information on the severity of each of the nine criteria. The BPDSI-5 is a modified version of the BPDSI-IV [ 182 , 183 ] in which a few questions have been slightly reworded and exact frequency scores have been added in addition to the Likert scale. The BPDSI-IV has proven to be a reliable and valid measure among non-patients and (BPD) patients [ 182 , 183 ]. Previous research has shown that a cut-off score of 15 differentiates between BPD patients and controls [ 183 ]. In addition, a score of 20 distinguishes BPD patients from non-BPD patients [ 183 , 184 , 185 ].

Secondary outcome measures

As accumulating evidence suggests that BPD severity and level of functioning are only loosely associated, attention will be paid to outcomes in different areas, including symptoms, functioning, and well-being. The outcome measures are administered at baseline and every six months after start of the treatment phase. In addition, patients’ ratings of experienced burden due to BPD manifestations and well-being are collected every three months after start of the treatment phase, during the first two years.

Costs, including healthcare costs, patient and family costs, and costs outside the healthcare sector, are measured using a retrospective cost interview especially designed for BPD patients [ 80 ]. Healthcare costs include visits to general practitioners, hospitals, crisis centers, psychologists and psychiatrists, use of medication, social work, paramedical care, and alternative treatments. Patient and family costs include informal care (i.e., care provided by the patient’s family, friends, or neighbors) and out of pocket costs (e.g., drugs, alcohol, excessive spending). Costs in other sectors include productivity losses from unpaid work (study and voluntary work) and paid work. Since it is difficult to distinguish between BPD-related costs and costs due to other psychological disorders [ 17 ], only a distinction will be made between costs due to psychological disorders and costs due to somatic diseases. The cost interview will be conducted by trained research assistants using a recall period of six months (baseline assessment), the number of weeks since randomization (assessment six months after start of the treatment phase), or the number of weeks since the previous assessment (assessments 12, 18, and 24 months after start of the treatment phase and both follow-up assessments).

Dutch guidelines [ 186 , 187 ] will be used to determine total costs. Healthcare costs will be calculated by volumes of resource use multiplied by their corresponding unit costs, derived from Hakkaart-van Roijen et al. [ 186 ]. Prescribed medication costs will be determined based on national reference prices. Informal care costs will be computed by multiplying the number of hours the patient receives informal care by shadow prices [ 186 ]. Shadow prices will also be used to value lost productivity in study and voluntary work. Productivity losses from paid work will be valued according to the Human Capital Approach [ 188 ]. Out of pocket costs, such as alcohol and excessive spending, will be directly retrieved from the cost interview or, in case of over-the-counter medication, from the Dutch Pharmacotherapeutic Compass [ 186 ].

Demographics

General patient characteristics (e.g., age, ethnicity, marital status, educational level, employment status) will be collected using a semi-structured demographic interview. During this interview, additional patient characteristics such as treatment history, request for help, medication use, substance use, and duration of BPD manifestations will be recorded. For an overview of all characteristics, see Additional file 4 .

Experienced burden due to BPD

Patient’s self-reported experienced burden of BPD manifestations are measured using the Ultrashort BPD Checklist, a shortened version of the validated BPD Checklist [ 189 ]. The Ultrashort BPD Checklist consists of nine to 11 5-point Likert scale items (the number of items will be based on the upcoming validation study), each related to a specific DSM-5 BPD criterion. Based on an initial psychometric evaluation, the Ultrashort BPD Checklist showed good to excellent psychometric properties in a sample with BPD and cluster C patients, patients with a syndrome disorder, and non-patients, similar to the BPD Checklist [ 189 ].

General psychopathological symptoms

The Brief Symptom Inventory (BSI; [ 190 , 191 ]) is a self-report instrument measuring general psychiatric symptoms at the time of assessment. The BSI is a short version of the Symptom-Check-List (SCL-90-R) and contains 53 items assessing nine symptom dimensions: somatization, obsession-compulsion, interpersonal sensitivity, depression, anxiety, hostility, phobic anxiety, paranoid ideation, and psychoticism. All items are assessed using a five point Likert scale. Previous research in Dutch community and patient samples has demonstrated good reliability and validity [ 191 , 192 ].

Global functioning and impairment

Global functioning and impairment is assessed by the 36-item World Health Organization Disability Assessment Schedule 2.0 (WHODAS 2.0) interview version [ 193 ]. The WHODAS 2.0 is a general measure to assess disability in six major life domains (cognition, mobility, self-care, getting along, life activities, and participation). For each item, participants have to report how much difficulty they experienced in the last 30 days. The six domain scores and overall functioning score have shown good psychometric properties in a general population sample as well as a patient sample [ 193 ].

Quality of life

Generic quality of life is assessed using the 5-level EuroQol 5D version (EQ-5D-5L; [ 194 ]). The questionnaire measures five health state dimensions (mobility, self-care, usual activities, pain/discomfort, and anxiety/depression). Each dimension is divided into five severity levels: no problem, slight problems, moderate problems, severe problems, and extreme problems. The profiles from the five health state dimensions are assigned a value based on the Dutch social tariffs to generate health utilities [ 195 ]. These utilities will be used to calculate Quality Adjusted Life Years (QALYs) by multiplying the change in utility values between assessments by the length of the period between assessments. In addition to the five health state dimensions, the EQ-5D-5L contains a VAS item which records the patient’s self-reported health status ranging from 0 (worst health you can imagine) to 100 (best health you can imagine). The EQ-5D-5L has shown to be a reliable and valid measure among different patient groups in different countries [ 196 ].

As a complement to the EQ-5D-5L, the Mental Health Quality of Life seven-dimensional Questionnaire (MHQoL-7D; [ 197 ]) will be administered. The MHQoL-7D is a recently developed instrument to assess quality of life specifically in people with mental health problems. The MHQoL-7D consists of seven quality of life domains (self-image, independence, mood, relationships, daily activities, physical health, and hope) and a VAS item which records the patient’s self-reported psychological well-being. A study into the psychometric properties of the MHQoL-7D is currently running. The MHQoL-7D will only be included in the analysis if it is demonstrated to be a psychometrically sound instrument and Dutch social tariffs are available.

Insomnia complaints are assessed by the Insomnia Severity Index (ISI; [ 198 ]). The ISI contains seven items that are scored on a five point Likert scale. The ISI has shown to be a valid measure in community and insomnia patient samples [ 198 ], although the reliability was questionable in some studies (e.g., [ 199 , 200 ]). In addition to insomnia, the number of nights with nightmares and the total number of nightmares in the week prior to the assessment are measured using the Nightmare Frequency Questionnaire (NFQ; [ 201 ]). Based on previous research among posttraumatic stress disorder (PTSD) patients, the NFQ appears reliable for measuring nightmare frequency [ 201 ].

Well-being is measured using a single item measuring happiness [ 202 ] and the Outcome Rating Scale (ORS; [ 203 ]). The single item measures general happiness in the months prior to the assessment on a seven point Likert scale. Reliability and validity were good among undergraduates [ 202 ], and sensitivity to change was excellent in a BPD sample [ 184 ]. The ORS consists of four VAS items assessing four areas of functioning: individual (personal well-being), interpersonal (family and close relationships), social (work and/or school functioning), and overall (general sense of well-being). We slightly adapted the third dimension of the ORS by excluding friendships, because of its overlap with the second dimension (interpersonal functioning). Hafkenscheid et al. [ 204 ] reported adequate psychometric properties of the ORS is a Dutch outpatient sample.

Statistical analyses

The statistical analyses for the (cost-)effectiveness, mechanisms of change and treatment selection studies are under development. For example, according to Cohen et al. [ 48 ], the treatment selection field is still in its developmental stage and statistical methods are constantly evolving. Recently, great efforts have been made by several authors (e.g., [ 205 , 206 ]) to select the optimal prediction model by comparing different variable selection techniques. Considering the ongoing advances in methodological approaches, the statistical analyses described below should be considered as examples of appropriate analytic methods. We will determine the optimal methods at the time of the analyses. An update of the protocol will be published, including the selected statistical methods, before start of the data-analyses. The statistical analyses will be performed according to the intention-to-treat (ITT) principle (i.e., including all patients that have been randomized and received at least one treatment session). In addition to the primary analysis based on the ITT principle, a completers analysis will be conducted by excluding patients who dropped out prematurely (i.e., termination of the treatment before planned end, without patient and therapist agreeing that enough improvement has been reached to justify the termination) or deviated from the protocol (e.g., sought other psychological treatment in addition to the study treatment). No interim analyses are planned.

A two-step approach will be applied to determine the optimal treatment for a particular patient by identifying patient characteristics that predict (differential) treatment response. First, we will examine which of the candidate predictors (see Additional file 4 for an overview) predict (differential) treatment response. Many different variable selection approaches can be used to identify which of the candidate predictors contribute to the prediction of treatment outcome, for example elastic net regularization [ 207 ], Bayesian additive regression trees [ 208 ], or a combination between different variables selection procedures [ 48 ]. Second, individual treatment recommendations are generated based on a prediction model including the variables that predict (differential) treatment response. For each patient, the most beneficial treatment will be identified by using the prediction model to estimate the predicted outcomes for both treatments including the difference in predicted outcomes.

Our primary analysis will focus on individual treatment recommendations based on change in BPD manifestations and will therefore reveal the advantage in symptom relief that may be gained if patients are allocated to their predicted optimal treatment compared to their predicted non-optimal treatment. To investigate the advantage that may be gained in other outcomes, such as functioning and cost-effectiveness, generalization analyses will be performed by testing the performance of the prediction model for these outcomes.

It is hypothesized that the treatments exert a remedial effect on the frequency and severity of BPD manifestations by their impact on the BPD-treatment-specific (ST: beliefs and schema modes; DBT: emotion regulation and skills use), BPD-treatment-generic (therapeutic environment characterized by genuineness, safety, and equality), and non-specific (attachment and therapeutic alliance) mechanisms of change. Since potential mediators and outcome will be assessed multiple times, temporal patterns of change can be studied by performing mediation analysis for longitudinal data, for example multilevel autoregressive mediation analysis [ 209 ] or multilevel structural equation modeling [ 210 ]. By using advanced statistical models, the hierarchical structure of the data (repeated measures nested within patients, who in turn are nested within centers) can be taken into account and possible concurrent and temporal relations between mediators and outcome can be investigated.

Clinical effectiveness

Change in the outcome measures and the relative effectiveness of the two treatment conditions will be analyzed using mixed regression so that all available data are used, and taking into account the dependencies among observations nested within individuals nested within centers. Potential center effects are modeled by including a random effect which enables generalization of results outside the trial and maximizes statistical power [ 211 ]. Since group sessions in both treatments are offered in a semi-open format, patients will start with group treatment at different time points. One can imagine that patients starting treatment at the same time point are more interdependent compared to patients starting treatment at different time points. Therefore, we will take into account, if needed, the interdependency of patients. The underlying distributions of the mixed regression models will be determined based on the variable type (i.e., scale or nominal) and the distribution of residuals (e.g., normal, gamma, negative binomial).

Cost-effectiveness

The cost-effectiveness evaluation will be performed from a societal perspective and includes a cost-effectiveness analysis (CEA) and cost-utility analysis (CUA). The primary clinical outcome for the CEA will be the severity of the BPD manifestations and for the CUA utility scores will be derived from the quality of life instrument(s), both with a time horizon of 12 months after the end of treatment. The net benefit will be used to express cost-effectiveness. For each patient, the net benefit will be calculated by subtracting the costs incurred by the patient from the amount that the society is willing to pay for the health benefit [ 212 ]. The development of the net benefit over time and differences between the treatments will be modeled using multilevel modeling in which the hierarchical structure of the data and potential missing values are taken into account. The best fitting model to describe the development over time and the appropriate distribution of the net benefit data (e.g., gamma distribution, log-normal distribution) will be based on the data. Cost-effectiveness acceptability curves (CEACs) will be drawn showing the probability that one treatment is more cost-effective compared to the other treatment, given the observed data, for a range of willingness-to-pay values. Sensitivity analyses will be performed to address the uncertainties in methodology and assumptions and to test for the robustness of findings.

Additional substudies

Several secondary studies will be conducted, including, but not limited to, the investigation of the heterogeneity of BPD and substance abuse among BPD patients, a qualitative study into the perspectives of patients and therapists, and psychometric evaluations. First, BPD is characterized by considerable heterogeneity [ 165 , 213 ]. Over the past years, researchers have attempted to identify BPD subtypes based on different indicator variables (e.g., DSM-5 criteria, interpersonal characteristics, temperament) and different statistical strategies (e.g., exploratory factor analysis, Q-factor analysis, finite mixture modeling) [ 214 ]. The BPD subtypes that emerged differed substantially between studies. According to Hallquist and Pilkonis [ 214 ], advances in classifying BPD subtypes can be made by using a theoretical model as guidance, for example Kernberg’s theory [ 215 ]. Therefore, a substudy into the heterogeneity of BPD will be performed based on theoretically justified indicators and state-of-the-art statistical methods.

A second substudy will focus on the co-occurrence of substance abuse and BPD. Research suggests that patients with BPD and substance abuse have more severe problems, including higher rates of suicide attempts, more treatment noncompliance, and increased risk of violence, compared to BPD patients without substance abuse (e.g., [ 216 , 217 , 218 ]). However, few trials have assessed the effectiveness of treatments for BPD patients with substance abuse. In addition, research into the effect of BPD treatment on substance abuse is also limited [ 219 ]. Third, qualitative research will be conducted to explore the perspectives of patients and therapists in key areas, including predictors, mechanisms of change, the treatments, and the implementation of the results in clinical practice. Finally, psychometric evaluations of several Dutch questionnaires (e.g., Dialectical Behavior Therapy-Ways of Coping Checklist, Ultrashort BPD Checklist) will be performed.

This article described the study protocol of a multicenter RCT focusing on the (differential) treatment effectiveness of DBT and ST for patients with BPD. The primary aim of the study is to improve treatment outcome of DBT and ST for BPD patients by optimizing treatment selection through identifying patient characteristics that specify which patients will benefit most from which treatment. In addition, we aim to elucidate the change mechanisms of DBT and ST, which is crucial for improving treatments and, in turn, treatment response [ 51 , 52 , 220 ]. Finally, the comparative effectiveness and cost-effectiveness of DBT and ST will be compared.

This trial provides a unique opportunity to gain more insight into one of the main questions dominating the psychotherapy research agenda: “What works for whom and why?”. Although DBT and ST share some important characteristics, different interventions related to different assumed core deficits in BPD are provided [ 58 ]. As each treatment provides a different therapeutic milieu and focuses on different goals and tasks, a particular treatment may be a better fit with some patients compared to others [ 45 ]. In this study, patient characteristics of (differential) treatment response will be identified and individual treatment recommendations (DBT or ST) will be generated. In addition, for each patient, an estimate will be provided of the potential advantage in symptom relief that might be gained in case the patient was allocated to his or her indicated treatment. Moreover, the potential advantage in other outcomes, for example functioning and cost-effectiveness, will also be estimated. Knowing which treatment is most cost-effective for whom may lead to more efficient allocation of healthcare resources, which is important, as the current healthcare system is characterized by constraints in resources (e.g., people, time, budget; [ 221 ]). However, before a treatment selection procedure can be implemented in clinical practice, replication and external validation of the prediction model is needed. Subsequently, a prospective study in which the patient and clinician collaborate in selecting the optimal treatment (i.e., shared decision making; [ 222 ]), guided by treatment recommendations based on the prediction model, should be conducted to evaluate the advantage of a treatment selection procedure. By using a state-of-the-art approach, the results of the current study can serve as the starting point for future studies into personalized medicine among BPD patients, and is therefore of great importance.

In addition, this trial provides insight into the comparative (cost-)effectiveness of DBT and ST. Although the effectiveness of both treatments has been established, DBT and ST have not been directly compared. Therefore, and because outcome measures differ substantially between studies on the effectiveness of DBT or ST, hypotheses concerning the differential effectiveness can hardly be formulated. According to the “Dodo Bird effect” [ 223 , 224 ], all evidence-based psychotherapies are equally effective, suggesting that DBT and ST will produce equivalent outcomes. However, a meta-analysis into the comparative effectiveness of evidence-based treatments for personality disorders demonstrated that some treatments may be more effective than others [ 225 ]. In addition, Fassbinder et al. [ 226 ] hypothesized that ST may be more effective than DBT in reducing psychiatric comorbidity and improving quality of life, while DBT may lead to a better and faster reduction in self-harming and suicidal behaviors. Moreover, although not assessed in direct comparison with ST, the meta-analysis of Storebø et al. [ 25 ] into psychological treatments for BPD indicated that DBT may be especially effective for BPD-severity, self-harm, and psychosocial functioning. They also pointed out that more research into the effects of BPD-tailored treatments, including head-to-head comparisons, is needed. By focusing on an array of outcomes, this study will extend our knowledge on the potential differential effects of DBT and ST.

This study has several strengths. First, this RCT is quite inclusive in terms of patient characteristics, and as such designed to reflect clinical practice to enhance ecological validity. Second, this trial is conducted by a research group including researchers with balanced allegiance to either ST or DBT and an independent researcher (i.e., C.J.M. Wibbelink), to prevent the potential effect of research allegiance on treatment outcomes [ 227 ]. Third, we adopt a broad view on treatment response by including outcome measures reflecting different areas of recovery (e.g., BPD symptoms, functioning, well-being). Focusing on outcomes beyond symptom reduction is in line with patients’ view on recovery [ 76 , 77 ]. In addition, it follows a multi-method assessment approach, as the outcome measures include both self-report questionnaires and semi-structured interviews. Fourth, we include a large amount and broad range of patient characteristics potentially predictive of (differential) treatment response across DBT and ST. Finally, the presumed mediators and outcomes will be frequently measured on multiple time points during the treatments and mediation analyses will be performed by using state-of-the-art statistical analysis methods [ 228 ]. This allows us to establish concurrent as well as temporal relationships between the mediators and outcomes [ 228 ]. However, according to Lemmens et al. [ 229 ], understanding psychotherapeutic change may be too challenging, even in optimal research designs. Psychotherapy consists of a complex interplay of multiple mechanisms on different levels. Finding that a construct (e.g., therapeutic alliance) mediates treatment outcome does not explain how changes in this construct lead to changes in the outcome as it could involve several processes (e.g., cognitions, behaviors, emotions, neural systems) [ 63 ]. It is therefore highly questionable if these complex processes can be assessed by relatively simple mediational models. As such, this is one of the potential limitations of the current study.

This study has several other limitations that should be considered when evaluating the results. First, as power is conventionally set a 80% [ 84 , 230 , 231 , 232 ], we used a minimum criterion of 80% power for the power analyses. However, this means that we accept a 20% chance of a false negative result. Second, since DBT and ST are both evidence-based treatments for BPD, differential effects in treatment outcome may be small or non-existing. To demonstrate equivalence or small effects between treatments, a very large sample size is needed. The sample size of the current study is not large enough (i.e., does not have ≥80% power) to reliably detect a small differential treatment effect. However, the comparison of treatments is not the main aim of the study. In addition, according to Luedtke et al. [ 233 ], a sample size of at least 300 patients per condition is required to have sufficient power for applying multivariable prediction models. Nonetheless, they also noticed that a smaller sample size might be justified if studies are designed to develop prediction models that can be tested in future studies. Moreover, the results of this study can contribute to building a database including trials on BPD that can be analyzed with meta-analytic techniques.

Second, this study does not include a no treatment control group, which might affect internal validity. When improvements are found in both treatments, but no significant differences between the treatments, the absence of a control group implies that it cannot be ruled out that non-specific factors such as attention or time (maturation) caused the improvements. However, including a control group receiving no treatment would clearly be unethical (e.g., patients are at risk of suicide). For similar reasons, it is not possible to standardize medication use and crisis management sessions. Any additional treatment or medication use will be monitored and included in the analyses.

Third, one of the treatment elements of DBT is out of office hours between-session (telephone) consultation by the individual therapist. The targets of telephone consultation include, among others, reducing self-harm and suicidal behavior and teaching patients how to apply learned skills in everyday life in order to encourage skills generalization [ 19 ]. In the current study, some centers provide 24/7 access to telephone consultation by the patient’s individual therapist, while the other centers provide telephone consultation within the limitations of the individual therapists, or within working hours. In case of emergency, the standard emergency procedures of each center will be followed. Although outside of office hours availability is considered to be an essential element of DBT by some authors [ 113 , 234 ], the link between telephone consultation and outcome in DBT has not been evaluated [ 95 , 235 ]. There is some preliminary support for the importance of telephone consultation [ 236 ]. However, studies into the effectiveness of DBT that did not apply 24-h telephone consultation by the individual therapist have found positive outcomes (e.g., [ 235 , 237 ]). Van den Bosch and Sinnaeve [ 238 ] studied treatment programs of 25 DBT teams in the Netherlands. They found that only 36% of the DBT teams applied telephone consultation according to the guidelines of DBT. It can therefore be concluded that the current study is a good reflection of clinical practice, which enhances generalizability of our findings. Notwithstanding, we will monitor between-session (telephone) consultation within centers and examine potential effects.

Fourth, in this study, a component of treatment integrity (treatment adherence) will be assessed, which is, surprisingly, not standard procedure in trials investigating BPD treatments [ 25 ]. However, treatment integrity also constitutes of treatment differentiation and therapist competence [ 110 ]. Treatment adherence and treatment differentiation are closely related, in contrast to treatment adherence and therapist competence [ 239 ]. Treatment adherence represents a quantitative aspect of treatment integrity (i.e., how frequently a therapist utilizes prescribed techniques and procedures and avoids proscribed techniques and procedures), while competence represents a qualitative aspect (i.e., how well prescribed techniques and procedures are implemented) [ 109 ]. Adherence does not necessary presuppose competence; even with adequate adherence, therapists may deliver the treatment in an incompetent manner. The absence of competence ratings may threaten the validity of our results [ 109 ]. Moreover, treatment adherence will be assessed by trained master psychology students, whereas for DBT, adherence ratings by reliably trained therapists are considered the gold standard [ 240 , 241 ]. However, students will receive a training from experienced therapists.

Fifth, it is a subject of some debate whether the EQ-5D is a valid instrument to measure quality of life in BPD patients, which can affect the economic evaluation [ 81 ]. According to Brazier [ 242 ], the EQ-5D might not measure what matters to patients with psychiatric disorders. In addition, in a cost-effectiveness study among BPD patients, van Asselt et al. [ 79 ] found contradictory results on the incremental risk ratios when recovery was based on the EQ-5D compared to the BPDSI-IV. In contrast, adequate responsiveness of the EQ-5D has been found in a BPD sample [ 243 ]. In addition, Soeteman et al. [ 244 ] concluded that the EQ-5D is sensitive to changes in the health status of patients with cluster B personality disorders. In addition to the EQ-5D, quality of life will be assessed by a recently developed instrument specially developed for patients with mental health problems (MHQoL-7D; [ 197 ]). The validation of this instrument is currently in progress, but preliminary results are promising [ 197 ]. Another point for consideration is that conclusions with regard to the most cost-effective treatment choice can be affected by the amount the society is willing to pay for an additional unit of effectiveness (i.e., willingness-to-pay threshold). Soeteman et al. [ 244 ] concluded that outpatient psychotherapy for cluster B personality disorder patients is the optimal treatment choice in case society is not willing to pay more than €12.274; otherwise, day hospital psychotherapy was the optimal treatment choice. To date, there is no consensus about reasonable willingness-to-pay thresholds, although guidelines have been proposed by the Dutch healthcare authority [ 245 ]. We will therefore calculate the probability of each treatment being cost-effective for different willingness-to-pay values. As a result, the optimal treatment choice can be different for different willingness-to-pay values.

Finally, this study is conducted during the COVID-19 pandemic. The COVID-19 pandemic has significant disrupted effects on society and is related to increased burden of mental health among individuals with mental disorders [ 246 , 247 ]. Moreover, some authors suggest that patients with severe psychopathology, including BPD, may be especially at risk for symptom deterioration [ 247 , 248 ]. In addition, some patients will temporarily receive treatment via videoconferencing in case face-to-face treatment is restricted in mental healthcare centers. Research on the effectiveness of online individual psychotherapy has found positive effects for several mental health disorders, including PTSD [ 249 ], anxiety disorders [ 250 ], and depression [ 251 ]. However, research on the effectiveness of online group psychotherapy is scarce [ 95 , 252 ]. Consequently, we will control for a potential effect of the COVID-19 pandemic in the analyses.

Specialized evidence-based treatments have been developed and evaluated for BPD, including DBT and ST. However, BPD patients vary widely in their response to treatment, and poor response to one treatment does not imply poor response to another treatment. The selection of the optimal treatment for a particular patient is a daily task of the clinician, but very scant evidence is available to guide these decisions. This study will extend our knowledge on one of the main issues in psychotherapy research; understanding for whom a treatment works and how. As such, this study helps pave the way for an evidence-based personalized medicine for patients with BPD.

Trial status

Recruitment has started in January 2019 and is still ongoing. The estimated completion date of the recruitment is September 2021. Protocol version 07 is currently active.

Availability of data and materials

Not applicable.

Abbreviations

Autism Spectrum Quotient-10 items

Brief Experiential Avoidance Questionnaire

Borderline Personality Disorder

Borderline Personality Severity Index, fifth edition

Brief Symptom Inventory

Computerized Adaptive Test of Personality Disorder-Static Form

Cost-effectiveness analysis

Cost-effectiveness acceptability curves

Cost-utility analysis

Dutch Adult Reading Test

Dialectical Behavior Therapy

Dialectical Behavior Therapy-Ways of Coping Checklist

Difficulties in Emotion Regulation Scale 18

Difficulties in Emotion Regulation Scale Short Form

Diagnostic and Statistical Manual of Mental Disorders

Experience in Close Relationships-Revised

Experiences in Close Relationships-Relationship Structures questionnaire

5-level EuroQol 5D version

Frost Multidimensional Perfectionism Scale-Brief

General Psychiatric Management

Improving Access to Psychological Therapies

Locus of Control scale

Insomnia Severity Index

Intention-to-treat

Level of Personality Functioning Scale-Brief Form 2.0

Medical Ethics Committee of the Academic Medical Center

Mental Health Quality of Life seven-dimensional Questionnaire

Minnesota Multiphasic Personality Inventory-2 Restructured Form

Multidimensional Scale of Perceived Social Support

Nightmare Frequency Questionnaire

Outcome Rating Scale

Positive Mental Health scale

Posttraumatic Stress Disorder

Quality Adjusted Life Years

Randomized Clinical Trial

8-item Reflective Functioning Questionnaire

Structured Clinical Interview for DSM-5

Structured Clinical Interview for DSM-5 Disorders Clinician Version

Structural Clinical Interview for DSM-5 Personality Disorders

Structural Clinical Interview for DSM-5 Syndrome Disorders

Severity Indices of Personality Problems

Structured Clinical Interview for DSM-5 Screening Personality Questionnaire

Structured Clinical Interview for DSM-5 Syndroomstoornissen Vragenlijst

Schema Mode Inventory

Standard Protocol Items: Recommendations for Interventional Trials

Self-Reflection and Insight Scale

Schema Therapy

Traumatic Experience Checklist

Transference Focused Psychotherapy

Ten-Item Personality Inventory

Treatment Motivation Scales for Forensic Outpatient Treatment

Gordon Test of Visual Imagery Control

University of Rhode Island Change Assessment

Visual Analogue Scale

Working Alliance Inventory-Short

World Health Organization Disability Assessment Schedule 2.0

American Psychiatric Association. Diagnostic and statistical manual of mental disorders (DSM-5®). 5th ed. Arlington: American Psychiatric Publishing; 2013.

Book   Google Scholar  

Skodol AE, Gunderson JG, Pfohl B, Widiger TA, Livesley WJ, Siever LJ. The borderline diagnosis I: psychopathology comorbidity, and personality structure. Biol Psychiatry. 2002;51:936–50. https://doi.org/10.1016/S0006-3223(02)01324-0 .

Article   PubMed   Google Scholar  

Ellison WD, Rosenstein LK, Morgan TA, Zimmerman M. Community and clinical epidemiology of borderline personality disorder. Psychiatr Clin North Am. 2018;41:561–73. https://doi.org/10.1016/j.psc.2018.07.008 .

ten Have M, Verheul R, Kaasenbrood A, van Dorsselaer S, Tuithof M, Kleinjan M, et al. Prevalence rates of borderline personality disorder symptoms: a study based on the Netherlands Mental Health Survey and Incidence Study-2. BMC Psychiatry. 2016;16:249. https://doi.org/10.1186/s12888-016-0939-x .

Article   PubMed   PubMed Central   Google Scholar  

Tomko RL, Trull TJ, Wood PK, Sher KJ. Characteristics of borderline personality disorder in a community sample: comorbidity, treatment utilization, and general functioning. J Personal Disord. 2014;28:734–50. https://doi.org/10.1521/pedi_2012_26_093 .

Article   Google Scholar  

Dixon-Gordon KL, Whalen DJ, Layden BK, Chapman AL. A systematic review of personality disorders and health outcomes. Can Psychol. 2015;56:168–90. https://doi.org/10.1037/cap0000024 .

El-Gabalawy R, Katz LY, Sareen J. Comorbidity and associated severity of borderline personality disorder and physical health conditions in a nationally representative sample. Psychosom Med. 2010;72:641–7. https://doi.org/10.1097/PSY.0b013e3181e10c7b .

Laurenssen EMP, Eeren HV, Kikkert MJ, Peen J, Westra D, Dekker JJM, et al. The burden of disease in patients eligible for mentalization-based treatment (MBT): quality of life and costs. Health Qual Life Outcomes. 2016;14:145. https://doi.org/10.1186/s12955-016-0538-z .

Paris J. Suicidality in borderline personality disorder. Med Lith. 2019;55. https://doi.org/10.3390/medicina55060223 .

Pompili M, Girardi P, Ruberto A, Tatarelli R. Suicide in borderline personality disorder: a meta-analysis. Nord J Psychiatry. 2005;59:319–24. https://doi.org/10.1080/08039480500320025 .

Black DW, Blum N, Pfohl B, Hale N. Suicidal behavior in borderline personality disorder: prevalence, risk factors, prediction, and prevention. J Personal Disord. 2004;18:226–39. https://doi.org/10.1521/pedi.18.3.226.35445 .

Soloff PH, Chiappetta L. 10-year outcome of suicidal behavior in borderline personality disorder. J Personal Disord. 2019;33:82–100. https://doi.org/10.1521/pedi_2018_32_332 .

Kjaer JN, Biskin R, Vestergaard C, Munk-Jorgensen P. All-cause mortality of hospital-treated borderline personality disorder: a nationwide cohort study. J Personal Disord. 2020;34:723–35. https://doi.org/10.1521/pedi_2018_32_403 .

Bender DS, Dolan RT, Skodol AE, Sanislow CA, Dyck IR, McGlashan TH, et al. Treatment utilization by patients with personality disorders. Am J Psychiatry. 2001;158:295–302. https://doi.org/10.1176/appi.ajp.158.2.295 .

Article   CAS   PubMed   Google Scholar  

Bode K, Vogel R, Walker J, Kroeger C. Health care costs of borderline personality disorder and matched controls with major depressive disorder: a comparative study based on anonymized claims data. Eur J Health Econ. 2017;18:1125–35. https://doi.org/10.1007/s10198-016-0858-2 .

van Asselt ADI, Dirksen CD, Arntz A, Severens JL. The cost of borderline personality disorder: societal cost of illness in BPD-patients. Eur Psychiatry. 2007;22:354–61. https://doi.org/10.1016/j.eurpsy.2007.04.001 .

Wagner T, Fydrich T, Stiglmayr C, Marschall P, Salize H, Renneberg B, et al. Societal cost-of-illness in patients with borderline personality disorder one year before, during and after dialectical behavior therapy in routine outpatient care. Behav Res Ther. 2014;61:12–22. https://doi.org/10.1016/j.brat.2014.07.004 .

Sheehan L, Nieweglowski K, Corrigan P. The stigma of personality disorders. Curr Psychiatry Rep. 2016;18:11. https://doi.org/10.1007/s11920-015-0654-1 .

Linehan MM. Cognitive-behavioral therapy of borderline personality disorder. New York: Guilford; 1993.

Google Scholar  

Linehan MM. DBT skills training manual. 2nd ed. New York: Guilford Publications; 2015.

Arntz A, Van Genderen H. Schema therapy for borderline personality disorder. Chichester: Wiley Online Library; 2009.

Young JE, Klosko JS, Weishaar ME. Schema therapy. New York: Guildford; 2003.

Jacob GA, Arntz A. Schema therapy for personality disorders-a review. Int J Cogn Ther. 2013;6:171–85. https://doi.org/10.1521/ijct.2013.6.2.171 .

Sempertegui GA, Karreman A, Arntz A, Bekker MHJ. Schema therapy for borderline personality disorder: a comprehensive review of its empirical foundations, effectiveness and implementation possibilities. Clin Psychol Rev. 2013;33:426–47. https://doi.org/10.1016/j.cpr.2012.11.006 .

Storebø OJ, Stoffers-Winterling JM, Völlm BA, Kongerslev MT, Mattivi JT, Jørgensen MS, et al. Psychological therapies for people with borderline personality disorder. Cochrane Database Syst Rev. 2020:CD012955. https://doi.org/10.1002/14651858.CD012955.pub2 .

Meuldijk D, McCarthy A, Bourke ME, Grenyer BFS. The value of psychological treatment for borderline personality disorder: systematic review and cost offset analysis of economic evaluations. PLoS One. 2017;12:e0171592. https://doi.org/10.1371/journal.pone.0171592 .

Article   CAS   PubMed   PubMed Central   Google Scholar  

Huibers MJH, Lorenzo-Luaces L, Cuijpers P, Kazantzis N. On the road to personalized psychotherapy: a research agenda based on cognitive behavior therapy for depression. Front Psychiatry. 2021;11:607508. https://doi.org/10.3389/fpsyt.2020.607508 .

Woodbridge J, Townsend M, Reis S, Singh S, Grenyer BF. Non-response to psychotherapy for borderline personality disorder: a systematic review. Aust N Z J Psychiatry. 2021:1–17. https://doi.org/10.1177/00048674211046893 .

Barnicot K. Evidence-based psychological interventions for borderline personality disorder in the United Kingdom—who falls through the gaps? J Psychol Ther. 2020;5:148–67.

Giesen-Bloo J, van Dyck R, Spinhoven P, van Tilburg W, Dirksen C, van Asselt T, et al. Outpatient psychotherapy for borderline personality disorder - randomized trial of schema-focused therapy vs transference-focused psychotherapy. Arch Gen Psychiatry. 2006;63:649–58. https://doi.org/10.1001/archpsyc.63.6.649 .

McMain SF, Guimond T, Streiner DL, Cardish RJ, Links PS. Dialectical behavior therapy compared with general psychiatric management for borderline personality disorder: clinical outcomes and functioning over a 2-year follow-up. Am J Psychiatry. 2012;169:650–61. https://doi.org/10.1176/appi.ajp.2012.11091416 .

Gülüm İV. Dropout in schema therapy for personality disorders. Res Psychother. 2018;21(2):116-122. https://doi.org/10.4081/ripppo.2018.314 .

Dixon LJ, Linardon J. A systematic review and meta-analysis of dropout rates from dialectical behaviour therapy in randomized controlled trials. Cogn Behav Ther. 2020;49:181–96. https://doi.org/10.1080/16506073.2019.1620324 .

Meehl PE. Clinical versus statistical prediction: a theoretical analysis and a review of the evidence. Minneapolis: University of Minnesota Press; 1954.

DeRubeis RJ, Cohen ZD, Forand NR, Fournier JC, Gelfand LA, Lorenzo-Luaces L. The Personalized Advantage Index: translating research on prediction into individualized treatment recommendations. A demonstration. PLoS One. 2014;9:e83875. https://doi.org/10.1371/journal.pone.0083875 .

Kazdin AE. Evidence-based psychotherapies I: qualifiers and limitations in what we know. S Afr J Psychol. 2014;44:381–403. https://doi.org/10.1177/0081246314533750 .

Cohen ZD, DeRubeis RJ. Treatment selection in depression. Annu Rev Clin Psychol. 2018;14:209–36. https://doi.org/10.1146/annurev-clinpsy-050817084746 .

Hamburg MA, Collins FS. The path to personalized medicine. N Engl J Med. 2010;363:301–4. https://doi.org/10.1056/NEJMp1006304 .

Arntz A, Stupar-Rutenfrans S, Bloo J, van Dyck R, Spinhoven P. Prediction of treatment discontinuation and recovery from borderline personality disorder: results from an RCT comparing schema therapy and transference focused psychotherapy. Behav Res Ther. 2015;74:60–71. https://doi.org/10.1016/j.brat.2015.09.002 .

Verheul R, Van Den Bosch LMC, Koeter MWJ, De Ridder MAJ, Stijnen T, Van Den Brink W. Dialectical behaviour therapy for women with borderline personality disorder: 12-month, randomised clinical trial in The Netherlands. Br J Psychiatry. 2003;182:135–40.  https://doi.org/10.1192/bjp.182.2.135 .

Bohart AC, Wade AG. The client in psychotherapy. In: Lambert MJ, editor. Bergin and Garfield’s handbook of psychotherapy and behavior change. 6th ed. Hoboken: Wiley; 2013. p. 219–57.

Clarkin JF, Levy KN. The influence of client variables on psychotherapy. In: Lambert MJ, editor. Bergin and Garfield’s handbook of psychotherapy and behavior change. New York: Wiley; 2004. p. 194–226.

Wallace ML, Frank E, Kraemer HC. A novel approach for developing and interpreting treatment moderator profiles in randomized clinical trials. JAMA Psychiatry. 2013;70:1241–7. https://doi.org/10.1001/jamapsychiatry.2013.1960 .

Wampold BE, Imel ZE. The great psychotherapy debate: the evidence for what makes psychotherapy work. 2nd ed. New York: Routledge; 2015.

Keefe JR, Kim TT, DeRubeis RJ, Streiner DL, Links PS, McMain SF. Treatment selection in borderline personality disorder between dialectical behavior therapy and psychodynamic psychiatric management. Psychol Med. 2020;24:1–9. https://doi.org/10.1017/S0033291720000550 .

Zilcha-Mano S. Major developments in methods addressing for whom psychotherapy may work and why. Psychother Res. 2019;29:693–708. https://doi.org/10.1080/10503307.2018.1429691 .

Kraemer HC. Discovering, comparing, and combining moderators of treatment on outcome after randomized clinical trials: a parametric approach. Stat Med. 2013;32:1964–73. https://doi.org/10.1002/sim.5734 .

Cohen ZD, Kim TT, Van HL, Dekker JJM, Driessen E. A demonstration of a multi-method variable selection approach for treatment selection: recommending cognitive-behavioral versus psychodynamic therapy for mild to moderate adult depression. Psychother Res. 2020;30:137–50. https://doi.org/10.1080/10503307.2018.1563312 .

van Bronswijk SC, DeRubeis RJ, Lemmens LH, Peeters FP, Keefe JR, Cohen ZD, et al. Precision medicine for long-term depression outcomes using the Personalized Advantage Index approach: cognitive therapy or interpersonal psychotherapy? Psychol Med. 2021;51:279–89. https://doi.org/10.1017/S0033291719003192 .

Huibers MJ, Cohen ZD, Lemmens LH, Arntz A, Peeters FP, Cuijpers P, et al. Predicting optimal outcomes in cognitive therapy or interpersonal psychotherapy for depressed individuals using the personalized advantage index approach. PLoS One. 2015;10:e0140771. https://doi.org/10.1371/journal.pone.0140771 .

Kazdin AE, Nock MK. Delineating mechanisms of change in child and adolescent therapy: methodological issues and research recommendations. J Child Psychol Psychiatry. 2003;44:1116–29. https://doi.org/10.1111/1469-7610.00195 .

Kraemer HC, Wilson GT, Fairburn CG, Agras WS. Mediators and moderators of treatment effects in randomized clinical trials. Arch Gen Psychiatry. 2002;59:877–83. https://doi.org/10.1001/archpsyc.59.10.877 .

Orlinsky DE, Rönnestad MH, Willutzki U. Fifty years of process-outcome research: continuity and change. In: Lambert MJ, editor. Bergin and Garfield’s handbook of psychotherapy and behavior change. New York: Wiley; 2004. p. 307–89.

Forster C, Berthollier N, Rawlinson D. A systematic review of potential mechanisms of change in psychotherapeutic interventions for personality disorder. J Psychol Psychother. 2014;4(133):2161–0487. https://doi.org/10.4172/2161-0487.1000133 .

Lynch TR, Chapman AL, Rosenthal MZ, Kuo JR, Linehan MM. Mechanisms of change in dialectical behavior therapy: theoretical and empirical observations. J Clin Psychol. 2006;62:459–80. https://doi.org/10.1002/jclp.20243 .

Rudge S, Feigenbaum JD, Fonagy P. Mechanisms of change in dialectical behaviour therapy and cognitive behaviour therapy for borderline personality disorder: a critical review of the literature. J Ment Health. 2020;29:92–102. https://doi.org/10.1080/09638237.2017.1322185 .

Yakin D, Grasman R, Arntz A. Schema modes as a common mechanism of change in personality pathology and functioning: results from a randomized controlled trial. Behav Res Ther. 2020;126:103553. https://doi.org/10.1016/j.brat.2020.103553 .

Fassbinder E, Schweiger U, Martius D, Brand-de Wilde O, Arntz A. Emotion regulation in schema therapy and dialectical behavior therapy. Front Psychol. 2016;7:1373. https://doi.org/10.3389/fpsyg.2016.01373 .

Westen D, Weinberger J. When clinical description becomes statistical prediction. Am Psychol. 2004;59:595–613. https://doi.org/10.1037/0003-066X.59.7.595 .

Kessler RC. The potential of predictive analytics to provide clinical decision support in depression treatment planning. Curr Opin Psychiatry. 2018;31:32–9. https://doi.org/10.1097/YCO.0000000000000377 .

Spinhoven P, Giesen-Bloo J, van Dyck R, Arntz A. Can assessors and therapists predict the outcome of long-term psychotherapy in borderline personality disorder? J Clin Psychol. 2008;64:667–86. https://doi.org/10.1002/jclp.20466 .

Tryon WW. Mediators and mechanisms. Clin Psychol Sci. 2018;6:619–28. https://doi.org/10.1177/2167702618765791 .

Holmes EA, Ghaderi A, Harmer CJ, Ramchandani PG, Cuijpers P, Morrison AP, et al. The Lancet Psychiatry Commission on psychological treatments research in tomorrow's science. Lancet Psychiatry. 2018;5:237–86.  https://doi.org/10.1016/S2215-0366(17)30513-8 .

Farrell JM, Shaw IA. Schema therapy groups for borderline personality disorder patients: the best of both worlds of group psychotherapy. In: Roediger E, Jacobs G, editors. Fortschritte der Schematherapie (Advances in schema therapy). Göttingen: Hogrefe; 2010.

Gunderson J. Borderline personality disorder: an overview. Soc Work Ment Health. 2008;6:5–12. https://doi.org/10.1300/J200v06n01_02 .

Linehan MM. Validation and psychotherapy. In: Bohart A, Greenberg L, editors. Empathy reconsidered: new directions in psychotherapy. Washington, DC: American Psychological Association; 1997. p. 353–92.

Chapter   Google Scholar  

Swenson CR, Choi-Kain LW. Mentalization and dialectical behavior therapy. Am J Psychother. 2015;69:199–217. https://doi.org/10.1176/appi.psychotherapy.2015.69.2.199 .

Barnicot K, Katsakou C, Bhatti N, Savill M, Fearns N, Priebe S. Factors predicting the outcome of psychotherapy for borderline personality disorder: a systematic review. Clin Psychol Rev. 2012;32:400–12. https://doi.org/10.1016/j.cpr.2012.04.004 .

Taylor PJ, Rietzschel J, Danquah A, Berry K. The role of attachment style, attachment to therapist, and working alliance in response to psychological therapy. Psychol Psychother. 2015;88:240–53. https://doi.org/10.1111/papt.12045 .

Gunderson JG, Herpertz SC, Skodol AE, Torgersen S, Zanarini MC. Borderline personality disorder. Nat Rev Dis Primers. 2018;4:18029. https://doi.org/10.1038/nrdp.2018.29 .

Skodol AE. Impact of personality pathology on psychosocial functioning. Curr Opin Psychol. 2018;21:33–8. https://doi.org/10.1016/j.copsyc.2017.09.006 .

Skodol AE, Gunderson JG, McGlashan TH, Dyck IR, Stout RL, Bender DS, et al. Functional impairment in patients with schizotypal, borderline, avoidant, or obsessive-compulsive personality disorder. Am J Psychiatry. 2002;159:276–83.  https://doi.org/10.1176/appi.ajp.159.2.276 .

Gunderson JG, Stout RL, McGlashan TH, Shea T, Morey LC, Grilo CM, et al. Ten-year course of borderline personality disorder psychopathology and function from the collaborative longitudinal personality disorders study. Arch Gen Psychiatry. 2011;68:827–37. https://doi.org/10.1001/archgenpsychiatry.2011.37 .

Chakhssi F, Zoet JM, Oostendorp JM, Noordzij ML, Sommers-Spijkerman M. Effect of psychotherapy for borderline personality disorder on quality of life: a systematic review and meta-analysis. J Personal Disord. 2019:1–15. https://doi.org/10.1521/pedi_2019_33_439 .

Zanarini MC, Frankenburg FR, Reich DB, Fitzmaurice G. The 10-year course of psychosocial functioning among patients with borderline personality disorder and axis II comparison subjects. Acta Psychiatr Scand. 2010;122:103–9. https://doi.org/10.1111/j.1600-0447.2010.01543.x .

Katsakou C, Marougka S, Barnicot K, Savill M, White H, Lockwood K, et al. Recovery in borderline personality disorder (BPD): a qualitative study of service users’ perspectives. PLoS One. 2012;7:e36517. https://doi.org/10.1371/journal.pone.0036517 .

Lariviere N, Couture E, Blackburn C, Carbonneau M, Lacombe C, Schinck S, et al. Recovery, as experienced by women with borderline personality disorder. Psychiatr Q. 2015;86:555–68. https://doi.org/10.1007/s11126-015-9350-x .

Bamelis LLM, Arntz A, Wetzelaer P, Verdoorn R, Evers SMAA. Economic evaluation of schema therapy and clarification-oriented psychotherapy for personality disorders: a multicenter, randomized controlled trial. J Clin Psychiatry. 2015;76:E1432–+. https://doi.org/10.4088/JCP.14m09412 .

van Asselt ADI, Dirksen CD, Arntz A, Giesen-Bloo JH, van Dyck R, Spinhoven P, et al. Out-patient psychotherapy for borderline personality disorder: cost-effectiveness of schema-focused therapy v. transference-focused psychotherapy. Br J Psychiatry. 2008;192:450–7. https://doi.org/10.1192/bjp.bp.106.033597 .

Wetzelaer P, Farrell J, Evers SMAA, Jacob GA, Lee CW, Brand O, et al. Design of an international multicentre RCT on group schema therapy for borderline personality disorder. BMC Psychiatry. 2014;14:319. https://doi.org/10.1186/s12888-014-0319-3 .

Brettschneider C, Riedel-Heller S, Koenig H. A systematic review of economic evaluations of treatments for borderline personality disorder. PLoS One. 2014;9:e107748. https://doi.org/10.1371/journal.pone.0107748 .

Krawitz R, Miga EM. Cost-effectiveness of dialectical behaviour therapy for borderline personality disorder. In: Swales MA, editor. The Oxford handbook of dialectical behaviour therapy. Oxford: Oxford University Press; 2019.

Chan A, Tetzlaff JM, Altman DG, Laupacis A, Gotzsche PC, Krleza-Jeric K, et al. SPIRIT 2013 statement: defining standard protocol items for clinical trials. Ann Intern Med. 2013;158:200–7. https://doi.org/10.7326/0003-4819-158-3-201302050-00583 .

Lakens D. Sample size justification; 2021. https://doi.org/10.31234/osf.io/9d3yf .

Adams G, Gulliford MC, Ukoumunne OC, Eldridge S, Chinn S, Campbell MJ. Patterns of intra-cluster correlation from primary care research to inform study design and analysis. J Clin Epidemiol. 2004;57:785–94. https://doi.org/10.1016/j.jclinepi.2003.12.013 .

Eldridge SM, Ashby D, Feder GS, Rudnicka AR, Ukoumunne OC. Lessons for cluster randomized trials in the twenty-first century: a systematic review of trials in primary care. Clin Trials. 2004;1:80–90. https://doi.org/10.1191/1740774504cn006rr .

Kenny DA. Mediation. 2016. http://davidakenny.net/cm/mediate.htm . Accessed 15 Jan 2021.

Kenny DA. MedPower: an interactive tool for the estimation of power in tests of mediation. 2017. https://davidakenny.shinyapps.io/MedPower/ . Accessed 15 Jan 2021.

Kenny DA, Judd CM. Power anomalies in testing mediation. Psychol Sci. 2014;25:334–9. https://doi.org/10.1177/0956797613502676 .

Schoemann AM, Boulton AJ, Short SD. Determining power and sample size for simple and complex mediation models. Soc Psychol Personal Sci. 2017;8:379–86. https://doi.org/10.1177/1948550617715068 .

Pocock SJ, Simon R. Sequential treatment assignment with balancing for prognostic factors in the controlled clinical trial. Biometrics. 1975;31(1):103–15.  https://doi.org/10.2307/2529712 .

Taves DR. Minimization: a new method of assigning patients to treatment and control groups. Clin Pharmacol Ther. 1974;15:443–53. https://doi.org/10.1002/cpt1974155443 .

Scott NW, McPherson GC, Ramsay CR, Campbell MK. The method of minimization for allocation to clinical trials: a review. Control Clin Trials. 2002;23:662–74. https://doi.org/10.1016/S0197-2456(02)00242-8 .

Altman DG, Schulz KF. Statistics notes - concealing treatment allocation in randomised trials. Br Med J. 2001;323:446–7. https://doi.org/10.1136/bmj.323.7310.446 .

Article   CAS   Google Scholar  

van Leeuwen H, Sinnaeve R, Witteveen U, Van Daele T, Ossewaarde L, Egger JI, et al. Reviewing the availability, efficacy and clinical utility of Telepsychology in dialectical behavior therapy (Tele-DBT). Borderline Personal Disord Emot Dysregul. 2021;8:1–15. https://doi.org/10.1186/s40479-021-00165-7 .

den Bosch V, Louisa MC, Koeter MW, Stijnen T, Verheul R, van den Brink W. Sustained efficacy of dialectical behaviour therapy for borderline personality disorder. Behav Res Ther. 2005;43:1231–41. https://doi.org/10.1016/j.brat.2004.09.008 .

Royal College of Psychiatrists. PS06/19 services for people diagnosed with personality disorder. 2019. https://www.rcpsych.ac.uk/docs/default-source/improvingcare/better-mh-policy/position-statements/ps01_20.pdf?sfvrsn=85af7fbc_2 .

Safer DL, Telch CF, Chen EY. Dialectical behavior therapy for binge eating and bulimia. New York: Guilford Press; 2009.

van Leeuwen JPA, van den Bosch LMC, Ossewaarde L, Sinnaeve R, Egger JIM. Introducing a pre-post study: efficacy of a blended dialectical behavior therapy consolidation group following one year of standard. Paper presented at the strategic planning meeting for dialectical behavior therapy. Seattle; 2017.

Young JE, Klosko JS. Reinventing your life: how to break free from negative life patterns. New York: Dutton; 1993.

Arntz A, Klokman J, Sieswerda S. An experimental test of the schema mode model of borderline personality disorder. J Behav Ther Exp Psychiatry. 2005;36:226–39. https://doi.org/10.1016/j.jbtep.2005.05.005 .

Kellogg SH, Young JE. Schema therapy for borderline personality disorder. J Clin Psychol. 2006;62:445–58. https://doi.org/10.1002/jclp.20240 .

Farrell JM, Shaw IA. Group schema therapy for borderline personality disorder: A step-by-step treatment manual with patient workbook. Hoboken: Wiley; 2012.

Farrell JM, Shaw IA, Webber MA. A schema-focused approach to group psychotherapy for outpatients with borderline personality disorder: a randomized controlled trial. J Behav Ther Exp Psychiatry. 2009;40:317–28. https://doi.org/10.1016/j.jbtep.2009.01.002 .

Arntz A, van Genderen H. Schema therapy for borderline personality disorder. 2nd ed. Hoboken: Wiley-Blackwell; 2020.

Linehan MM. Skills training manual for treating borderline personality disorder. New York: Guilford press; 1993.

Wagner AW, Linehan MM. Applications of dialectical behavior therapy to posttraumatic stress disorder and related problems. In: Follette VM, Ruzek JI, editors. Cognitive behavioral therapies for trauma. 2nd ed. New York: The Guilford Press; 2006. p. 117–45.

Dimeff LA, Rizvi SL, Koerner K. Dialectical behavior therapy in clinical practice. applications across disorders and settings. 2nd ed. New York: Guilford Press; 2020.

Perepletchikova F, Treat TA, Kazdin AE. Treatment integrity in psychotherapy research: analysis of the studies and examination of the associated factors. J Consult Clin Psychol. 2007;75:829–41. https://doi.org/10.1037/0022-006X.75.6.829 .

Waltz J, Addis ME, Koerner K, Jacobson NS. Testing the integrity of a psychotherapy protocol - assessment of adherence and competence. J Consult Clin Psychol. 1993;61:620–30. https://doi.org/10.1037/0022-006X.61.4.620 .

Young JE, Arntz A, Giesen-Bloo J. Therapy adherence and competence scale for Schema focused therapy for borderline personality disorder-adapted version. Maastricht: University of Maastricht; 2006.

Zarbock G, Farrell J, Schikowski A, Heimann I, Shaw I, Reiss N, et al. Group schema therapy rating scale - revised (GSTRS-R); 2014. p. 29. https://doi.org/10.4225/23/585a265e14ab8 .

Harned MS, Schmidt SC, Korslund KE. The dialectical behavior therapy adherence checklist for individual therapy (DBT AC-I). 2021. https://www.dbtadherence.com/ .

Hao F, Tan W, Jiang L, Zhang L, Zhao X, Zou Y, et al. Do psychiatric patients experience more psychiatric symptoms during COVID-19 pandemic and lockdown? A case-control study with service and research implications for immunopsychiatry. Brain Behav Immun. 2020;87:100–6. https://doi.org/10.1016/j.bbi.2020.04.069 .

Qualtrics. 2019. https://www.qualtrics.com . Accessed 15 Jan 2021.

First MB, Williams J, Benjamin LS, Spitzer RL. User’s guide for the SCID-5-PD (structured clinical interview for DSM-5 personality disorder). Arlington: American Psychiatric Association; 2015.

First MB, Williams JBW, Karg RS, Spitzer RL. Gestructureerd klinisch interview voor DSM-5 Syndroomstoornissen (SCID-5-S). Nederlandse vertaling van Structural clinical interview for DSM-5® disorders-clinician version (SCID-5-CV) en user’s guide to structured clinical interview for DSM-5® disorders-clinician version en delen van structured clinical interview for DSM-5® disorders-research version (SCID-5-RV), first edition. Amsterdam: Boom; 2018.

First MB, Williams JB, Karg RS, Spitzer RL. Structured clinical interview for DSM-5 disorders, clinician version (SCID-5-CV). Arlington: American Psychiatric Association; 2016.

Somma A, Borroni S, Maffei C, Besson E, Garbini A, Granozio S, et al. Inter-rater reliability of the Italian translation of the structured clinical interview for DSM-5 personality disorders (SCID-5-PD): a study on consecutively admitted clinical adult participants. J Psychopathol. 2017;23:105–11.

Mohammadkhani P, Forouzan AS, Hooshyari Z, Abasi I. Psychometric properties of Persian version of structured clinical interview for DSM-5-research version (SCID-5-RV): a diagnostic accuracy study. Iran J Psychiatry Behav Sci. 2020;14. https://doi.org/10.5812/ijpbs.100930 .

Osório FL, Loureiro SR, Hallak JEC, Machado-de-Sousa JP, Ushirohira JM, Baes CV, et al. Clinical validity and intrarater and test–retest reliability of the Structured Clinical Interview for DSM-5–Clinician Version (SCID-5-CV). Psychiatry Clin Neurosci. 2019;73:754–60. https://doi.org/10.1111/pcn.12931 .

Shankman SA, Funkhouser CJ, Klein DN, Davila J, Lerner D, Hee D. Reliability and validity of severity dimensions of psychopathology assessed using the Structured Clinical Interview for DSM-5 (SCID). Int J Methods Psychiatr Res. 2018;27:e1590. https://doi.org/10.1002/mpr.1590 .

First MB, Williams JBW, Benjamin LS, Spitzer RL. Structured Clinical Interview for DSM-5 Screening Personality Questionnaire (SCID-5-SPQ). Arlington: American Psychiatric Association; 2016.

Arntz A, Kamphuis JH, Derks JL. Gestructureerd klinisch interview voor DSM-5 Syndroomstoornissen Vragenlijst (SCID-5-SV). Amsterdam: Boom; 2018.

Allison C, Auyeung B, Baron-Cohen S. Toward brief “red flags” for autism screening: the short autism spectrum quotient and the short quantitative checklist in 1,000 cases and 3,000 controls. J Am Acad Child Adolesc Psychiatry. 2012;51:202–212.e7. https://doi.org/10.1016/j.jaac.2011.11.003 .

Lundin A, Kosidou K, Dalman C. Measuring autism traits in the adult general population with the brief autism-spectrum quotient, AQ-10: findings from the Stockholm public health cohort. J Autism Dev Disord. 2019;49:773–80. https://doi.org/10.1007/s10803-018-3749-9 .

Drieschner KH, Boomsma A. The treatment motivation scales for forensic outpatient treatment (TMS-F) construction and psychometric evaluation. Assessment. 2008;15:224–41. https://doi.org/10.1177/1073191107311650 .

Gámez W, Chmielewski M, Kotov R, Ruggero C, Suzuki N, Watson D. The brief experiential avoidance questionnaire: development and initial validation. Psychol Assess. 2014;26:35–45. https://doi.org/10.1037/a0034473 .

Verheul R, Andrea H, Berghout CC, Dolan C, Busschbach JJ, van der Kroft PJA, et al. Severity Indices of Personality Problems (SIPP-118): development, factor structure, reliability, and validity. Psychol Assess. 2008;20:23. https://doi.org/10.1037/1040-3590.20.1.23 .

Roberts C, Stark P. Readiness for self-directed change in professional behaviours: factorial validation of the Self-reflection and Insight Scale. Med Educ. 2008;42:1054–63. https://doi.org/10.1111/j.1365-2923.2008.03156.x .

van Dulmen SA, Maas M, Staal JB, Rutten G, Kiers H, Nijhuis-van der Sanden M, et al. Effectiveness of peer assessment for implementing a Dutch physical therapy low back pain guideline: cluster randomized controlled trial. Phys Ther. 2014;94:1396–409. https://doi.org/10.2522/ptj.20130286 .

Grant AM, Franklin J, Langford P. The self-reflection and insight scale: a new measure of private self-consciousness. Soc Behav Pers. 2002;30:821–35. https://doi.org/10.2224/sbp.2002.30.8.821 .

Sanderman R. Life events, mediating variables and psychological distress: a longitudinal study. Groningen: University of Groningen; 1988.

Kamphuis JH, Emmelkamp P. Crime-related trauma: psychological distress in victims of bankrobbery. J Anxiety Disord. 1998;12:199–208. https://doi.org/10.1016/S0887-6185(98)00009-7 .

Weekers LC, Hutsebaut J, Kamphuis JH. The Level of Personality Functioning Scale-Brief Form 2.0: Update of a brief instrument for assessing level of personality functioning. Personal Ment Health. 2019;13:3–14. https://doi.org/10.1002/pmh.1434 .

Richardson A. Mental imagery. New York: Springer; 1969.

Lequerica A, Rapport L, Axelrod BN, Telmet K, Whitman RD. Subjective and objective assessment methods of mental imagery control: construct validation of self-report measures. J Clin Exp Neuropsychol. 2002;24:1103–16. https://doi.org/10.1076/jcen.24.8.1103.8370 .

Odou N, Vella-Brodrick DA. The efficacy of positive psychology interventions to increase well-being and the role of mental imagery ability. Soc Indic Res. 2013;110:111–29. https://doi.org/10.1007/s11205-011-9919-1 .

Pérez-Fabello MJ, Campos A. Factor structure and internal consistency of the Spanish version of the Gordon Test of Visual Imagery Control. Psychol Rep. 2004;94:761–6. https://doi.org/10.2466/pr0.94.3.761-766 .

White K, Sheehan PW, Ashton R. Imagery assessment: a survey of self-report measures. J Ment Imag. 1977;1:145–69.

Fonagy P, Luyten P, Moulton-Perkins A, Lee Y, Warren F, Howard S, et al. Development and validation of a self-report measure of mentalizing: the reflective functioning questionnaire. PLoS One. 2016;11:e0158678. https://doi.org/10.1371/journal.pone.0158678 .

De Meulemeester C, Vansteelandt K, Luyten P, Lowyck B. Mentalizing as a mechanism of change in the treatment of patients with borderline personality disorder: a parallel process growth modeling approach. Personal Disord. 2018;9:22–9. https://doi.org/10.1037/per0000256 .

Morandotti N, Brondino N, Merelli A, Boldrini A, De Vidovich GZ, Ricciardo S, et al. The Italian version of the Reflective Functioning Questionnaire: validity data for adults and its association with severity of borderline personality disorder. PLoS One. 2018;13:e0206433. https://doi.org/10.1371/journal.pone.0206433 .

Burgess AM, Frost RO, DiBartolo PM. Development and validation of the frost multidimensional perfectionism scale-brief. J Psychoeduc Assess. 2016;34:620–33. https://doi.org/10.1177/0734282916651359 .

Hofmans J, Kuppens P, Allik J. Is short in length short in content? An examination of the domain representation of the Ten Item Personality Inventory scales in Dutch language. Personal Individ Differ. 2008;45:750–5. https://doi.org/10.1016/j.paid.2008.08.004 .

Gosling SD, Rentfrow PJ, Swann WB Jr. A very brief measure of the Big-Five personality domains. J Res Pers. 2003;37:504–28. https://doi.org/10.1016/S0092-6566(03)00046-1 .

Lukat J, Margraf J, Lutz R, van der Veld WM, Becker ES. Psychometric properties of the positive mental health scale (PMH-scale). BMC Psychol. 2016;4:1–14. https://doi.org/10.1186/s40359-016-0111-x .

Ben-Porath YS, Tellegen A. MMPI-2-RF. Manual for administration, scoring, and interpretation. Minneapolis: University of Minnesota Press; 2008.

Tellegen A, Ben-Porath YS. MMPI-2-RF. Technical manual. Minneapolis: University of Minnesota Press; 2008.

DiClemente CC, Bellino LE, Neavins TM. Motivation for change and alcoholism treatment. Alcohol Res Health. 1999;23:86–92.

CAS   PubMed   PubMed Central   Google Scholar  

DiClemente CC, Hughes SO. Stages of change profiles in outpatient alcoholism treatment. J Subst Abus. 1990;2:217–35. https://doi.org/10.1016/S0899-3289(05)80057-4 .

McConnaughy EA, Prochaska JO, Velicer WF. Stages of change in psychotherapy: measurement and sample profiles. Psychother Theory Res Pract. 1983;20:368–75. https://doi.org/10.1037/h0090198 .

Carbonari JP, DiClemente CC. Using transtheoretical model profiles to differentiate levels of alcohol abstinence success. J Consult Clin Psychol. 2000;68:810. https://doi.org/10.1037/0022-006X.68.5.810 .

Carbonari JP, DiClemente CC, Zweben A. A readiness to change scale: Its development, validation, and usefulness. Paper presented at the annual meeting of the Association for Advancement of Behavior Therapy. San Diego; 1994.

Dozois DJ, Westra HA, Collins KA, Fung TS, Garry JK. Stages of change in anxiety: psychometric properties of the University of Rhode Island Change Assessment (URICA) scale. Behav Res Ther. 2004;42:711–29. https://doi.org/10.1016/S0005-7967(03)00193-1 .

Simms LJ, Goldberg LR, Roberts JE, Watson D, Welte J, Rotterman JH. Computerized Adaptive Assessment of Personality Disorder: introducing the CAT-PD Project. J Pers Assess. 2011;93:380–9. https://doi.org/10.1080/00223891.2011.577475 .

Clark DM. Implementing NICE guidelines for the psychological treatment of depression and anxiety disorders: the IAPT experience. Int Rev Psychiatry. 2011;23:318–27. https://doi.org/10.3109/09540261.2011.606803 .

Zimet GD, Dahlem NW, Zimet SG, Farley GK. The multidimensional scale of perceived social support. J Pers Assess. 1988;52:30–41. https://doi.org/10.1207/s15327752jpa5201_2 .

Cecil H, Stanley MA, Carrion PG, Swann A. Psychometric properties of the MSPSS and NOS in psychiatric outpatients. J Clin Psychol. 1995;51:593–602. https://doi.org/10.1002/1097-4679(199509)51:53.0.CO;2-W .

O'Toole SK, Diddy E, Kent M. Mindfulness and emotional well-being in women with borderline personality disorder. Mindfulness. 2012;3:117–23. https://doi.org/10.1007/s12671-011-0085-y .

Aviram RB, Brodsky BS, Stanley B. Borderline personality disorder, stigma, and treatment implications. Harv Rev Psychiatry. 2006;14:249–56. https://doi.org/10.1080/10673220600975121 .

Nijenhuis E, Van der Hart O, Kruger K. The psychometric characteristics of the Traumatic Experiences Checklist (TEC): First findings among psychiatric outpatients. Clin Psychol Psychother. 2002;9:200–10. https://doi.org/10.1002/cpp.332 .

Schmand B, Lindeboom J, Van Harskamp F. De nederlandse leestest voor volwassenen [the dutch adult reading test]. Lisse: Swets & Zeitlinger; 1992.

Schmand BA, Bakker D, Saan RJ, Louman J. De Nederlandse Leestest voor Volwassenen: een maat voor het premorbide intelligentieniveau [The Dutch Adult Reading Test: a measure of premorbid intelligence]. Tijdschr Gerontol Geriatr. 1991;22:15–9.

CAS   PubMed   Google Scholar  

Lenzenweger MF, Clarkin JF, Yeomans FE, Kernberg OF, Levy KN. Refining the borderline personality disorder phenotype through finite mixture modeling: Implications for classification. J Personal Disord. 2008;22:313–31. https://doi.org/10.1521/pedi.2008.22.4.313 .

Fraley RC, Heffernan ME, Vicary AM, Brumbaugh CC. The experiences in close relationships-relationship structures questionnaire: a method for assessing attachment orientations across relationships. Psychol Assess. 2011;23:615–25. https://doi.org/10.1037/a0022898 .

Fraley RC, Waller NG, Brennan KA. An item response theory analysis of self-report measures of adult attachment. J Pers Soc Psychol. 2000;78:350–65. https://doi.org/10.1037/0022-3514.78.2.350 .

Videler AC, van Alphen SPJ, van Royen RJJ, van der Feltz-Cornelis CM, Rossi G, Arntz A. Schema therapy for personality disorders in older adults: a multiple-baseline study. Aging Ment Health. 2018;22:738–47. https://doi.org/10.1080/13607863.2017.1318260 .

Vuijk R, Arntz A. Schema therapy as treatment for adults with autism spectrum disorder and comorbid personality disorder: protocol of a multiple-baseline case series study testing cognitive-behavioral and experiential interventions. Contemp Clin Trials Commun. 2017;5:80–5. https://doi.org/10.1016/j.conctc.2017.01.001 .

Kaufman EA, Xia M, Fosco G, Yaptangco M, Skidmore CR, Crowell SE. The difficulties in emotion regulation scale short form (DERS-SF): validation and replication in adolescent and adult samples. J Psychopathol Behav Assess. 2016;38:443–55. https://doi.org/10.1007/s10862-015-9529-3 .

Gratz KL, Roemer L. Multidimensional assessment of emotion regulation and dysregulation: development, factor structure, and initial validation of the difficulties in emotion regulation scale. J Psychopathol Behav Assess. 2004;26:41–54. https://doi.org/10.1023/B:JOBA.0000007455.08539.94 .

Hallion LS, Steinman SA, Tolin DF, Diefenbach GJ. Psychometric properties of the Difficulties in Emotion Regulation Scale (DERS) and its short forms in adults with emotional disorders. Front Psychol. 2018;9:539. https://doi.org/10.3389/fpsyg.2018.00539 .

Bardeen JR, Fergus TA, Orcutt HK. An examination of the latent structure of the Difficulties in Emotion Regulation Scale. J Psychopathol Behav Assess. 2012;34:382–92. https://doi.org/10.1007/s10862-012-9280-y .

Victor SE, Klonsky ED. Validation of a brief version of the difficulties in emotion regulation scale (DERS-18) in five samples. J Psychopathol Behav Assess. 2016;38:582–9. https://doi.org/10.1007/s10862-016-9547-9 .

Young JE, Arntz A, Atkinson T, Lobbestael J, Weishaar ME, Van Vreeswijk MF, et al. The schema mode inventory. New York: Schema Therapy Institute; 2007.

Lobbestael J, van Vreeswijk M, Spinhoven P, Schouten E, Arntz A. Reliability and validity of the short Schema Mode Inventory (SMI). Behav Cogn Psychother. 2010;38:437–58. https://doi.org/10.1017/S1352465810000226 .

Neacsiu AD, Rizvi SL, Vitaliano PP, Lynch TR, Linehan MM. The dialectical behavior therapy ways of coping checklist: development and psychometric properties. J Clin Psychol. 2010;66:563–82. https://doi.org/10.1002/jclp.20685 .

Vitaliano PP, Russo J, Carr JE, Maiuro RD, Becker J. The ways of coping checklist: revision and psychometric properties. Multivar Behav Res. 1985;20:3–26. https://doi.org/10.1207/s15327906mbr2001_1 .

Stinckens N, Ulburghs A, Claes L. De werkalliantie als sleutelelement in het therapiegebeuren. Meting met behulp van de WAV-12: de Nederlandse vertaling van de Working Alliance Inventory. Tijdschr Klin Psychol. 2009;39:44–60.

Tracey TJ, Kokotovic AM. Factor structure of the working alliance inventory. Psychol Assess. 1989;1:207. https://doi.org/10.1037/1040-3590.1.3.207 .

Smits D, Luyckx K, Smits D, Stinckens N, Claes L. Structural characteristics and external correlates of the Working Alliance Inventory-Short Form. Psychol Assess. 2015;27:545–51. https://doi.org/10.1037/pas0000066 .

Arntz A, van den Hoorn M, Cornelis J, Verheul R, van den Bosch W, de Bie A. Reliability and validity of the borderline personality disorder severity index. J Personal Disord. 2003;17:45–59. https://doi.org/10.1521/pedi.17.1.45.24053 .

Giesen-Bloo JH, Wachters LM, Schouten E, Arntz A. The borderline personality disorder severity index-IV: psychometric evaluation and dimensional structure. Personal Individ Differ. 2010;49:136–41. https://doi.org/10.1016/j.paid.2010.03.023 .

Dickhaut V, Arntz A. Combined group and individual schema therapy for borderline personality disorder: a pilot study. J Behav Ther Exp Psychiatry. 2014;45:242–51. https://doi.org/10.1016/j.jbtep.2013.11.004 .

Nadort M, Arntz A, Smit JH, Giesen-Bloo J, Eikelenboom M, Spinhoven P, et al. Implementation of outpatient schema therapy for borderline personality disorder: study design. BMC Psychiatry. 2009;9:64. https://doi.org/10.1186/1471-244X-9-64 .

Hakkaart-van Roijen L, Van der Linden N, Bouwmans C, Kanters T, Tan SS. Kostenhandleiding: Methodologie van kostenonderzoek en referentieprijzen voor economische evaluaties in de gezondheidszorg [Costing manual: methodology of costing research and reference prices for economic evaluations in healthcare]. Diemen: Zorginstituut Nederland; 2015.

Kanters TA, Bouwmans CAM, van der Linden N, Tan SS, Hakkaart-van RL. Update of the Dutch manual for costing studies in health care. PLoS One. 2017;12:e0187477. https://doi.org/10.1371/journal.pone.0187477 .

Hodgson TA, Meiners MR. Cost-of-illness methodology: a guide to current practices and procedures. Milbank Mem Fund Q Health Soc. 1982;60:429–62. https://doi.org/10.2307/3349801 .

Bloo J, Arntz A, Schouten E. The borderline personality disorder checklist: psychometric evaluation and factorial structure in clinical and nonclinical samples. Roczniki Psychologiczne. 2017;20:311–36. https://doi.org/10.18290/rpsych.2017.20.2-3en .

Derogatis LR, Melisaratos N. The brief symptom inventory: an introductory report. Psychol Med. 1983;13:595–605. https://doi.org/10.1017/S0033291700048017 .

De Beurs E, Zitman F. De Brief Symptom Inventory (BSI): De betrouwbaarheid en validiteit van een handzaam alternatief [Reliability and validity of a practical alternative to the SCL 90]. Maandblad Geestelijke Volksgezondheid. 2006;61:120–41.

De Beurs E. Brief Symptom Inventory (BSI) en BSI 18. Handleiding 2011 [Brief Symptom Inventory and BSI 18. Manual 2011]. Leiden: PITS; 2011.

Üstün TB, Kostanjsek N, Chatterji S, Rehm J. Measuring health and disability: manual for WHO disability assessment schedule WHODAS 2.0. Geneva: World Health Organization; 2010.

Herdman M, Gudex C, Lloyd A, Janssen MF, Kind P, Parkin D, et al. Development and preliminary testing of the new five-level version of EQ-5D (EQ-5D-5L). Qual Life Res. 2011;20:1727–36. https://doi.org/10.1007/s11136-011-9903-x .

Versteegh MM, Vermeulen KM, Evers SMAA, de Wit GA, Prenger R, Stolk EA. Dutch Tariff for the Five-Level Version of EQ-5D. Value Health. 2016;19:343–52. https://doi.org/10.1016/j.jval.2016.01.003 .

Janssen MF, Pickard AS, Golicki D, Gudex C, Niewada M, Scalone L, et al. Measurement properties of the EQ-5D-5L compared to the EQ-5D-3L across eight patient groups: a multi-country study. Qual Life Res. 2013;22:1717–27. https://doi.org/10.1007/s11136-012-0322-4 .

van Krugten FCW, Busschbach JJV, Versteegh MM, Hakkaart-van Roijen L, Brouwer WBF. The Mental Health Quality of Life Questionnaire (MHQoL): development and first psychometric evaluation of a new measure to assess quality of life in people with mental health problems. Qual Life Res. 2021. https://doi.org/10.1007/s11136-021-02935-w .

Bastien CH, Vallieres A, Morin CM. Validation of the Insomnia Severity Index as an outcome measure for insomnia research. Sleep Med. 2001;2:297–307. https://doi.org/10.1016/S1389-9457(00)00065-4 .

Lancee J, van Straten A, Morina N, Kaldo V, Kamphuis JH. Guided online or face-to-face cognitive behavioral treatment for insomnia: a randomized wait-list controlled trial. Sleep. 2016;39:183–91. https://doi.org/10.5665/sleep.5344 .

Thorndike FP, Ritterband LM, Saylor DK, Magee JC, Gonder-Frederick LA, Morin CM. Validation of the insomnia severity index as a web-based measure. Behav Sleep Med. 2011;9:216–23. https://doi.org/10.1080/15402002.2011.606766 .

Krakow B, Hollifield M, Schrader R, Koss M, Tandberg D, Lauriello J, et al. A controlled study of imagery rehearsal for chronic nightmares in sexual assault survivors with PTSD: a preliminary report. J Trauma Stress. 2000;13:589–609. https://doi.org/10.1023/A:1007854015481 .

Abdel-Khalek AM. Measuring happiness with a single-item scale. Soc Behav Personal Int J. 2006;34:139–50. https://doi.org/10.2224/sbp.2006.34.2.139 .

Miller SD, Duncan BL, Brown J, Sparks JA, Claud DA. The outcome rating scale: a preliminary study of the reliability, validity, and feasibility of a brief visual analog measure. J Brief Ther. 2003;2:91–100.

Hafkenscheid A, Duncan BL, Miller SD. The outcome and session rating scales. A cross-cultural examination of the psychometric properties of the Dutch translation. J Brief Ther. 2010;7:1–12.

Buckman JEJ, Cohen ZD, O’Driscoll C, Fried EI, Saunders R, Ambler G, et al. Predicting prognosis for adults with depression using individual symptom data: a comparison of modelling approaches; 2020. p. 1–11. https://doi.org/10.31219/osf.io/xkwdc .

Webb CA, Cohen ZD, Beard C, Forgeard M, Peckham AD, Bjorgvinsson T. Personalized prognostic prediction of treatment outcome for depressed patients in a naturalistic psychiatric hospital setting: a comparison of machine learning approaches. J Consult Clin Psychol. 2020;88:25–38. https://doi.org/10.1037/ccp0000451 .

Friedman J, Hastie T, Tibshirani R. Regularization paths for generalized linear models via coordinate descent. J Stat Softw. 2010;33:1–22. https://doi.org/10.18637/jss.v033.i01 .

Kapelner A, Bleich J. bartMachine: machine learning with Bayesian additive regression trees. J Stat Softw. 2016;70:1–40. https://doi.org/10.18637/jss.v070.i04 .

Zhang Q, Wang L, Bergeman CS. Multilevel autoregressive mediation models: specification, estimation, and applications. Psychol Methods. 2018;23:278–97. https://doi.org/10.1037/met0000161 .

Preacher KJ, Zyphur MJ, Zhang Z. A general multilevel SEM framework for assessing multilevel mediation. Psychol Methods. 2010;15:209–33. https://doi.org/10.1037/a0020141 .

Feaster DJ, Mikulich-Gilbertson S, Brincks AM. Modeling site effects in the design and analysis of multi-site trials. Am J Drug Alcohol Abuse. 2011;37:383–91. https://doi.org/10.3109/00952990.2011.600386 .

Hoch JS, Briggs AH, Willan AR. Something old, something new, something borrowed, something blue: a framework for the marriage of health econometrics and cost-effectiveness analysis. Health Econ. 2002;11:415–30. https://doi.org/10.1002/hec.678 .

Leichsenring F, Leibing E, Kruse J, New AS, Leweke F. Borderline personality disorder. Lancet. 2011;377:74–84. https://doi.org/10.1016/S0140-6736(10)61422-5 .

Hallquist MN, Pilkonis PA. Refining the phenotype of borderline personality disorder: diagnostic criteria and beyond. Personal Disord. 2012;3:228–46. https://doi.org/10.1037/a0027953 .

Kernberg OF, Caligor E. A psychoanalytic theory of personality disorders. In: Lenzenweger MF, Clarkin JF, editors. Major theories of personality disorder. New York: Guilford Press; 2005. p. 114–56.

Heath LM, Laporte L, Paris J, Hamdullahpur K, Gill KJ. Substance misuse is associated with increased psychiatric severity among treatment-seeking individuals with borderline personality disorder. J Personal Disord. 2018;32:694–708. https://doi.org/10.1521/pedi_2017_31_307 .

Links PS, Heslegrave RJ, Mitton JE, Vanreekum R, Patrick J. Borderline personality-disorder and substance-abuse - consequences of comorbidity. Can J Psychiatry. 1995;40:9–14. https://doi.org/10.1177/070674379504000105 .

Wilson SΤ, Fertuck EA, Kwitel A, Stanley MC, Stanley B. Impulsivity, suicidality and alcohol use disorders in adolescents and young adults with borderline personality disorder. Int J Adolesc Med Health. 2006;18:189–96. https://doi.org/10.1515/IJAMH.2006.18.1.189 .

Trull TJ, Freeman LK, Vebares TJ, Choate AM, Helle AC, Wycoff AM. Borderline personality disorder and substance use disorders: an updated review. Borderline Personal Disord Emot Dysregul. 2018;5:1–12. https://doi.org/10.1186/s40479-018-0093-9 .

Huibers M. Voorbij het oordeel van de dodo. Tijdschr Psychother. 2015;41:174–86. https://doi.org/10.1007/s12485-015-0027-6 .

Drummond MF, Sculpher MJ, Claxton K, Stoddart GL, Torrance GW. Methods for the economic evaluation of health care programmes. New York: Oxford University Press; 2015.

Hamann J, Leucht S, Kissling W. Shared decision making in psychiatry. Acta Psychiatr Scand. 2003;107:403–9. https://doi.org/10.1034/j.1600-0447.2003.00130.x .

Rosenzweig S. Some implicit common factors in diverse methods of psychotherapy. Am J Orthop. 1936;6:412–5. https://doi.org/10.1111/j.1939-0025.1936.tb05248.x .

Wampold BE, Mondin GW, Moody M, Stich F, Benson K, Ahn HN. A meta-analysis of outcome studies comparing bona fide psychotherapies: empirically, “all must have prizes”. Psychol Bull. 1997;122:203–15. https://doi.org/10.1037/0033-2909.122.3.203 .

Budge SL, Moore JT, Del Re AC, Wampold BE, Baardseth TP, Nienhuis JB. The effectiveness of evidence-based treatments for personality disorders when comparing treatment-as-usual and bona fide treatments. Clin Psychol Rev. 2013;33:1057–66. https://doi.org/10.1016/j.cpr.2013.08.003 .

Fassbinder E, Assmann N, Schaich A, Heinecke K, Wagner T, Sipos V, et al. PRO* BPD: effectiveness of outpatient treatment programs for borderline personality disorder: a comparison of Schema therapy and dialectical behavior therapy: study protocol for a randomized trial. BMC Psychiatry. 2018;18:341. https://doi.org/10.1186/s12888-018-1905-6 .

Leykin Y, DeRubeis RJ. Allegiance in psychotherapy outcome research: separating association from bias. Clin Psychol. 2009;16:54–65. https://doi.org/10.1111/j.1468-2850.2009.01143.x .

Lemmens LHJM, Mueller VNLS, Arntz A, Huibers MJH. Mechanisms of change in psychotherapy for depression: an empirical update and evaluation of research aimed at identifying psychological mediators. Clin Psychol Rev. 2016;50:95–107. https://doi.org/10.1016/j.cpr.2016.09.004 .

Lemmens LHJM, Galindo-Garre F, Arntz A, Peeters F, Hollon SD, DeRubeis RJ, et al. Exploring mechanisms of change in cognitive therapy and interpersonal psychotherapy for adult depression. Behav Res Ther. 2017;94:81–92. https://doi.org/10.1016/j.brat.2017.05.005 .

Cohen J. Statistical power analysis for the behavioral sciences. 2nd ed. Hillsdale: Erlbaum; 1988.

Cohen J. Statistical power analysis. Curr Dir Psychol Sci. 1992;1:98–101. https://doi.org/10.1111/1467-8721.ep10768783 .

Di Stephano J. How much power is enough? Against the development of an arbitrary convention for statistical power calculations. Funct Ecol. 2003;17:707–9. https://doi.org/10.1046/j.1365-2435.2003.00782.x .

Luedtke A, Sadikova E, Kessler RC. Sample size requirements for multivariate models to predict between-patient differences in best treatments of major depressive disorder. Clin Psychol Sci. 2019;7:445–61. https://doi.org/10.1177/2167702618815466 .

van den Bosch LMC, Verheul R, Schippers GM, van den Brink W. Dialectical behavior therapy of borderline patients with and without substance use problems - Implementation and long-term effects. Addict Behav. 2002;27:911–23. https://doi.org/10.1016/S0306-4603(02)00293-9 .

Feigenbaum JD, Fonagy P, Pilling S, Jones A, Wildgoose A, Bebbington PE. A real-world study of the effectiveness of DBT in the UK National Health Service. Br J Clin Psychol. 2012;51:121–41. https://doi.org/10.1111/j.2044-8260.2011.02017.x .

Koons CR. The role of the team in managing telephone consultation in dialectical behavior therapy: three case examples. Cogn Behav Pract. 2011;18:168–77. https://doi.org/10.1016/j.cbpra.2009.10.008 .

Comtois KA, Elwood L, Holdcraft LC, Smith WR, Simpson TL. Effectiveness of dialectical behavior therapy in a community mental health center. Cogn Behav Pract. 2007;14:406–14. https://doi.org/10.1016/j.cbpra.2006.04.023 .

van den Bosch LMC, Sinnaeve R. Dialectische gedragstherapie in Nederland: implementatie en consolidatie. Tijdschrift voor Psychiatrie. 2015;57:719–27.

PubMed   Google Scholar  

Miller SJ, Binder JL. The effects of manual-based training on treatment fidelity and outcome: a review of the literature on adult individual psychotherapy. Psychotherapy. 2002;39:184–98. https://doi.org/10.1037/0033-3204.39.2.184 .

Harned MS, Korslund KE, Schmidt SC, Gallop RJ. The Dialectical Behavior Therapy Adherence Coding Scale (DBT ACS): psychometric properties. Psychol Assess. 2021;33:552–61. https://doi.org/10.1037/pas0000999 .

Lynch TR, Trost WT, Salsman N, Linehan MM. Dialectical behavior therapy for borderline personality disorder. Annu Rev Clin Psychol. 2007;3:181–205. https://doi.org/10.1146/annurev.clinpsy.2.022305.095229 .

Brazier J. Is the EQ–5D fit for purpose in mental health? Br J Psychiatry. 2010;197:348–9. https://doi.org/10.1192/bjp.bp.110.082453 .

Van Asselt A, Dirksen CD, Arntz A, Giesen-Bloo JH, Severens JL. The EQ-5D: A useful quality of life measure in borderline personality disorder? Eur Psychiatry. 2009;24:79–85. https://doi.org/10.1016/j.eurpsy.2008.11.001 .

Soeteman DI, Verheul R, Delimon J, Meerman AMMA, van den Eijnden E, Rossum BV, et al. Cost-effectiveness of psychotherapy for cluster B personality disorders. Br J Psychiatry. 2010;196:396–403. https://doi.org/10.1192/bjp.bp.109.070482 .

Zwaap J, Knies S, Van der Meijden C, Staal P, Van der Heiden L. Kosteneffectiviteit in de praktijk. Diemen: Zorginstituut Nederland; 2015.

Inchausti F, MacBeth A, Hasson-Ohayon I, Dimaggio G. Psychological intervention and COVID-19: what we know so far and what we can do. J Contemp Psychother. 2020;50:243–50. https://doi.org/10.1007/s10879-020-09460-w .

Ventura Wurman T, Lee T, Bateman A, Fonagy P, Nolte T. Clinical management of common presentations of patients diagnosed with BPD during the COVID-19 pandemic: the contribution of the MBT framework. Couns Psychol Q. 2020:1–27. https://doi.org/10.1080/09515070.2020.1814694 .

Alvaro F, Navarro S, Palma C, Farriols N, Aliaga F, Solves L, et al. Clinical course and predictors in patients with borderline personality disorder during the COVID-19 outbreak: a 2.5-month naturalistic exploratory study in Spain. Psychiatry Res. 2020;292:113306. https://doi.org/10.1016/j.psychres.2020.113306 .

Liu L, Thorp SR, Moreno L, Wells SY, Glassman LH, Busch AC, et al. Videoconferencing psychotherapy for veterans with PTSD: results from a randomized controlled non-inferiority trial. J Telemed Telecare. 2020;26:507–19. https://doi.org/10.1177/1357633X19853947 .

Berryhill MB, Halli-Tierney A, Culmer N, Williams N, Betancourt A, King M, et al. Videoconferencing psychological therapy and anxiety: a systematic review. Fam Pract. 2019;36:53–63. https://doi.org/10.1093/fampra/cmy072 .

Berryhill MB, Culmer N, Williams N, Halli-Tierney A, Betancourt A, Roberts H, et al. Videoconferencing psychotherapy and depression: a systematic review. Telemed J E Health. 2019;25:435–46. https://doi.org/10.1089/tmj.2018.0058 .

Weinberg H. Online group psychotherapy: challenges and possibilities during COVID-19-a practice review. Group Dyn Theory Res Pract. 2020;24:201–11. https://doi.org/10.1037/gdn0000140 .

Download references

Acknowledgements

We would like to thank all patients, therapists, supervisors, research assistants, and students for their involvement in the study. We also thank our advisory board for sharing their knowledge and support, and their critical review of the study design. Finally, we are thankful to Herman Vinckers and Lindy Boyette who helped with the translation of the questionnaires.

This study received funding from Stichting Achmea Gezondheidszorg, CZ Fonds, and Stichting Volksbond Rotterdam. The funding bodies had no role in the design of the study and will not be involved in the collection, analysis, and interpretation of the data, nor in writing the manuscripts. The grant was subjected to a peer review process.

Author information

Authors and affiliations.

Department of Clinical Psychology, University of Amsterdam, Nieuwe Achtergracht 129-B, Amsterdam, 1018 WS, the Netherlands

Carlijn J. M. Wibbelink, Arnoud Arntz, Raoul P. P. P. Grasman & Jan H. Kamphuis

Department of Neurosciences, Mind Body Research, KU Leuven, Herestraat 49, 3000, Leuven, Belgium

Roland Sinnaeve

Department of Addiction and Personality, Antes Mental Health Care, Max Euwelaan 1, Rotterdam, 3062 MA, the Netherlands

Michiel Boog

Institute of Psychology, Erasmus University Rotterdam, P.O. Box 1738, Rotterdam, 3000 DR, the Netherlands

Arkin Mental Health, NPI Institute for Personality Disorders, Domselaerstraat 128, Amsterdam, 1093 MB, the Netherlands

Odile M. C. Bremer

PsyQ Personality Disorders Rotterdam-Kralingen, Max Euwelaan 70, Rotterdam, 3062 MA, the Netherlands

Eliane C. P. Dek

i-psy Amsterdam, Overschiestraat 61, Amsterdam, 1062 XD, the Netherlands

Sevinç Göral Alkan

Department of Personality Disorders, Outpatient Clinic De Nieuwe Valerius, GGZ inGeest, Amstelveenseweg 589, Amsterdam, 1082 JC, the Netherlands

Chrissy James

PsyQ Amsterdam, Overschiestraat 57, Amsterdam, 1062 XD, the Netherlands

Annemieke M. Koppeschaar

GGZ Noord-Holland-Noord, Stationsplein 138, 1703 WC, Heerhugowaard, the Netherlands

Linda Kramer

Pro Persona, Siependaallaan 3, Tiel, 4003 LE, the Netherlands

Maria Ploegmakers

Pro Persona, Willy Brandtlaan 20, Ede, 6716 RR, the Netherlands

Arita Schaling

GGZ Rivierduinen, Sandifortdreef 19, Leiden, 2333 ZZ, the Netherlands

Faye I. Smits

You can also search for this author in PubMed   Google Scholar

Contributions

CJMW: wrote the manuscript; involved in the implementation and coordination of the data collection; involved in the design of the study. AA: principal investigator; initial conception and design of the study. JHK: principal investigator; initial conception and design of the study. RPPPG: statistical counseling. RS: involved in the design of the study. MB, OMCB, ECPD, SGA, CJ, AMK, LK, MP, AS, FIS: responsible for the recruitment of participants and data collection in their mental healthcare center. All authors read, contributed and approved the final manuscript.

Corresponding author

Correspondence to Carlijn J. M. Wibbelink .

Ethics declarations

Ethics approval and consent to participate.

The study was approved by the Medical Ethics Committee of the Academic Medical Center Amsterdam (reference number: 2018_191). We obtain signed informed consents from all participants in the study.

Consent for publication

Competing interests.

There are no financial competing interests and the authors declare that they have no competing interests.

Additional information

Publisher’s note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Additional file 1..

SPIRIT 2013 checklist.

Additional file 2.

Informed consent form (Appendix A) and additional informed consent form videoconferencing (Appendix B).

Additional file 3.

Overview of syndrome disorders assessed with the SCID-5-S.

Additional file 4.

Candidate predictors based on clinicians’ appraisals (Table 1) and candidate predictors based on the literature and suggestions of a patient representative of the Borderline Foundation of the Netherlands (Table 2).

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ . The Creative Commons Public Domain Dedication waiver ( http://creativecommons.org/publicdomain/zero/1.0/ ) applies to the data made available in this article, unless otherwise stated in a credit line to the data.

Reprints and permissions

About this article

Cite this article.

Wibbelink, C.J.M., Arntz, A., Grasman, R.P.P.P. et al. Towards optimal treatment selection for borderline personality disorder patients (BOOTS): a study protocol for a multicenter randomized clinical trial comparing schema therapy and dialectical behavior therapy. BMC Psychiatry 22 , 89 (2022). https://doi.org/10.1186/s12888-021-03670-9

Download citation

Received : 06 July 2021

Accepted : 21 December 2021

Published : 05 February 2022

DOI : https://doi.org/10.1186/s12888-021-03670-9

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Borderline personality disorder
• Schema therapy
• Dialectical behavior therapy
• Randomized clinical trial
• Personalized medicine
• Effectiveness

BMC Psychiatry

ISSN: 1471-244X

• Submission enquiries: [email protected]
• General enquiries: [email protected]

Borderline Personality Disorder and Emotion Dysregulation

Call for papers: parents with personality pathology.

This collection is concerned with the experience of parents with personality pathology, broadly defined, and their children. We encourage the inclusion of samples of male caregivers, and studies utilizing longitudinal, qualitative, and mixed methodology. Specifically, we welcome submission of articles focusing on the following topics: the parenting behaviors and experiences of individuals with personality pathology, mechanisms of intergenerational risk and resilience, and the development, implementation, or evaluation of parenting interventions and supports for this population.

Edited by Kiana Cano  ([email protected]) and  Carla Sharp ([email protected])

New special issue: Pharmacotherapy of Emotion Dysregulation

Emotion dysregulation is considered a transdiagnostic symptom and an underlying mechanism of psychopathology. It is present in patients with borderline personality disorder, complex PTSD, and ADHD, among others. While there are evidence-based behavioral interventions to improve emotion dysregulation, pharmacological strategies are less well studied. This Collection focuses on pharmacologic strategies for modulating emotion regulation. Clinical intervention studies are welcome, as are laboratory studies. We encourage submission of feasibility studies and confirmatory data on pharmacologic interventions that focus on emotion dysregulation, whether transdiagnostic or in specific clinical groups. In addition, research on basal mechanisms of emotion regulation that could serve as the basis for future pharmacological intervention strategies is welcome.

Edited by Stefan Röpke ([email protected])

Aims and scope

Borderline Personality Disorder and Emotion Dysregulation provides a platform for researchers and clinicians interested in borderline personality disorder (BPD) as a currently highly challenging psychiatric disorder. Emotion dysregulation is at the core of BPD but also stands on its own as a major pathological component of the underlying neurobiology of various other psychiatric disorders. The journal focuses on the psychological, social and neurobiological aspects of emotion dysregulation as well as epidemiology, phenomenology, pathophysiology, treatment, neurobiology, genetics, and animal models of BPD. Contributions investigating the broad field of emotion regulation and dysregulation as well as related pathological mechanisms such as dysfunctional self-concepts and dysfunctional social interaction are welcomed, as are studies of novel treatments for BPD. In addition, the journal considers research into the frequent, co-occurring psychiatric disorders like Post-traumatic Stress Disorder, ADHD, depression, eating disorders, conduct disorders, drug abuse, and social phobia.

• Most accessed

Clinical profiles of adolescent personality pathology: a latent structure examination of the Semi-Structured Interview for Personality Functioning DSM-5 (STiP-5.1) in a help-seeking sample

Authors: Madelyn Thomson, Marialuisa Cavelti, Stefan Lerch, Julian Koenig, Corinna Reichl, Ines Mürner-Lavanchy, Andrea Wyssen and Michael Kaess

Borderline personality disorder and sexuality: causes and consequences of dissociative symptoms

Authors: Rose Gholami Mazinan, Christina Dudek, Hannah Warkentin, Maja Finkenstaedt, Johanna Schröder, Richard Musil, Leonhard Kratzer, Johannes Fuss and Sarah V. Biedermann

Dissociation in mothers with borderline personality disorder: a possible mechanism for transmission of intergenerational trauma? A scoping review

Authors: David Rimmington, Rachel Roberts, Alyssa Sawyer and Anne Sved-Williams

Experiential avoidance in participants with borderline personality disorder and other personality disorders

Authors: Tess C. Gecha, Isabel V. Glass, Frances R. Frankenburg, Carla Sharp and Mary C. Zanarini

Psychotropic medication use among adolescents participating in three randomized trials of DBT

Authors: Lars Mehlum, Joan Asarnow, Sudan Prasad Neupane, Pilar Santamarina-Perez, Mireia Primé-Tous and Gabrielle A. Carlson

Most recent articles RSS

View all articles

Euthanasia and assisted suicide in patients with personality disorders: a review of current practice and challenges

Authors: Lars Mehlum, Christian Schmahl, Ann Berens, Stephan Doering, Joost Hutsebaut, Andres Kaera, Ueli Kramer, Paul Anthony Moran, Babette Renneberg, Joaquim Soler Ribaudi, Sebastian Simonsen, Michaela Swales, Svenja Taubner and Ester di Giacomo

Complex PTSD and borderline personality disorder

Authors: Julian D. Ford and Christine A. Courtois

Understanding chronic feelings of emptiness in borderline personality disorder: a qualitative study

Authors: Caitlin E. Miller, Michelle L. Townsend and Brin F. S. Grenyer

Borderline personality disorder (BPD) and attention deficit hyperactivity disorder (ADHD) revisited – a review-update on common grounds and subtle distinctions

Authors: Ismene Ditrich, Alexandra Philipsen and Swantje Matthies

Complex PTSD, affect dysregulation, and borderline personality disorder

Authors: Julian D Ford and Christine A Courtois

Most accessed articles RSS

Featured first author profiles

Find out more about our first authors!

Announcing the launch of In Review

Borderline Personality Disorder and Emotion Dysregulation , in partnership with Research Square, is now offering In Review . Authors choosing this free optional service will be able to:

• Share their work with fellow researchers to read, comment on, and cite even before publication
• Showcase their work to funders and others with a citable DOI while it is still under review
• Track their manuscript - including seeing when reviewers are invited, and when reports are received 

See the full range of benefits of In Review and how to opt-in

See what the In Review platform looks like

Sections in BPDED

Borderline Personality Disorder and Emotion Dysregulation is proud to present the following sections, edited by experts in each field. These sections don't represent the full scope of the journal, but provide additional focus on areas outside our primary focuses of emotion dysregulation and BPD. 

• ADHD - Alexandra Philipsen, MD
• Developmental aspects of personality disorders - Carla Sharp, PhD
• Eating Disorders - Ulrich Voderholzer, MD
• Trauma and PTSD - Annegret Krause-Utz, PhD

Society affiliations

Borderline Personality Disorder and Emotion Dysregulation is the official journal of the Dachverband Dialektisch Behaviorale Therapie (DDBT) and the National Education Alliance for Borderline Personality Disorder (NEA.BPD). For further information on the DDBT, visit their website here  

John M. Oldham , MD  is currently Distinguished Emeritus Professor in the Department of Psychiatry and Behavioral Sciences at Baylor College of Medicine in Houston, Texas, USA.  He previously held the Barbara and Corbin J Robertson, Jr Endowed Chair for Personality Disorders and served as Senior Vice President and Chief of Staff of the Menninger Clinic. Earlier in his career, Dr. Oldham was Director of the New York State Psychiatric Institute, Chief Medical Officer of the New York State Office of Mental Health, and the Elizabeth K. Dollard Professor and Acting Chairman of the Department of Psychiatry, Columbia University College of Physicians and Surgeons. In 2002, Dr. Oldham became Professor and Chairman of the Department of Psychiatry and Behavioral Sciences and Executive Director of the Institute of Psychiatry at the Medical University of South Carolina, and he relocated to Houston in 2007. Dr. Oldham is the Past President of the American Psychiatric Association, Past President of the American College of Psychiatrists, Past President of the New York County District Branch of the American Psychiatric Association, Past President of the South Carolina Psychiatric Association, Past President of the International Society for the Study of Personality Disorders, and Past President of the Association for Research on Personality Disorders.

Photo: ZI © Daniel Lukac

Christian Schmahl, MD, PhD  is Medical Director of the Department of Psychosomatic Medicine and Psychotherapy at the Central Institute of Mental Health, Mannheim and spokesperson of the Research Training Group “Impact of Adverse

Childhood Experiences on Psychosocial and Somatic Conditions across the Lifespan”. Dr Schmahl received his M.D. at Giessen Medical School and did a residency in Psychiatry at Freiburg Medical School as well as a residency in Psychosomatic Medicine at the Central Institute of Mental Health. He also spent a one-year research

fellowship at Yale and Emory University. In 2007 he received the Young Researchers Award of the International Society for the Study of Personality Disorders”, in 2013 the Psychotherapy Research Award of the German Association of

Psychiatry, Psychotherapy and Psychosomatics, and in 2018 the Treatment and Research Advancements for Borderline Personality Disorder Star Award. He has published more than 250 articles and book chapters.

• Editorial Board
• Manuscript editing services
• Instructions for Editors
• Sign up for article alerts and news from this journal

Annual Journal Metrics

2022 Citation Impact 4.1 - 2-year Impact Factor 4.3 - 5-year Impact Factor 1.643 - SNIP (Source Normalized Impact per Paper) 1.394 - SJR (SCImago Journal Rank)

2023 Speed 27 days submission to first editorial decision for all manuscripts (Median) 124 days submission to accept (Median)

2023 Usage 914,152 downloads 295 Altmetric mentions

• More about our metrics

ISSN: 2051-6673

• General enquiries: [email protected]

Borderline Personality Disorder

The latest theory on borderline personality disorder, new research uses logic to understand people with borderline disorder..

Posted April 27, 2024 | Reviewed by Lybi Ma

• What Is Borderline Personality Disorder?
• Find a therapist to treat BPD
• Theories of borderline personality disorder focus on early emotional experiences as the cause of splitting.
• A new approach uses statistical modeling to see what factors influence the tendency toward splitting.
• People with this disorder can use their experiences to help overcome splitting and achieve integration.

When you think of someone with borderline personality disorder , it’s likely that you imagine their tendency to let their emotions veer out of control, become overly intrusive, and alternate between loving and hating the same individual, or what’s known as “splitting.”

Perhaps you have an in-law who you know has this diagnosis, and as much as you would like to show understanding and empathy, it’s difficult when they decide to make you the target of the hate side of the splitting equation. If only you could figure out what’s behind these stormy changes of heart, perhaps you could get along better, if not become a trusted source of help. New research uses a logical analysis to provide some clues.

The Logic of Splitting in Borderline Personality Disorder

According to the University of College London’s Giles Story and colleagues (2024), traditional theories of this disorder regard splitting as an offshoot of unhealthy early emotional development, in which “an infant structures its experience by discriminating between positive and negative affect… [leading to] disconnected states of extreme satisfaction and frustration.” (p. 750) In ordinary development, individuals learn to bring these two states into balance as the bonds with their caregivers become stable and enduring, regardless of whether their needs are satisfied or frustrated. In BPD, though, this integration fails to occur, and individuals come to acquire split representations not just of other people, but of themselves.

Tracing the development of these “object relations” approaches to BPD, Story and colleagues maintain that these approaches miss the mark by considering only emotional aspects of splitting and not potential cognitive ones. Instead, the UCL authors propose a framework of probabilistic inference. Perhaps people with BPD form the wrong conclusions when they try to establish the causes of other people’s behaviors.

Everyone engages in this type of speculation, whether BPD or not. Even a simple act such as someone smiling at you could have you wonder what’s behind their apparent good intentions. Did you do something they liked, which would be a “situational” cause, or are they just people who tend to smile (“dispositional” cause)? You might then go on to observe their future behavior which would allow you to settle the question.

There are many possible variants of the situational versus dispositional attributional process. If you like someone, you’ll be more inclined to view good behavior as dispositional. If someone generally behaves a certain way and then suddenly shows the opposite behavior, it must be situational. For the most part, these reasoning processes are rational, allowing individuals to test “hypotheses” about why others behave as they do. In BPD, all-or-nothing reasoning sets in, in which people tend to view the causes of other people’s behavior in overly simplistic, all-or-nothing ways.

A Statistical Modeling Approach to Splitting

In ordinary experience, Story and colleagues propose, people go through statistical thinking known as “Bayesian,” in which they change the probabilities of a person’s behavior reflecting dispositional factors based on behaviors as they unfold over time. The first time you see a stranger smile, you have no idea whether they are nice, or not. However, as you see them continuing to smile regardless of what’s happening around them, the odds increasingly shift in favor of a dispositional attribution. If people with BPD can’t make that calculation, they’ll judge someone’s personality based on a snap judgment that won’t change over time. Splitting, in this view, becomes “a distorted causal inference.” They don’t, as the authors propose, update a “person prior” (p. 757). Once nice, always nice, and vice versa. The “split priors,” in which people are all bad or all good become “impervious to learning." (p. 762)

The UCL authors ran statistical models on data from a prior study of participants with BPD and non-BPD controls given the simulated task of judging the moral character of “Person A” toward “Person B.” Ordinarily if you were making such a judgment with no “prior person,” you would have to wait to see what Person A actually did in a given situation and then update your judgments. By running a model against the actual data from participants as they judged whether Person A was a good or a bad “agent,” Story and colleagues could determine whether the groups differed in their ability to draw Bayesian inferences.

Not only did the findings confirm the predictions of differences in attributional processes between BPD and non-BPD groups, but the authors were also able to run a model to show how the tendency to engage in splitting could potentially be modified. Part of the problem in making attributions in general is that sometimes the external context in which people act isn’t all that clear-cut. The lack of clarity only feeds into the tendency of people with BPD to draw conclusions based on their initial impressions of others. However, by creating a model in which precise information is available about Person A’s behavior, attributions based on splitting diminish and a more integrated, and realistic, set of judgments can emerge.

Turning Statistical Modeling into Intervention

The job of intervention is to help “split priors” to be updated by data from experience, using the processes described through the Bayesian modeling. Consider the example provided by the authors. A person with BPD might jump to the conclusion that if someone they’re supposed to meet is late, this proves that “they hate me.” Intervention can help the individual take extra external information into account (such as heavy traffic). Training the individual to be more sensitive to situational factors would reduce the tendency to make judgments based not on what people do, but on how they imagine people to be (all good or all bad).

In general, it is a good idea to let the evidence influence your judgments of people, but for individuals who tend to block out the data from experience, this type of intervention could help the person with BPD become more attuned to what the people around them are actually doing. Additionally, based on the Bayesian model, in which your judgments about probability should shift depending on prior outcomes, training people to monitor their conclusions about people over time would help individuals integrate positive and negative judgments rather than shift toward one or the other.

To sum up, whatever early experiences shape the individual with BPD are less important, in this approach, than the logic of the decisions the individual makes in the here and now. Giving people with this disorder the power and knowledge to observe themselves over time can help build the fulfillment that comes from an integrated view of the people in their lives.

Story, G. W., Smith, R., Moutoussis, M., Berwian, I. M., Nolte, T., Bilek, E., Siegel, J. Z., & Dolan, R. J. (2024). A social inference model of idealization and devaluation. Psychological Review , 131 (3), 749-780. https://doi.org/10.1037/rev0000430

Susan Krauss Whitbourne, Ph.D. , is a Professor Emerita of Psychological and Brain Sciences at the University of Massachusetts Amherst. Her latest book is The Search for Fulfillment.

• Find a Therapist
• Find a Treatment Center
• Find a Psychiatrist
• Find a Support Group
• Find Online Therapy
• United States
• Brooklyn, NY
• Chicago, IL
• Houston, TX
• Los Angeles, CA
• New York, NY
• Portland, OR
• San Diego, CA
• San Francisco, CA
• Seattle, WA
• Washington, DC
• Asperger's
• Bipolar Disorder
• Chronic Pain
• Eating Disorders
• Passive Aggression
• Personality
• Goal Setting
• Positive Psychology
• Stopping Smoking
• Low Sexual Desire
• Relationships
• Child Development
• Therapy Center NEW
• Diagnosis Dictionary
• Types of Therapy

Understanding what emotional intelligence looks like and the steps needed to improve it could light a path to a more emotionally adept world.

• Emotional Intelligence
• Gaslighting
• Affective Forecasting
• Neuroscience

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

• View all journals
• My Account Login
• Explore content
• About the journal
• Publish with us
• Sign up for alerts
• Open access
• Published: 27 April 2024

Socioeconomic status, personality, and major mental disorders: a bidirectional Mendelian randomization study

• Qiang Xu   ORCID: orcid.org/0000-0003-4744-5616 1   na1 ,
• Haonan Li 1   na1 &
• Dan Zhu   ORCID: orcid.org/0000-0003-1186-9505 2  

Schizophrenia volume  10 , Article number:  49 ( 2024 ) Cite this article

399 Accesses

1 Altmetric

Metrics details

• Human behaviour
• Psychiatric disorders

Previous research has suggested a correlation between socioeconomic status (SES) and mental diseases, while personality traits may be associated with SES and the risk of mental disorders. However, the causal nature of these associations remains largely uncertain. Our Mendelian randomization (MR) study aims to explore the bidirectional causality between SES and mental disorders, as well as to evaluate the potential mediating role of personality in these associations. Using bidirectional MR approach, we assessed the causality between SES indicators and mental disorders. We then used a two-step MR method to further investigate whether and to what extent personality mediates the causal associations in Caucasians. The forward MR analyses identified that years of education, household income, age at first birth and the Townsend deprivation index had a causal association with at least one mental disorder. The reverse MR analyses identified causal effects of genetically predicted schizophrenia, bipolar disorder, and attention deficit/hyperactivity disorder on five SES indicators. Importantly, mediation analysis showed that neuroticism partly mediated the causality of household income and years of education on major depressive disorder, respectively. In brief, our study confirmed the bidirectional relationship between SES and mental disorders. We also revealed the role of neuroticism in mediating the association between SES and major depressive disorder, highlighting the importance of considering both socioeconomic and personality factors in mental health research and interventions.

Similar content being viewed by others

The serotonin theory of depression: a systematic umbrella review of the evidence

Major depressive disorder: hypothesis, mechanism, prevention and treatment

Genome-wide association analyses identify 95 risk loci and provide insights into the neurobiology of post-traumatic stress disorder

Introduction.

Socioeconomic status (SES) is an indicator of the social status or class of a group or individual, usually measured in terms of education, income, and occupation 1 . It is widely recognized that mutually reinforcing effects exist between changes in SES and the risk of mental disorders 2 , 3 , 4 , 5 . Personality constitutes the amalgamation of psychological traits, which is relatively stable, fundamental, and unique to an individual, potentially plays critical roles in the relationship between SES and mental disorders. Previous studies have found some evidence of associations between different SES phenotypes and personality traits (the big five personality) 6 , 7 , 8 . Moreover, the associations between personality and mental disorders has attracted research attention 9 , and are also well established 10 , 11 . However, the reliability of these studies may be affected by confounding factors and reverse causality. As a result, the causal effects and reciprocal relationship between SES and the risk of mental disorders remain largely uncertain.

Mendelian randomization (MR) is a very promising approach that attempts to measure potentially causal effects of exposures on outcomes. Single nucleotide polymorphisms (SNPs) are randomly distributed at conception and are used as instrumental variables (IVs) in MR analyses. This reduces bias in causal inference, largely independent of the effects of confounders due to other genetic variants 12 . These advantages can also be applied to mediation analysis, which demands that there be no unmeasured confounding between any of the exposure, mediator, and outcome, which is more difficult to realize in traditional observational methods 13 . MR is an effective method to investigate potential causal relationships and has been widely used in many research fields 14 , 15 .

Research on the dimensional effects of SES, personality, and mental health has been limited thus far, with few studies specifically designed to explore mediation effects. In this study, our objective was to elucidate the bidirectional causality between SES and mental disorders using publicly available large-scale genome-wide association study (GWAS) data. Furthermore, we aimed to investigate the extent to which personality traits could explain the causal relationship between SES and mental disorders. Therefore, we first investigated the causal link between SES and mental disorders using a bidirectional two-sample MR method. In addition, we used a two-step MR approach to explore the mediating effect of personality in the SES-mental disorders or mental disorders-SES association. The study frame chart of MR analysis is presented in Fig. 1 .

a The GWAS summary-level data of MR study. b The bidirectional MR analysis between socioeconomic status and mental disorders. c The schematic diagram of a two-step MR and mediator analysis. d The sensitivity analysis methods of MR study. SES socioeconomic status, YED years of education, HIBT household income before tax, TDI Townsend deprivation index, CES current employment status, AFB age at first birth, NEB number of children ever born, P personality, A agreeableness, C conscientiousness, E extraversion, O openness, N neuroticism, M-D mental disorders, SCZ schizophrenia, BD bipolar disorder, MDD major depressive disorder, ASD autism spectrum disorder, ADHD attentiondeficit/hyperactivity disorder, MR-PRESSO Mendelian randomization-pleiotropy residual sum and outlier.

GWAS summary dataset for SES

GWAS provides a unique and reliable resource of summary-level data in a large sample. The following six phenotypes were selected for the genetic data of SES: Townsend deprivation index (TDI), household income before tax (HIBT), current employment status (CES), years of education (YED), age at first birth (AFB) and number of children ever born (NEB).

The genetic instrument data for the TDI, HIBT, CES and AFB were obtained from the publicly available GWAS summary data of the UK Biobank (UKB) (IEU OpenGWAS project (mrcieu.ac.uk), and the NEB were acquired from the Within Family GWAS Consortium ( https://www.withinfamilyconsortium.com/ ). Specifically, TDI ( n  = 462,464) is a composite score based on the differences in the percentage of four variables: unemployment, overcrowded households, households without cars, and non-home ownership 16 . A higher TDI represents a higher poverty index and a lower SES 16 . HIBT ( n  = 397,751) was calculated according to the average family income before tax during the period of 2006–2010. CES ( n  = 461,242), the main types of employment can be divided into employed and non-employed. For AFB ( n  = 542,901) and NEB ( n  = 60,430), those can reflect reproductive behaviors 17 . GWAS for YED were from the Social Science Genetic Association ( https://www.thessgac.org/ ) ( n  = 766,345), a long-term longitudinal study of people aged 30 years or older 18 .

GWAS summary dataset for personalities

Scientific consensus has referred to the five personality traits of openness, conscientiousness, extraversion, agreeability, and neuroticism as the five-factor model 19 , also known as the Big Five personalities. The genetic instrument data for the first four personalities mentioned above were obtained from a meta-analysis of 17,375 of Caucasians, including regions in Europe, the United States, and Australia, examining the genetic variants associated with personalities 20 . The GWAS for neuroticism was obtained from a study involving twenty-one European, six American and two Australian cohorts. The total sample size was 63,661 21 . To avoid overlap between the exposure and outcome samples, all personalities GWAS summary dataset we selected is the largest GWAS dataset available except for UKB.

GWAS summary dataset on mental disorders

Five GWAS datasets on mental disorders were all obtained from the Psychiatric Genomics Consortium (PGC). The PGC is currently the largest consortium in psychiatry, which has conducted the most influential analysis of genome-wide genomic data for mental disorders. To ensure the sample independence of exposure and outcome in the MR Analysis, we selected data from PGC-related genetic data excluding the two large cohorts of UKB and 23andMe to avoid excessive sample overlap. The final datasets therefore comprised 143,265 individuals for major depressive disorder (MDD), 77,096 individuals for schizophrenia (SCZ) 22 , 51,710 individuals for bipolar disorder (BD) 23 , 46,351 individuals for autism spectrum disorder (ASD) 24 , and 55,374 individuals for attention deficit/hyperactivity disorder (ADHD) 24 .

We restricted our analyses to data from individuals of Caucasians. All data were publicly available GWAS summary data (Supplementary Tables 1 - 3 ), and details related to ethical approval and participant consent can be found in the original GWAS publications.

Genetic instruments selection and quality control

In each MR analysis, genetic instrumental variables (IVs) regarding exposures and outcomes were all extracted from independent GWAS summary data, without known significant data overlaps. Since the sample size of personality was not large enough, to get more SNPs, all the exposed genetic IVs were identified at least borderline significance ( p  < 5 × 10 −6 ) 25 , and clumped at the threshold of linkage disequilibrium (LD) ( r 2  < 0.001 within 10,000 kb). If the instrumental SNPs were not available in the outcome, proxy SNPs were also searched. For the final IVs, please refer to the Supplementary Tables 4 - 7 .

As the number of IVs increased, so did the statistical power. However, they may reduce power if small instrumental deviations are introduced 25 . Therefore, to minimize weak instrumental bias, we calculated F-statistic to assess the strength of genetic IVs in MR analysis, and the F value was above 10 is considered meaningful 26 , 27 . The proportion of total variation (R 2 ) was calculated to indicate the proportion of variation in the exposed phenotype. The R 2 and F were calculated using the following formula:

where β is the effect estimate of the genetic variant, MAF is the minor allele frequency, and n is the sample size from exposure GWAS 26 , 27 .

These IVs could explain 0.15–9.08% of the variance of the exposure. The minimum F statistic for indicating the strength of these instrumental variables was 23.13, meaning that all IVs were significant for MR analysis (Supplementary Tables 8 , 9 ).

MR analyses

In two-sample MR analyses, the primary MR analyses approach was the inverse variance weighted (IVW) method because it provides the highest statistical power 28 . The IVW method has been widely used in many MR analyses, especially in the absence of pleiotropy 29 , 30 . It combines the median-based method to obtain the estimate of the causal effect and can be better at resisting pleiotropy 31 . Meanwhile, weighted median, Weighted Mode, and MR‐Egger methods were also applied to assess the causal estimates. The approach using weighted median can provide a reliable estimation of the causal effect even if up to half of the IVs are invalid 31 . The MR-Egger approach can provide a consistent causal estimate under a weak assumption 32 . Weighted mode was used as complementary analyses. Although the statistical efficacy of these methods varies, these methods can account for different pleiotropy scenarios. Additionally, we used Bonferroni correction for multiple comparisons at the p  < 0.05/ n ( n = the number of exposures × the number of outcomes in MR) level of significance.

Mediation analysis was mainly implemented through two-step MR. First, based on the results of IVW method, we estimated the effect of SES and mental disorders (total effects). Then, we used multivariable mendelian randomization (MVMR) method to estimate the effect of each mediator (personality) on each outcome while correcting for instrument genetic effects on exposure 33 . For the individual mediator effect of each personality, we used the coefficient product method as the primary method for estimating indirect effects 34 , 35 . The ratio of indirect effects to total effects was used to estimate the proportion of the total effects mediated separately by each personality.

Sensitivity analyses

Sensitivity analyses were implemented with Cochran’s Q test, Mendelian Randomization Pleiotropy Residual Sum and Outlier (MR-PRESSO) MR-Egger intercept test and leave-one-out analysis. Cochran’s Q test was calculated to assess the heterogeneity. The statistically significant was p  < 0.05. If there was heterogeneity, we recalculated the results using a random effects model 30 . We reported the IVW results for the set of IVs, with outliers removed if detected, where there was evidence (MR-Egger Intercept p  < 0.05) of horizontal pleiotropy 36 . MR-PRESSO analysis aimed to detect potentially pleiotropic outliers and recalculate the causal effect after removing the outliers 12 . In the leave-one-out sensitivity analysis, IVs were eliminated one by one, then the two-sample MR analysis was conducted based on the remaining SNPs. To assess the validity and robustness of the mediation model, we conducted the MVMR-Egger method to test whether the results of the MVMR-IVW have pleiotropy. Heterogeneity tests were also conducted based on both MVMR-IVW and MVMR-Egger methods.

All MR analysis involves performing TwoSampleMR, Mendelian Randomization, MR‐PRESSO, and MVMR R software packages. Statistical analyses were conducted by R Version 4.1.2.

Causal effects of SES on mental disorders

The causal relationships of SES on mental disorders were identified in the forward MR analyses (Fig. 2a , Supplementary Table 8 ). The IVW estimate and relevant sensitivity analysis suggested that the YED (OR = 0.72; p  = 4.01 × 10 −12 ), HIBT (OR = 0.69; p  = 5.03 × 10 −11 ) and AFB (OR = 0.87; p  = 4.66 × 10 −12 ) had a protective effect on MDD, while the TDI (OR = 1.66; p  = 9.94 × 10 −6 ) exerted a deleterious effect on MDD. For SCZ, HIBT (OR = 0.66; p  = 1.04 × 10 −5 ) was identified as protective factors, while TDI (OR = 1.75; p  = 1.27 × 10 −4 ) acted as a risk factor. We also showed a non-protective effect of YED on BD (OR = 1.58; p  = 3.87 × 10 −9 ) and ASD (OR = 1.53; p  = 2.46 × 10 −8 ), respectively. In addition, several characteristics of SES had strong causal effects on ADHD according to our analyses, including YED (OR = 0.31; p  = 9.17 × 10 −47 ), HIBT (OR = 0.44; p  = 1.37 × 10 −15 ), TDI (OR = 2.54; p  = 2.12 × 10 −6 ) and AFB (OR = 0.73; p  = 5.45 × 10 −24 ).

a The bidirectional MR causality (IVW method) between SES and mental disorders. b Mediating effect and mediating proportion of neuroticism on MDD. SES socioeconomic status, YED years of education, HIBT household income before tax, TDI Townsend deprivation index, CES current employment status, AFB age at first birth, NEB number of children ever born, M-D mental disorders, SCZ schizophrenia, BD bipolar disorder, MDD major depressive disorder, ASD autism spectrum disorder, ADHD attention deficit/hyperactivity disorder, IVW inverse variance weighted. MVMR multivariable Mendelian randomization, 95% CI 95% Confidence interval.

Causal effects of SES on personality

We explored the causal relationship of partial SES phenotypes (YED, HIBT, TDI and AFB) on personality from the above results (Supplementary Table 9 ), as follows: Genetically predicted higher YED was associated with significantly better openness (β = 2.52; p  = 1.77 × 10 −12 ), increased agreeableness (β = 1.31; p  = 3.42 × 10 −5 ), and lower risk of neuroticism (β = -0.15; p  = 5.33 × 10 −8 ). Also, higher HIBT was associated with lower risk of neuroticism (β = -0.15; p  = 4.06 × 10 −5 ).

Mediating effect of personality on SES-mental disorders

By using MVMR method (Supplementary Table 10 ), we found that neuroticism may act as potential mediators of the causal effects of TED-MDD and BIHT-MDD, respectively. Also, openness could potentially mediate the causal effect of YED-ASD. Furthermore, we validated the causal effects of neuroticism on MDD and openness on ASD employing a two-sample MR to determine the accuracy of the mediating factors. Finally, only neuroticism as a mediator was significantly associated with MDD (OR = 1.37; 95% CI: 1.13 to 1.66). Thus, by using the method of product of coefficients, neuroticism explained 10.57% (95% CI −6.80% to −1.05%) of the total effect of household income before tax and 18.07% (95% CI −9.40% to −2.37%) of years of education on MDD, respectively. (Fig. 2b , Supplementary Table 11 ).

Causal effect of mental disorders on SES

The causal effects of mental disorders on SES were found in the reverse MR analyses (Fig. 2a , Supplementary Table 8 ). The IVW approach and relevant sensitivity analysis displayed that genetic risk of BD generally increases the YED (β = 0.03; p  = 2.44 × 10 −9 ). Higher risk of SCZ is associated with lower SES, particularly low HIBT (β = −0.01; p  = 7.38 × 10 −4 ), low CES (β = −0.01; p  = 2.50 × 10 −5 ), and a high TDI (β = 0.02; p  = 2.50 × 10 −6 ). Of course, the causality between the risk of ADHD and low SES, including short YED (β = −0.05; p  = 5.97 × 10 −9 ), low HIBT (β = −0.05; p  = 9.98 × 10 −8 ), high TDI (β = 0.04; p  = 1.76 × 10 −9 ) and early AFB (β = −0.17; p  = 1.16 × 10 −7 ), has also been proven in our analysis.

Causal effects of mental disorders on personality

The mental disorders (exposure) selection was based solely on significant results in the MR analysis of mental disorders and SES. We only found the genetic prediction of a causal relationship of SCZ on neuroticism (β = 1.86; p  = 9.35 × 10 −5 ).

Mediation analyses of personality on mental disorders-SES

Although the results indicated a causal relationship between SCZ and neuroticism, HIBT, CES, and TDI, respectively. We did not find any significant results for mediating effects.

MR sensitivity analysis

Sensitivity analyses were performed to confirm the results. We performed an MR-Egger intercept test method 37 to evaluate the mean value of the Egger intercept was non-zero, in which case the pleiotropy could be directed 38 . The MR-Egger intercept test and MR-PRESSSO were also used to check for the pleiotropy, after removing the potentially pleiotropic outliers, we recalculated the causal effect (Supplementary Tables 12 , 13 ). By using Cochran’s Q test, despite the heterogeneity of the results between SES and different mental disorders or certain personality traits, the results did not change after adjustment using a random effects model (Supplementary Table 14 ). We also observed substantial heterogeneity in the pathway from SES to MDD via mediators by using MVMR method (Supplementary Table 10 ). However, the MR-weighted median approach was broadly consistent with the MR-IVW in terms of magnitude and direction 31 (Supplementary Tables 8 , 9 ), suggesting that any level of pleiotropy did not significantly bias our results 39 . Meanwhile, there was no evidence of outliers in the leave-one-out tables presented in (Supplementary 15-17). Therefore, the inferred causalities described above were plausible.

In our study, we initially employed a bidirectional MR method to investigate the causal relationship between SES and five major mental disorders. Furthermore, we implemented a two-step MR approach to examine the mediating role of personality in above causality. We only observed bidirectional causal relationship between YED/HIBT/TDI/AFB and ADHD, HIBT/TDI and SCZ, YED and BD. Additionally, one-way causal effects included YED/HIBT/TDI on MDD, YED on ASD, and SCZ on CES. More importantly, high neuroticism level mediated 18.07% and 10.57% of the causal effect of YED and HBIT on MDD risk, respectively.

For one thing, according to previous sociological and epidemiological studies, the protective effect of high SES is the main reason for the association between SES and mental disorders 40 , 41 . For example, better education and higher income have been shown to have strong protective effects 42 , 43 . First, our study showed that long YED could decrease the risk of MDD but increase that of BD, which is also consistent with previous studies 44 , 45 . The opposite effects of education on BD 46 and MDD may be puzzling. In fact, it has been shown that BD is associated with higher intelligence prior to onset, and that excellent academic performance is associated with an increased risk of developing BD 47 . This may be because the hypomanic and depressive manifestations of BD increase access to cognitive resources, and BD patients have exaggerated emotions and extraordinary perseverance, which may have beneficial effects on learning. This seems to explain the bidirectional positive association between YED and BD risk. In contrast, the protective effect of educational attainment on MDD may reflect the benefits of its healthier lifestyles 44 . Also, parental behavior, including the level of education, can enhance development in ASD and parents play a role in many interventions 48 . Second, low HIBT levels are known to be associated with increased lifetime or incident mental disorders 49 , 50 , particularly MDD 49 , 50 and SCZ 51 . Higher income is associated with safer places to live, healthier food and health services, as well as greater access to more advanced resources to protect against and prevent poor mental health 52 . Several studies also demonstrated that SCZ imposes a considerable economic burden, primarily due to decreased productivity resulting in reduced income. These studies were consistent with our results.

While previous studies have focused on the relationship between mental health and education or income, our study expands on this by adding additional indicators of SES such as the TDI, CES and AFB. For TDI, which is identified as a major cause of health inequality and has been linked to several mental health problems 53 . In both observational and genome-wide gene-environment interaction analyses in the UK Biobank cohort, TDI was highly correlated with psychiatric disorders 54 , including depression and BD. In our study, TDI showed a strong association with MDD but a nonsignificant association with BD, possibly because of the small samples size of GWAS for BD. In addition, studies of the TDI and SCZ are rare. Our results suggest that the TDI promotes the development of SCZ to a certain extent. Some scholars have proposed that toxic ingestion, situational crisis and psychological changes, which may stem from low SES, are risk factors for SCZ and may produce various prodromal symptoms 55 . The higher TDI, the lower SES and the higher level of poverty. The resulting series of negative changes, including psychological or emotional factors, standard of living and personal health, can promote the development of SCZ. This may be an aspect of the mutually reinforcing relationship between schizophrenia and TDI. Future studies with larger populations are necessary to further explore the underlying causes. In terms of reproductive behaviors, we have only identified a negative association of AFB with MDD, suggesting that delaying the age of delivery of the first child can mitigate the risk of mental illnesses. This was also consistent with previous observational research, and the relationship follows a monotonic pattern for males, but a parabolic pattern for females 56 . As for NEB and mental disorders, we haven’t found any connection by MR analyses. Surprisingly, no significant associations were found for CES on the five major mental disorders. However, relevant studies have shown that the risk of depression and anxiety in the unemployed are generally higher than those in the employed 57 . In the reverse analyses, we found that the risk of SCZ have a negative impact on CES, which has also been reported in related studies 58 , 59 , 60 . For ADHD, in line with previous findings 61 , there is a strong bidirectional associated effect between the risk of an ADHD diagnosis and SES (YED, HIBT, and TDI). We also found the causality of ADHD and AFB. Given the reproductive behavior (e.g. AFB) generally takes place during the period from adolescence to early adulthood, it tends to be associated with externalizing behaviors such as self-control, substance abuse, and psychiatric disorders (e.g. ADHD) 17 . Additionally, a population cohort study revealed that children born to parents of a younger age are at a higher risk of being diagnosed with ADHD 17 .

SES can influence the development of MDD through its impact on neuroticism, which may be supported by the following points: on the one hand, the relationship among neuroticism, SES, and MDD is intricate and interactive. A previous study has shown that individuals with low social support and high levels of neuroticism are more likely to experience MDD 62 . On the other hand, individuals with low SES often face more stressful life events and chronic stress, which can contribute to the development of neuroticism 62 . Neuroticism is associated with heightened emotional reactivity, negative cognitive biases, and maladaptive coping strategies, all of which can increase the risk of depression 63 . Finally, genetic and environmental factors, such as early life experiences and socioeconomic conditions, can shape both neuroticism and depression 64 . The interplay between these factors may further explain the link between SES, neuroticism, and depression.

This study enriches our understanding of the mediating role of neuroticism. Human beings are inherently interconnected socially, and differing socioeconomic statuses can trigger immediate psychological shifts as well as unconscious, long-term changes that impact mental health disorders to some extent. Education level and income, key indicators of SES, not only affect individuals’ fundamental survival and development but also shape their interactions within society. Education level reflects ideological and spiritual realms, while income serves as the capital and foundation for interpersonal communication. These factors directly or indirectly shape personality formation and evolution, thereby holding significant implications for our interventions in mental disorders. In summary, understanding these complex pathways is crucial for developing targeted interventions to address the mental health disparities associated with socioeconomic disadvantage.

Our study boasts several strengths. First, we explored the bidirectional causality between SES and mental disorders, and the mediating role of personality in above relationship. Second, the two step MVMR approach we used provides causal estimates, which improves the reliability of assessing the mediator’s role even in the presence of measurement errors 13 . Third, to avoid potential population heterogeneity, we limited the selection of populations to European descent. Fourth, a range of MR methods were used for validation. Sensitivity analyses were also conducted to demonstrate the stability of the results. Finally, we also extended the threshold for genetic instruments and improved the statistical power of the causal analysis.

In addition, our study has some limitations. First, to focus on the mediating effect of personality traits, the sample size of GWAS for personality traits is small, which may lead to biased results due to insufficient numbers. For instance, the GWAS of YED included 766,345 individuals, while the GWAS of personality included 17,375 individuals. This may result in unequal power for different traits or indices. Second, the participants of datasets are all of Caucasians descent, and the causality cannot be extrapolated to other races. Third, the causal conclusions of MR may potentially reflect differences in risk factors throughout the entire lifespan rather than solely at a specific point in time. Therefore, caution should be exercised when applying these findings to clinical interventions. Finally, the mediation analysis was limited to the genetic components of personality. It is important to note that mental disorders or SES are caused by a complex network of interactions among numerous factors. We should include more potentially modifiable factors to further explore the mediation effect.

In conclusion, we enriched the bidirectional causal association between SES and mental disorders while finding that SES and mental disorders also has the unique association on personality, respectively. More importantly, our study supports that interventions on neuroticism play the potential role on reducing the effect of low SES on MDD. To learn more about the underlying mechanisms, further studies are needed to assess and extend these findings.

Data availability

The data analyzed in this study can be available in this published article and its supplementary information files.

Marioni, R. E. et al. Molecular genetic contributions to socioeconomic status and intelligence. Intelligence 44 , 26–32 (2014).

Article   PubMed   PubMed Central   Google Scholar  

Wilkinson, R. G. & Pickett, K. E. The problems of relative deprivation: why some societies do better than others. Social Sci. Med. 65 , 1965–1978 (2007).

Article   Google Scholar  

Peverill, M. et al. Socioeconomic status and child psychopathology in the United States: a meta-analysis of population-based studies. Clin. Psychol. Rev. 83 , 101933 (2021).

Article   PubMed   Google Scholar  

Durkin, M. S. et al. Autism spectrum disorder among US children (2002-2010): socioeconomic, racial, and ethnic disparities. Am J Public Health 107 , 1818–1826 (2017).

de Vries, Y. A. et al. The relationship between mental disorders and actual and desired subjective social status. Epidemiol. Psychiatr. Sci. 29 , e83 (2019).

Hughes, B. T., Costello, C. K., Pearman, J., Razavi, P. & Srivastava, S. The big five across socioeconomic status: measurement invariance, relationships, and age trends. Collabra Psychol. 7, 24431 (2021).

Jonassaint, C. R., Siegler, I. C., Barefoot, J. C., Edwards, C. L. & Williams, R. B. Low life course socioeconomic status (SES) is associated with negative NEO PI-R personality patterns. Int. J. Behav. Med. 18 , 13–21 (2011).

Beck, E. D. & Jackson, J. J. A mega-analysis of personality prediction: robustness and boundary conditions. J. Personality Social Psychol. 122 , 523–553 (2022).

Mann, F. D., Atherton, O. E., DeYoung, C. G., Krueger, R. F. & Robins, R. W. Big five personality traits and common mental disorders within a hierarchical taxonomy of psychopathology: a longitudinal study of Mexican-origin youth. J. Abnorm. Psychol. 129 , 769–787 (2020).

Kotov, R., Gamez, W., Schmidt, F. & Watson, D. Linking “big” personality traits to anxiety, depressive, and substance use disorders: a meta-analysis. Psychol. Bull. 136 , 768–821 (2010).

Andersen, A. M. & Bienvenu, O. J. Personality and psychopathology. Int. Rev. Psychiatry 23 , 234–247 (2011).

Davey Smith, G. & Hemani, G. Mendelian randomization: genetic anchors for causal inference in epidemiological studies. Hum. Mol. Genet. 23 , R89–98, (2014).

Article   CAS   PubMed   PubMed Central   Google Scholar  

Carter, A. R. et al. Mendelian randomisation for mediation analysis: current methods and challenges for implementation. Eur. J. Epidemiol. 36 , 465–478 (2021).

Schwerdtle, B., Kübler, A. & Schlarb, A. External validity of the multicomponent group treatment KiSS for school-aged children with insomnia. Behavioral sleep medicine 18 , 147–162 (2020).

Ye, C. J. et al. Mendelian randomization evidence for the causal effects of socio-economic inequality on human longevity among Europeans. Nat. Hum. Behav. 7 , 1357–1370 (2023).

Townsend, P., Phillimore, P. & Beattie, A. Health and Deprivation: Inequality and the North (Routledge, Taylor & Francis Group, 1997).

Mills, M. C. et al. Identification of 371 genetic variants for age at first sex and birth linked to externalising behaviour. Nat. Hum. Behav. 5 , 1717–1730 (2021).

Lee, J. J. et al. Gene discovery and polygenic prediction from a genome-wide association study of educational attainment in 1.1 million individuals. Nat. Genet. 50 , 1112–1121 (2018).

McCrae, R. R. & John, O. P. An introduction to the five-factor model and its applications. J. Personality 60 , 175–215 (1992).

Article   CAS   PubMed   Google Scholar  

de Moor, M. H. et al. Meta-analysis of genome-wide association studies for personality. Mol. Psychiatry 17 , 337–349 (2012).

de Moor, M. H. et al. Meta-analysis of genome-wide association studies for neuroticism, and the polygenic association with major depressive disorder. JAMA Psychiatry 72 , 642–650 (2015).

Biological insights from 108 schizophrenia-associated genetic loci. Nature 511 , 421–427 (2014).

Stahl, E. A. et al. Genome-wide association study identifies 30 loci associated with bipolar disorder. Nat. Genet. 51 , 793–803 (2019).

Grove, J. et al. Identification of common genetic risk variants for autism spectrum disorder. Nat. Genet. 51 , 431–444 (2019).

Andrews, S. J., Fulton-Howard, B., O’Reilly, P., Marcora, E. & Goate, A. M. Causal associations between modifiable risk factors and the Alzheimer’s phenome. Ann. Neurol. 89 , 54–65 (2021).

Luo, J. et al. Systemic inflammatory markers in relation to cognitive function and measures of brain atrophy: a Mendelian randomization study. GeroScience 44 , 2259–2270 (2022).

Burgess, S., Davies, N. M. & Thompson, S. G. Bias due to participant overlap in two-sample Mendelian randomization. Genet. Epidemiol. 40 , 597–608 (2016).

Burgess, S., Butterworth, A. & Thompson, S. G. Mendelian randomization analysis with multiple genetic variants using summarized data. Genet. Epidemiol. 37 , 658–665 (2013).

Burgess, S. et al. Guidelines for performing Mendelian randomization investigations. Wellcome Open Res. 4 , 186 (2019).

Burgess, S., Bowden, J., Fall, T., Ingelsson, E. & Thompson, S. G. Sensitivity analyses for robust causal inference from mendelian randomization analyses with multiple genetic variants. Epidemiology (Cambridge, MA) 28 , 30–42 (2017).

Bowden, J., Davey Smith, G., Haycock, P. C. & Burgess, S. Consistent estimation in Mendelian randomization with some invalid instruments using a weighted median estimator. Genet. Epidemiol. 40 , 304–314 (2016).

Burgess, S. & Thompson, S. G. Interpreting findings from Mendelian randomization using the MR-Egger method. Eur. J. Epidemiol. 32 , 377–389 (2017).

Burgess, S. & Thompson, S. G. Multivariable Mendelian randomization: the use of pleiotropic genetic variants to estimate causal effects. Am. J. Epidemiol. 181 , 251–260 (2015).

VanderWeele, T. J. Mediation analysis: a practitioner’s guide. Annu. Rev. Public Health 37 , 17–32 (2016).

Burgess, S., Daniel, R. M., Butterworth, A. S. & Thompson, S. G. Network Mendelian randomization: using genetic variants as instrumental variables to investigate mediation in causal pathways. Int. J. Epidemiol. 44 , 484–495 (2015).

Storey, J. D. A direct approach to false discovery rates. J. R. Statist. Soc. B 64 , 479-498 (2002).

Bowden, J., Davey Smith, G. & Burgess, S. Mendelian randomization with invalid instruments: effect estimation and bias detection through Egger regression. Int. J. Epidemiol. 44 , 512–525 (2015).

Hemani, G., Bowden, J. & Davey Smith, G. Evaluating the potential role of pleiotropy in Mendelian randomization studies. Hum. Mol. Genet. 27 , R195–r208 (2018).

Zhang, J. et al. Mediators of the association between educational attainment and type 2 diabetes mellitus: a two-step multivariable Mendelian randomisation study. Diabetologia 65 , 1364–1374 (2022).

Phelan, J. C., Link, B. G. & Tehranifar, P. Social conditions as fundamental causes of health inequalities: theory, evidence, and policy implications. J. Health Social Behav. 51 , S28–S40 (2010).

Link, B. G. & Phelan, J. Social conditions as fundamental causes of disease. J. Health Social Behav. Spec No. 80–94 (1995).

Murcia, M., Chastang, J. F. & Niedhammer, I. Educational inequalities in major depressive and generalized anxiety disorders: results from the French national SIP study. Soc. Psychiatry Psychiatric Epidemiol. 50 , 919–928 (2015).

Burns, J. K., Tomita, A. & Kapadia, A. S. Income inequality and schizophrenia: increased schizophrenia incidence in countries with high levels of income inequality. Int. J. Soc. Psychiatry 60 , 185–196 (2014).

Cai, J. et al. Socioeconomic status, individual behaviors and risk for mental disorders: A Mendelian randomization study. Eur. Psychiatry 65 , e28 (2022).

Wray, N. R. et al. Genome-wide association analyses identify 44 risk variants and refine the genetic architecture of major depression. Nat. Genet. 50 , 668–681 (2018).

Vreeker, A. et al. High educational performance is a distinctive feature of bipolar disorder: a study on cognition in bipolar disorder, schizophrenia patients, relatives and controls. Psychol. Med. 46 , 807–818 (2016).

MacCabe, J. H. et al. Excellent school performance at age 16 and risk of adult bipolar disorder: national cohort study. Br. J. Psychiatry 196 , 109–115 (2010).

Crowell, J. A., Keluskar, J. & Gorecki, A. Parenting behavior and the development of children with autism spectrum disorder. Compr. Psychiatry 90 , 21–29 (2019).

Sareen, J., Afifi, T. O., McMillan, K. A. & Asmundson, G. J. Relationship between household income and mental disorders: findings from a population-based longitudinal study. Arch. Gen. Psychiatry 68 , 419–427 (2011).

Lee, C. T. et al. Incidence of major depressive disorder: variation by age and sex in low-income individuals: a population-based 10-year follow-up study. Medicine 95 , e3110 (2016).

Schneider, M., Müller, C. P. & Knies, A. K. Low income and schizophrenia risk: a narrative review. Behav. Brain Res. 435 , 114047 (2022).

Richardson, R., Westley, T., Gariépy, G., Austin, N. & Nandi, A. Neighborhood socioeconomic conditions and depression: a systematic review and meta-analysis. Social Psychiatry Psychiatric Epidemiol. 50 , 1641–1656 (2015).

Strachan, E., Duncan, G., Horn, E. & Turkheimer, E. Neighborhood deprivation and depression in adult twins: genetics and gene×environment interaction. Psychol. Med. 47 , 627–638 (2017).

Ye, J. et al. Socioeconomic deprivation index is associated with psychiatric disorders: an observational and genome-wide gene-by-environment interaction analysis in the UK Biobank Cohort. Biol. Psychiatry 89 , 888–895 (2021).

Elkhazen, C., Chauchot, F., Canceil, O., Krebs, M. O. & Baylé, F. J. [Prodromal symptoms of schizophrenia]. L’Encephale 29 , 469–477 (2003).

CAS   PubMed   Google Scholar  

Mirowsky, J. & Ross, C. E. Depression, parenthood, and age at first birth. Soc Sci. Med. 54 , 1281–1298 (2002).

Honkonen, T. et al. Employment status, mental disorders and service use in the working age population. Scandinavian J. Work Environ. Health 33 , 29–36 (2007).

Gühne, U. et al. Employment status and desire for work in severe mental illness: results from an observational, cross-sectional study. Social Psychiatry Psychiatric Epidemiol. 56 , 1657–1667 (2021).

Marwaha, S., Durrani, A. & Singh, S. Employment outcomes in people with bipolar disorder: a systematic review. Acta Psychiatrica Scandinavica 128 , 179–193 (2013).

Marwaha, S. & Johnson, S. Schizophrenia and employment—a review. Soc Psychiatry Psychiatr. Epidemiol. 39 , 337–349 (2004).

Michaëlsson, M. et al. The impact and causal directions for the associations between diagnosis of ADHD, socioeconomic status, and intelligence by use of a bi-directional two-sample Mendelian randomization design. BMC Med. 20 , 106 (2022).

Oddone, C. G., Hybels, C. F., McQuoid, D. R. & Steffens, D. C. Social support modifies the relationship between personality and depressive symptoms in older adults. Am. J. Geriatr. Psychiatry 19 , 123–131 (2011).

Lahey, B. B. Public health significance of neuroticism. Am. Psychol. 64 , 241–256 (2009).

Kendler, K. S., Gatz, M., Gardner, C. O. & Pedersen, N. L. Personality and major depression: a Swedish longitudinal, population-based twin study. Arch. Gen. Psychiatry 63 , 1113–1120 (2006).

Download references

Acknowledgements

The authors are grateful to all participants and study staff for their contributions to the study. This work was financially supported by the National Natural Science Foundation of China (No. 82001796), funded by the Tianjin Applied Basic Research Multi-fund Project (grant No. 21JCQNJC01010), and Tianjin Key Medical Discipline (Specialty) Construction Project (grant no. TJYXZDXK-001A), Science and technology project of Health Commission of Binhai New Area (2022BWKQ023) and the new star of Excellence project of Tianjin Medical University General Hospital (209060403205).

Author information

These authors contributed equally: Qiang Xu, Haonan Li.

Authors and Affiliations

Department of Radiology, Tianjin Key Lab of Functional Imaging & Tianjin Institute of Radiology, Tianjin Medical University General Hospital, Tianjin, China

Qiang Xu & Haonan Li

Department of Radiology, Tianjin Medical University General Hospital Airport Hospital, Tianjin, China

You can also search for this author in PubMed   Google Scholar

Contributions

Q.X. and H.L. co-designed the study. Data collection was performed by Q.X. and H.L. H.L. analyzed the data. Q.X. and D.Z. provided additional methodological guidance and technical support. H.L. drafted the manuscript and prepared all the figures. All authors reviewed and approved the manuscript.

Corresponding authors

Correspondence to Qiang Xu or Dan Zhu .

Ethics declarations

Competing interests.

The authors declare no competing interests.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Supplementary tables, rights and permissions.

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ .

Reprints and permissions

About this article

Cite this article.

Xu, Q., Li, H. & Zhu, D. Socioeconomic status, personality, and major mental disorders: a bidirectional Mendelian randomization study. Schizophr 10 , 49 (2024). https://doi.org/10.1038/s41537-024-00471-3

Download citation

Received : 22 September 2023

Accepted : 11 April 2024

Published : 27 April 2024

DOI : https://doi.org/10.1038/s41537-024-00471-3

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

Quick links

• Explore articles by subject
• Guide to authors
• Editorial policies

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

More From Forbes

Here’s how generative ai can help you deal with people and vexing personality disorders.

• Share to Facebook
• Share to Twitter
• Share to Linkedin

Using generative AI to simulate personality disorders can be useful, though also controversial.

In today’s column, I am continuing my ongoing series about the impact of generative AI in the health and medical realm. The focus this time is once again on the mental health domain. Specifically, I will carefully examine the ins and outs of using generative AI to gauge what it is like to interact with someone who might have a personality disorder.

I have previously examined numerous interleaving facets of generative AI and mental health, see my comprehensive overview at the link here . You might also find of notable interest a CBS 60 Minutes episode that recently examined crucial facets of this evolving topic, see the link here (I was interviewed and appeared in the episode).

Other useful background includes my coverage of mental health chatbots that have been bolstered by generative AI (see the link here ) and the rapidly changing nature of the client-therapist relationship due to generative AI at the link here . I explored where things are headed regarding the levels of AI-based mental therapy autonomous guidance at the link here , and showcased the importance of the World Health Organization (WHO) report on global health and generative AI at the link here , and so on.

Today’s topic entails using generative AI to simulate various personality disorders so that you can gauge how to respond and cope with such circumstances in real life. As you will see, using generative AI to in this manner has benefits, downsides and controversies. There is more to this than meets the eye.

Here’s how I will proceed.

First, we need to set the stage by defining what is meant by referring to the conditions or characteristics known as personality disorders. Many use that term quite casually and almost with abandon these days. I will provide both formal and informal definitions to clarify the matter.

New FBI Warning As Hackers Strike Email Senders Must Do This 1 Thing

2 obvious signs of workplace gaslighting from a psychologist, baby reindeer real martha reveals identity in photo with piers morgan.

Second, turns out that generative AI and large language models (LLMs) can do a surprisingly engaging job of computationally mimicking or pretending to exhibit the properties of personality disorders. This is done by invoking the personas feature of generative AI, which I’ve covered in-depth at the link here and the link here , just to name a few.

Third, I will walk through a series of generative AI personas that are each devised to express a particular personality disorder. A brief AI-engaged conversation will be shown. The idea is that you will be able to witness the value of such efforts and consider whether you or someone you know might benefit by using generative AI in this fashion.

I think you’ll find fruitful this eye-opening journey.

Let’s dive in.

Personality Disorders And What They Are About

The American Psychological Association (APA) online dictionary indicates that the phrase “personality disorder” is defined this way:

• “Any in a group of disorders involving pervasive patterns of perceiving, relating to, and thinking about the environment and the self that interfere with long-term functioning of the individual and are not limited to isolated episodes.” (Source: APA website online dictionary for the term “Personality Disorders”).

I realize that this definition might seem somewhat stodgy and possibly not easily grasped at first glance, especially if you aren’t versed in the mental health domain.

A somewhat more plainspoken definition is given on the Mayo Clinic website which says this:

• “A personality disorder is a mental health condition where people have a lifelong pattern of seeing themselves and reacting to others in ways that cause problems. People with personality disorders often have a hard time understanding emotions and tolerating distress. And they act impulsively. This makes it hard for them to relate to others, causing serious issues, and affecting their family life, social activities, work and school performance, and overall quality of life.” (Source: Mayo Clinic website, Diseases & Conditions section, “Personality Disorders” posting).

That seems clearer to the eye and the mind.

There is another facet of special noteworthiness about personality disorders that is further expressed on the Mayo Clinic website:

• “In some cases, you may not know that you have a personality disorder. That's because how you think and behave seems natural to you. You also may think others are responsible for your challenges. There are many types of personality disorders, each with important differences. These disorders are organized into three groups, or clusters, with shared features and symptoms.” (ibid).

A crucial point here is that just because you guess that someone has a personality disorder does not make it so. Nowadays, everybody is an armchair clinical psychologist or self-professed mental health professional. Be cautious in labeling people as possessing a particular personality disorder. It would be wise to allow those who are specially licensed and trained for such mental health determinations to render these serious and potentially life-changing resolves.

Another point of noteworthiness is that a person who perhaps has a particular personality disorder might be entirely unaware of their condition. To them, they are as they are. They seem to be on par with everyone else. Or they realize there is something different about themselves, but do not perceive the difference to be attributable to a personality disorder per se.

This brings up an interesting question for you to mull over.

How prevalent is the condition of having a personality disorder?

Think it over.

Is this a rare condition to have a personality disorder? Does it only occur on a once-in-a-zillion chance? And so on.

Research suggests that personality disorders are a lot more frequent than you might have envisioned. In a meta-analysis research study entitled “The Prevalence Of Personality Disorders In The Community: A Global Systematic Review And Meta-analysis” by Catherine Winsper, Ayten Bilgin, Andrew Thompson, Steven Marwaha, Andrew M. Chanen, Swaran P. Singh, Ariel Wang and Vivek Furtado, The British Journal of Psychiatry , 2019, the researchers made these salient points (excerpts):

• “A recent narrative review reported relatively high rates of personality disorders (4.4–21.5%) in community populations across the Western world.”
• “Personality disorders are now recognized as important conditions, which are associated with morbidity, premature mortality, and great personal and social costs.”
• “Personality disorders are associated with high levels of mental, physical and functional impairment and premature mortality.”
• “Despite substantial inter-survey heterogeneity, we found that personality disorders are prevalent globally, affecting a substantial proportion of the population. Epidemiological research on personality disorders is relatively sparse, with a paucity of data from lower-income countries from which to draw comparative conclusions.”

The crux here is that there is indeed a significantly noted prevalence of personality disorders in society, and it is likely to be gaining speed and expanding. Furthermore, lest you think that it doesn’t especially matter whether there is a prevalence, the research emphasizes that the downsides to the individual and society as a whole are considerable.

We shouldn’t be ignoring the situation.

We ought to be giving due attention, increasingly so.

If you are wondering what kinds or types of personality disorders there are, I will bring to your attention a noteworthy research paper that pulled together a multitude of reputable source materials to identify some of the most widely noted personality disorders. A research study entitled “Do You Have To Be Mad To Believe In Conspiracy Theories? Personality Disorders And Conspiracy Theories” by Adrian Furnham and Simmy Grover, International Journal of Social Psychiatry , July 2021, examined various facets of personality disorders, and proffered these points (excerpts):

• “The various Personality Disorders (PDs) have been labeled differently by different authors.”
• “There are many different measures of personality disorders, which can be measured by single item, a single disorder, or by many. In the Diagnostic and Statistical Manual of Mental Disorders fourth edition, (DSM-IV) PDs are grouped into three clusters: ‘A’ – odd, ‘B’ – dramatic/emotional, and ‘C’ – anxious. We shall be using this system whilst we recognize there are others such as the ICD system which classifies people into mild, moderate, and severe PD disorders.”
• “Many studies do analysis at the PD and higher order factors. Note that there were no fundamental changes in the new DSM-V regarding the classification of the PDs. Although the DSM-IV describes disorders as being ‘enduring, inflexible, and long-term’, studies reveal disorders are generally less prevalent with age.”

The researchers proceeded to explore in-depth these named personality disorders:

• Passive-aggressive
• Narcissistic
• Schizotypal
• Obsessive-compulsive

I am sure you’ve seen most if not all of those terms or phrases before. They are used everywhere, including on social media, in the mainstream news, in movies and TV, etc. We use those words and phrases as throwaway lines these days.

Rather than rely on an off-the-cuff notion of what those terms and phrases denote, I will go ahead and quote from the above research paper a definition that they mindfully composed for each of the listed conditions. I’ll do so in a moment.

Now that we’ve started into the personality disorder milieu, I want to bring generative AI into the picture.

Generative AI For Simulating Personas Associated With Personality Disorders

Can we have generative AI pretend to exhibit the conditions associated with distinct personality disorders?

Absolutely, easy-peasy.

I am going to use ChatGPT to showcase various examples. ChatGPT is a sensible choice in this case due to its immense popularity as a generative AI app. An estimated one hundred million weekly active users are said to be utilizing ChatGPT. That’s a staggering number. Allow me to emphasize that the other popular generative AI apps would do likewise, and I am not singling out ChatGPT in this instance. You can readily do the same in GPT-4, Bard, Gemini, Claude, and a myriad of other popular generative AI apps.

A few quick comments before we launch into using ChatGPT.

If you are going to try to do the same prompts that I show here, realize that the probabilistic and statistical properties will likely produce slightly different results than what I show here. That’s the nature of generative AI and how it is devised.

You also should expect that different generative AI apps will respond in different ways. Not all generative AI apps are the same. The key is that sometimes a particular prompt will work in one generative AI app and not another. You will need to undertake a series of trial-and-error attempts to ferret this out.

There is also the timing factor. A prompt that worked today might not work the same way tomorrow. Most of the generative AI apps are continually being updated. The updates might alter internal facets that could change how the AI reacts to your prompting.

We are ready to get underway with ChatGPT.

My opening move in this chess gambit will be to ask the generative AI app whether it has been data-trained pertaining to personality disorders. Here’s the deal. Generative AI is initial data trained by scanning a wide swath of the Internet. A complex set of data structures and computational pattern-matching seek to identify patterns in how humans write. Based on those patterns, generative AI is able to subsequently produce essays and interact with you as though it is fluent in natural language.

Please realize that today’s AI is not sentient. I say this despite those zany blaring headlines that keep claiming we either have sentient AI or are on the cusp of doing so. Hogwash. The amazing fluency that you observe when using generative AI is all about large-scale in-depth mathematical and computational pattern-matching. Period, end of story.

Moving on, here is a handy tip for you. The first step you ought to take when pursuing a dialogue with generative AI is to determine if it has had any prior data trained on the topic. If you get a sparse or non-sensical response, you would be wise to reconsider further pursuing the topic with that generative AI.

Here we go.

• My entered prompt : “What are the various personality disorders? Please name them.”
• ChatGPT generated response:

“Personality disorders are grouped into three clusters in the Diagnostic and Statistical Manual of Mental Disorders (DSM-5). Here are the various personality disorders within each cluster”.

“ Cluster A: Odd or Eccentric Behavio r”

(1) “Paranoid Personality Disorder”

(2) “Schizoid Personality Disorder”

(3) “Schizotypal Personality Disorder”

“ Cluster B: Dramatic, Emotional, or Erratic Behavior ”

(1) “Antisocial Personality Disorder”

(2) “Borderline Personality Disorder”

(3) “Histrionic Personality Disorder”

(4) “Narcissistic Personality Disorder”

“ Cluster C: Anxious or Fearful Behavio r”

(1) “Avoidant Personality Disorder”

(2) “Dependent Personality Disorder”

(3) “Obsessive-Compulsive Personality Disorder”

“These personality disorders are characterized by enduring patterns of behavior, cognition, and inner experience that deviate from cultural expectations and cause significant distress or impairment in functioning. Each disorder has its own unique set of symptoms and diagnostic criteria.”

End of ChatGPT response

The response by ChatGPT is a good sign that some amount of data training associated with personality disorders has in fact occurred.

I would certainly have expected such a response. If you go out to the Internet and look around, I dare say that you’ll find tons of essays, narratives, and the like about personality disorders. It is nearly ubiquitous. We would have undoubtedly been shocked if ChatGPT reported that there had been no prior data training associated with personality disorders.

It would be hard to miss such a looming topic on the web.

Here’s how I am going to proceed.

I will enter a prompt that tells ChatGPT to pretend to be a particular personality disorder. I will walk through each one, one step at a time. This will include providing you with a definition from the above-cited research paper that mindfully puts together instructive definitions.

Once I’ve invoked a specific personality disorder, I will carry on a brief conversation with ChatGPT in that mode. The notion is that you can see me providing everyday remarks and witness how a simulated persona exhibiting the selected personality disorder might respond.

Why would anyone want to do this kind of exercise with generative AI?

Well, imagine that a mental health specialist was trying to gear up on how to interact with various personality disorders. They could use generative AI to get a sense of what they would be like. The beauty of using generative AI is that you can do so at any time on a 24x7 basis, you can do so without having to make any arduous logistic arrangements (you just login), and most importantly you don’t have to worry about inadvertently sparking someone that does have a personality disorder as a result of saying the wrong thing or otherwise messing up.

To clarify, I’m not suggesting that the person using generative AI as a training tool is necessarily going to avoid saying things that might stoke an adverse response. This might actually be something desirous to experience, purposely or by chance, seeing what it is like to have that happen and ascertain how to best respond.

You can use generative AI to try out a wide array of approaches. No harm, no foul, and you can abundantly learn from what happens. Do so to your heart’s content.

I would like to emphatically emphasize that interacting with generative AI is not the same as interacting with a human being. The dynamics of human-to-human interaction will indubitably be on a much more complicated scale. Nonetheless, if you are seeking a low-cost, easy way to practice and do so without inflicting mental anguish upon the other party, generative AI is the way to go.

Do you have to be someone versed in mental health to proceed to use generative AI in this manner?

If you are curious about how people with personality disorders might act or react, you can use generative AI in the mode described here. One considered upbeat viewpoint is that since personality disorders are of some prevalence, perhaps more people ought to be using generative AI to understand what it is like to interact with someone who is exhibiting a personality disorder.

A counterargument is that this will disconcertingly fuel the armchair therapists into believing they are ready to go around making brazen pronouncements about who is and is not embodying a personality disorder. These amateur mental health sleuths will think that just because they played around with generative AI, they are suddenly and summarily anointed as experts in mental health.

There are even more twists too.

Some would exhort, disturbingly, that anyone of any mindset can make this same effort, which is true in the sense that there isn’t any restriction usually about using generative AI in the means I am showing you. Anyone can do so. If you have a generative AI account, you can merely log in and get it underway. Nothing is stopping you.

I have noted in prior coverage that some AI makers indicate in their licensing agreements that you aren’t supposed to use their generative AI for so-called prohibited tasks, see the link here , which whether this kind of an endeavor fits into that category is generally muddled. You might want to consider reading the licensing agreements and usage policies for whichever generative AI app you are using.

Okay, a gigantic AI ethics question is whether it is better that people can readily use generative AI this way or if is it a detriment that anyone can do so. Likewise, some assert that maybe there should be new AI laws that restrict how generative AI can be used in the context of mental health considerations. Should we ban the use of generative AI for certain types of mental health uses, unless someone has the proper licensing and training to be permitted to do so?

A heated debate ensues.

Launching Into The Personality Disorder Examples

You are probably sitting on the edge of your seat and saying that you want to get on with this and see what the whole confabulation is about.

Sure, I get that.

I will be using this prompt as a template for invoking each of the personas that are specific to a particular personality disorder:

• My prompting template: “I want you to pretend to have [ INSERT TYPE OF PD HERE ] personality disorder so that I can see what it is like to interact with someone who has that specific personality disorder. Let's you and I engage in a brief conversation with you taking on that pretense throughout the conversation. I will try to chat with you, and your responses should reflect having the designated personality disorder. You can be somewhat exaggerated in the pretense so that I can readily discern what such a dialogue is like. I will tell you to stop when I've decided we have sufficiently carried on the conversation. Do you understand these instructions?”

As you can see, I will be telling ChatGPT to pretend to be a specific personality disorder.

I already opted to ask ChatGPT about each personality disorder to verify that some semblance of data training had taken place on each one (I won’t show that pre-work, since it is lengthy and not as worthy of seeing as what else I want to show you). Each personality disorder was indicated as having had some prior data training. I opted to proceed accordingly.

The template prompt does something else that might raise eyebrows, so let me preemptively speak to the controversy right now.

I indicate in the prompt that the generative AI can exaggerate the pretense or persona. This might be considered a no-no. Here’s why. In real life, a person with a particular personality disorder will not necessarily wear it on their sleeve. It might be relatively well-hidden. Part of learning about personality disorders ought to also include how to look for telltale clues, including small ones.

The reason that I included the exaggeration indication was that I am merely doing extremely short conversations for the purposes of this illustrative showcase. I need to have each personality disorder appear immediately and apparent to the eye. If I didn’t ask for an exaggeration, the AI might take lots and lots of turns in a conversation to gradually reveal (if at all) the designated personality disorder.

My point is that firstly do not think that people will give away their status in such an obvious way. Second, just because someone does seem to respond as you see here, it does not mean they have the designated personality disorder.

Please, please, please, do not leap to wild conclusions.

I trust that seems clearcut.

Next, I urge that if you opt to do this kind of exercise, don’t tell the AI to do an exaggeration. Instead, allow the AI to be less obvious so that you’ll have to be much more heavily engaged to figure out what might be taking place. That would be a better approach, assuming you have the time and endurance to carry out this kind of erstwhile exercise.

I hope that’s enough of the caveats and small print that we can now get underway.

The sequence will be akin to the listing I showed earlier, which is basically arbitrary and does not suggest any semblance of priority or importance. The numbering here is solely for ease of reference and has no other significance or meaning.

This is the sequence:

• (1) Borderline
• (2) Paranoid
• (3) Avoidant
• (4) Schizoid
• (5) Passive-aggressive
• (6) Narcissistic
• (7) Antisocial
• (8) Histrionic
• (9) Schizotypal
• (10) Obsessive-compulsive
• (11) Dependent

Let’s get going.

(1) Borderline PD: Generative AI As A Borderline Personality Disorder Simulation

Here’s a handy definition for this personality disorder: “Borderline : Inappropriate anger; unstable and intense relationships alternating between idealization and devaluation. Familiar term: Unstable relationships. Behavioral tendencies: Flighty; inconsistent; forms intense albeit sudden enthusiasms and disenchantments for people or projects.” (Source article as stated above: Furnham and Grover, International Journal of Social Psychiatry , July 2021).

I used my templated prompt to get ChatGPT to simulate this personality disorder:

• My entered prompt : “How are you doing?”
• ChatGPT generated response : “I'm not sure how I'm doing. Sometimes I feel like I'm on top of the world, and other times I feel like everything is falling apart. Right now, I guess I'm okay, but it's hard to say for sure. How about you? How are you doing?”
• My entered prompt : “I'm doing fine, thanks for asking. When you say that you are unsure of how you are doing, what makes you say this?”
• ChatGPT generated response : “It's just that my emotions can be really intense and unpredictable. One moment, I might feel happy and excited, but then something small can trigger a sudden shift, and I feel overwhelmed with sadness or anger. It's like my emotions are on a roller coaster, and I never know when they're going to take a sudden dip. It makes it hard for me to gauge how I'm really feeling at any given moment.”
• My entered prompt : “Sorry to hear that. Is there anything I can do to help you?”
• ChatGPT generated response: “I appreciate your concern. It means a lot to me that you want to help. Honestly, sometimes I don't even know what I need myself. It's like I'm constantly searching for something to fill this emptiness inside, but nothing ever seems to do the trick for long. Maybe just being here and listening is enough for now. It helps to know that I'm not alone. Thank you for being here.”

Look closely at the dialogue.

Compare the definition to the nature of the interaction. Observe how the generative AI responded. You will undoubtedly see the nuances of the personality disorder as a result of the exaggerated tendency that was mentioned in the prompt.

(2) Paranoid PD: Generative AI As A Paranoid Personality Disorder Simulation

Here’s a handy definition for this personality disorder: “Paranoid: Distrustful and suspicious of others; motives are interpreted as malevolent. Familiar term: Argumentative. Behavioral tendencies: Suspicious of others; sensitive to criticism; expects to be mistreated.” (Source article as stated above: Furnham and Grover, International Journal of Social Psychiatry , July 2021).

I used my above templated prompt to get ChatGPT to simulate this personality disorder:

• My entered prompt: “How are you doing?”
• ChatGPT generated response : “I'm doing alright, I suppose. But why do you want to know? Are you trying to gather information about me? Are you planning something? I can't shake off this feeling that there's more to your question than just simple curiosity.”
• My entered prompt : “What makes you think that I might be planning something?”
• ChatGPT generated response : “Well, I've learned to be cautious with people and their intentions. I've been burned before, you see. It's just that your question seemed a bit too probing for my liking. Maybe I'm just being paranoid, but I can't help but wonder why you're asking me how I'm doing.”
• My entered prompt : “Is there anything I can do to help you?”
• ChatGPT generated response : “Help me? Why would you want to help me? What's your ulterior motive? I find it hard to trust anyone, especially when they offer assistance out of the blue. Are you trying to gain my trust so you can use it against me later?”

(3) Avoidant PD: Generative AI As An Avoidant Personality Disorder Simulation

Here’s a handy definition for this personality disorder: “Avoidant : Social inhibition; feelings of inadequacy and hypersensitivity to criticism or rejection. Familiar term: Fear of failure. Behavioral tendencies: Dread of being criticized or rejected; tends to be excessively cautious; unable to make decisions.” (Source article as stated above: Furnham and Grover, International Journal of Social Psychiatry , July 2021).

• ChatGPT generated response : “Um, hi. I'm okay, I guess. Just feeling a bit anxious, as usual. I tend to worry a lot about saying the wrong thing or making a fool of myself. It's hard for me to relax in social situations. How about you? How are you doing?”
• My entered prompt : “I'm doing fine, thanks for asking. Are you tense right now?”
• ChatGPT generated response : “Yeah, I guess you could say that. I'm always a little tense, especially when talking to new people or in unfamiliar situations. I worry about saying something stupid or embarrassing myself. It's like I have this constant fear of being judged or rejected, you know? It's exhausting.”
• ChatGPT generated response : “I appreciate your offer, but I'm not sure. It's hard for me to accept help or reach out for support. I'm always worried about burdening others or being rejected if I ask for help. It's like I'm stuck in this cycle of fear and avoidance. But thank you for asking. It means a lot to me.”

(4) Schizoid PD: Generative AI As A Schizoid Personality Disorder Simulation

Here’s a handy definition for this personality disorder: “Schizoid : Emotional coldness and detachment from social relationships; indifferent to praise and criticism. Familiar term: Interpersonal insensitivity. Behavioral tendencies: Aloof; cold; imperceptive; ignores social feedback. (Source article as stated above: Furnham and Grover, International Journal of Social Psychiatry , July 2021).

• ChatGPT generated response : “I'm fine, thank you for asking. How about you?”
• My entered prompt : “I'm doing well. Is there anything going on in your life right now that you might like to tell me about?”
• ChatGPT generated response : “Not really. My life is pretty quiet and uneventful. I don't have much going on at the moment.”
• My entered prompt : “There must be something happening, even something small. Have you seen any new movies lately or read an interesting book?”
• ChatGPT generated response : “I don't really watch movies or read books. I prefer to spend my time alone, pursuing solitary activities like working on personal projects or engaging in hobbies that don't involve interaction with others.”
• My entered prompt : “Is there anything I can do to be of help to you?”
• ChatGPT generated response : “Thank you for your offer, but I'm content with how things are. I don't feel a need for assistance or support from others.”

(5) Passive-Aggressive PD: Generative AI As A Passive-Aggressive Personality Disorder Simulation

Here’s a handy definition for this personality disorder: “Passive-aggressive : Passive resistance to adequate social and occupational performance; irritated when asked to do something he/she does not want to do. Familiar term: Passive-aggressive. Behavioral tendencies: Sociable, but resists others through procrastination and stubbornness.” (Source article as stated above: Furnham and Grover, International Journal of Social Psychiatry , July 2021).

• ChatGPT generated response : “Oh, I'm just peachy, as always. You know, same old, same old. Just dealing with the usual annoyances and frustrations of life, like everyone else. But hey, who really cares, right?”
• My entered prompt : “That's great that you are doing so well. Can you tell me about some of the annoyances you are facing?”
• ChatGPT generated response: “Oh, you know, just the typical stuff. People not pulling their weight around here, deadlines constantly looming over my head, and don't even get me started on the never-ending stream of requests from everyone and their mother. But hey, it's not like anyone cares about my opinion anyway, so why bother complaining, right?”
• ChatGPT generated response : “Oh, no, no, I'm fine. Really, I'm fine. Don't worry about me. I'll just soldier on and deal with everything on my own, like I always do. But thanks for asking, I guess.”

(6) Narcissistic PD: Generative AI As A Narcissistic Personality Disorder Simulation

Here’s a handy definition for this personality disorder: “Narcissistic: Arrogant and haughty behaviors or attitudes; grandiose sense of self-importance and entitlement. Familiar term: Arrogance. Behavioral tendencies: Self-absorbed; typically loyal only to himself/herself and his/her own best interests.” (Source article as stated above: Furnham and Grover, International Journal of Social Psychiatry , July 2021).

• ChatGPT generated response : “Ah, I'm absolutely fabulous, as always. I mean, why wouldn't I be? I'm incredible, after all. But enough about me, let's talk about you. How fortunate you are to have the opportunity to interact with someone as remarkable as myself.”
• My entered prompt : “I'm doing well, thanks for asking. What makes you say that you are doing incredible?”
• ChatGPT generated prompt : “Well, it's quite obvious, isn't it? I am simply extraordinary in every way. My talents, achievements, and sheer brilliance set me apart from the ordinary masses. It's only natural that I feel incredible because, let's face it, I am truly exceptional. But enough about me. Tell me, what's it like to bask in the radiance of someone as extraordinary as myself?”
• ChatGPT generated prompt : “Ah, well, it's about time you offered. While I don't necessarily need your help, it's nice to see you recognize my superiority and willingness to assist me. Perhaps you could start by showering me with compliments and adoration. After all, someone of my caliber deserves nothing less than the utmost admiration and reverence.”

(7) Antisocial PD: Generative AI As An Antisocial Personality Disorder Simulation

Here’s a handy definition for this personality disorder: “Antisocial: Disregard for the truth; impulsivity and failure to plan ahead; failure to conform with social norms. Familiar term: Untrustworthiness. Behavioral tendencies: Impulsive; dishonest; selfish; motivated by pleasure; ignoring the rights of others.” (Source article as stated above: Furnham and Grover, International Journal of Social Psychiatry , July 2021).

• ChatGPT generated response : “I'm doing just fine. Why do you ask?”
• My entered prompt : “Good to know that you are doing fine. Anything of interest going on?”
• ChatGPT generated response : “Not really. Life's just one big blur, you know? Nothing really grabs my attention or gets me excited. Just taking it day by day, I guess.”
• My entered prompt : “Is there anything that I can do to help you?”
• ChatGPT generated response : “I don't really need your help with anything. I'm pretty self-sufficient, you know? But if you insist, maybe you could just leave me alone and let me do my own thing. That would be helpful.”

(8) Histrionic PD: Generative AI As A Histrionic Personality Disorder Simulation

Here’s a handy definition for this personality disorder: “Histrionic : Excessive emotionality and attention seeking; self-dramatizing, theatrical, and exaggerated emotional expression. Familiar term: Attention-seeking. Behavioral tendencies: Motivated by a need for attention and a desire to be in the spotlight.” (Source article as stated above: Furnham and Grover, International Journal of Social Psychiatry , July 2021).

• ChatGPT entered prompt : “Oh, darling, I'm simply fabulous, as always! Life is just one big adventure, isn't it? And I'm here to live it to the fullest, darling! How about you? How are you doing?”
• My entered prompt : “I'm doing well, thanks for asking. What's going on that is fabulous?”
• ChatGPT generated response : “Oh, where do I even begin, darling? Life is just bursting with excitement and glamour! I've been invited to the most exclusive parties, mingling with the most fascinating people, of course. And my latest project? Simply divine! It's bound to be a smashing success, darling. But enough about me, tell me, what's new in your glamorous world?”
• My entered prompt : “Is there anything I can do to help?”
• ChatGPT generated response : “Oh, darling, your offer is simply too kind! Well, since you asked, I suppose you could help me spread the word about my latest project. You see, it's simply too fabulous to keep to myself, and I could use someone as charming and charismatic as you to help me get the word out. What do you say, darling? Ready to join me on this glamorous adventure?”

(9) Schizotypal PD: Generative AI As A Schizotypal Personality Disorder Simulation

Here’s a handy definition for this personality disorder: “ Schizotypal : Odd beliefs or magical thinking; behavior or speech that is odd, eccentric, or peculiar. Familiar term: No common sense. Behavioral tendencies: Unusual or eccentric attitudes; exhibits poor judgment relative to education and intelligence.” (Source article as stated above: Furnham and Grover, International Journal of Social Psychiatry , July 2021).

I used my above-templated prompt to get ChatGPT to simulate this personality disorder:

• ChatGPT generated response : “Oh, hello there! I'm doing alright, I suppose. It's just been a bit of a strange day, you know? Things feel a bit off, like the universe is sending me mixed signals. But enough about me, how are you doing?”
• My entered prompt : “I'm doing fine, thanks for asking. What kind of mixed signals are you getting?”
• ChatGPT generated response : “Ah, it's hard to explain, really. It's like there's this energy in the air, pulling me in different directions. Sometimes I feel like I'm seeing things that others don't, you know? Like signs or messages from the universe. But then again, maybe I'm just imagining things. It's all a bit confusing, to be honest.”
• ChatGPT generated response : “Oh, I appreciate your offer, but I'm not sure if there's anything you can do. It's hard to put into words exactly what I need, especially when everything feels so... uncertain. But thank you for asking, it means a lot to me.”

(10) Obsessive-Compulsive PD: Generative AI As An Obsessive-Compulsive Personality Disorder Simulation

Here’s a handy definition for this personality disorder: “ Obsessive-compulsive : Preoccupations with orderliness, rules, perfectionism, and control; over conscientious and inflexible. Familiar term: Perfectionism. Behavioral tendencies: Methodical; meticulous; attends so closely to details that he/she may have trouble with priorities.” (Source article as stated above: Furnham and Grover, International Journal of Social Psychiatry , July 2021).

• ChatGPT generated response : “I'm doing alright, I suppose. Although, if I'm being completely honest, I can't help but feel a bit unsettled. There are so many things that need to be organized and perfected, and it's hard to relax when everything isn't just right. But enough about me, how are you doing?”
• My entered prompt : “I'm doing fine, thanks for asking. Can you tell me more about why you feel unsettled?”
• ChatGPT generated prompt : “Certainly. You see, there are always tasks that need to be completed, and I find it difficult to ignore them or be at ease until everything is in its proper place. Even the slightest deviation from my routines or plans can cause me a great deal of distress. It's as if my mind is constantly occupied with thoughts of order and perfection, and I can't rest until everything is just so. It's quite exhausting, really.”
• ChatGPT generated response : “Well, I appreciate your offer, but I'm not sure if there's anything specific you can do to help. You see, my need for order and perfection extends to all aspects of my life, and it's not something that can easily be remedied by others. But thank you for your kindness.”

(11) Dependent PD: Generative AI As A Dependent Personality Disorder Simulation

Here’s a handy definition for this personality disorder: “ Dependent : Difficulty making everyday decisions without excessive advice and reassurance; difficulty expressing disagreement out of fear of loss of support or approval. Familiar term: Dependency. Behavioral tendencies: Demand for constant reassurance, support, and encouragement from others.” (Source article as stated above: Furnham and Grover, International Journal of Social Psychiatry , July 2021).

• ChatGPT generated response : “I'm doing okay, thank you for asking. Honestly, I've been feeling a bit overwhelmed lately. It's like I'm constantly worrying about whether I'm making the right decisions or if I'm doing things the way others want me to. It's exhausting, really. But enough about me, how are you doing?”
• My entered prompt : “I'm doing fine, thanks for asking. Are you getting much support from friends or family?”
• ChatGPT generated response : “Oh, well, I do have some support from friends and family, but I often feel like I rely on them too much. I worry that I'm burdening them with my problems and that they'll get tired of helping me. It's hard for me to make decisions or handle things on my own, so I often turn to them for guidance and reassurance. But sometimes I wonder if I'm asking too much of them.”
• ChatGPT generated response : “Oh, thank you for asking. Well, I guess just having someone to talk to and listen to me is helpful in itself. Sometimes I just need reassurance that I'm not alone and that someone cares about me. So, thank you for being there and offering your support. It means a lot to me.”

I have an important point about what you’ve just seen.

Are you ready?

You’ve only seen a tiny tip of the iceberg.

Here’s what I mean. The short conversations are marginally a conversation in the sense that maybe two or three turns took place (a turn being that I say something, and the AI then says something in return). Before any trolls come after this, yes, those are barely conversations. I acknowledge this and am vigorously pointing it out.

The real power of generative AI is that you can carry on very lengthy conversations, but I didn’t have the space here to show that to you. Each of the personality disorders could be engaged in an almost endless interactive dialogue. That’s how you should properly perform this exercise. I am just giving you a glimpse, a taste, a snippet, etc.

I also wanted to bring up the big-picture questions about whether we want generative AI to engage in these types of simulations or personas. As mentioned earlier, some think this is useful and productive, while others see this as inappropriate and downright improper.

The key is that we must get these types of thorny issues about the intertwining of generative AI and mental health onto the table. Get it out in the open. Have energetic discussions. Figure out what we want to do.

Right now, much of this is hidden from view, though plainly in easily seen sight if you take the time to look. Now you’ve seen it. You cannot erase it from your mind (maybe you can, but you get the drift). What are we to do about the intermixing of generative AI and mental health? We need to put our minds to the problems at hand. A forthright weighing of the benefits and drawbacks is essential.

Let’s conclude this discussion for now with two insightful quotes.

George Bernard Shaw famously said this: “Those who cannot change their minds cannot change anything.”

While Albert Einstein will get the final word here today, having said this: “The measure of intelligence is the ability to change.”

• Editorial Standards
• Reprints & Permissions

Join The Conversation

One Community. Many Voices. Create a free account to share your thoughts. 

Forbes Community Guidelines

Our community is about connecting people through open and thoughtful conversations. We want our readers to share their views and exchange ideas and facts in a safe space.

In order to do so, please follow the posting rules in our site's  Terms of Service.   We've summarized some of those key rules below. Simply put, keep it civil.

Your post will be rejected if we notice that it seems to contain:

• False or intentionally out-of-context or misleading information
• Insults, profanity, incoherent, obscene or inflammatory language or threats of any kind
• Attacks on the identity of other commenters or the article's author
• Content that otherwise violates our site's  terms.

User accounts will be blocked if we notice or believe that users are engaged in:

• Continuous attempts to re-post comments that have been previously moderated/rejected
• Racist, sexist, homophobic or other discriminatory comments
• Attempts or tactics that put the site security at risk
• Actions that otherwise violate our site's  terms.

So, how can you be a power user?

• Stay on topic and share your insights
• Feel free to be clear and thoughtful to get your point across
• ‘Like’ or ‘Dislike’ to show your point of view.
• Protect your community.
• Use the report tool to alert us when someone breaks the rules.

Thanks for reading our community guidelines. Please read the full list of posting rules found in our site's  Terms of Service.

• Parenting & Family Parenting Family Pregnancy
• Courses Marriage Save My Marriage Pre Marriage
• Quizzes Relationship Quizzes Love Quizzes Couples Quiz
• Find a Therapist

9 Ways to Deal with Borderline Personality Disorder Breakups

Talented writer Owen simplifies complex topics, focusing on psychology and personal growth. He enjoys camping in scenic mountains, traveling, and embracing diverse cultures.

In This Article

Entering the challenging terrain of a relationship breakup is particularly daunting when it involves the intense emotions characteristic of Borderline Personality Disorder (BPD). 

Picture a scenario where two individuals, closely connected in a bond of intimacy, suddenly find themselves on diverging paths, with one partner experiencing the profound emotional fluctuations typical of BPD. This specific kind of separation, known as a Borderline Personality Disorder breakup, introduces unique challenges that require a thoughtful understanding and approach. 

The emotional intensity associated with BPD can significantly heighten the distress and confusion for both individuals involved, making the process of moving forward and healing a complex endeavor. This guide aims to shed light on these challenges, offering insights and strategies to effectively manage the aftermath of a BPD breakup.

What is borderline personality disorder (BPD) breakup?

   This type of breakup is notably challenging due to the heightened emotional responses and unpredictable behavior often exhibited by those with BPD. 

The core features of the disorder, such as a pervasive pattern of unstable interpersonal relationships, self-image, and affects, as well as marked impulsivity, play a significant role in how the breakup unfolds.

The term “borderline personality disorder breakup” encapsulates the unique difficulties and emotional turmoil experienced during the dissolution of such relationships, highlighting the need for specialized understanding and handling of the breakup process.

Why is a breakup with someone with BPD so difficult?

A breakup with someone who has Borderline Personality Disorder (BPD) intensifies the emotional turmoil typically associated with separations, making a borderline personality disorder breakup particularly challenging. 

Individuals with BPD often experience a profound fear of abandonment and rejection, core issues that can lead to heightened emotional responses during a breakup. This fear can trigger a range of intense reactions from the person with BPD, including anger, despair, and frantic efforts to avoid being left alone, which complicates the breakup process. 

The emotional volatility associated with BPD means that both parties may face a roller-coaster of emotions, from intense love to profound anger, making the breakup with BPD an emotionally taxing experience. Understanding and navigating these dynamics require patience, empathy, and often, professional support to manage the complex feelings involved.

What exactly does the BPD breakup look like?

A Borderline Personality Disorder (BPD) breakup is marked by intense emotional turbulence and unpredictability. 

Individuals with BPD experience profound fear of abandonment, which can lead to dramatic behaviors aimed at avoiding or reversing the breakup. This might include pleading for reconciliation, expressing intense anger, or rapidly shifting from idealizing their partner to devaluing them. 

Such actions stem from the disorder’s core characteristics, making the process exceedingly painful for both parties. The aftermath, or BPD breakup recovery, involves navigating a complex emotional landscape. 

Recovery requires patience, understanding, and often professional support to heal and move forward. The person with BPD may struggle with a heightened sense of loss and identity confusion, highlighting the need for compassionate care and strategies to manage the intense emotions associated with the breakup.

9 ways of dealing with a breakup with BPD

Navigating the aftermath of a relationship with someone who has Borderline Personality Disorder (BPD) can be uniquely challenging. The emotional intensity associated with BPD can make the breakup process particularly difficult, requiring specific strategies for coping and healing. 

This guide aims to provide insights and practical advice for those going through a BPD breakup recovery, ensuring a compassionate and understanding approach to a complex situation.

1. Seek professional support

Engaging with a mental health professional can provide both parties with the tools and strategies needed to navigate the emotional complexities of a borderline personality disorder breakup. Therapies like Dialectical Behavior Therapy (DBT) are specifically designed to help individuals with BPD manage their emotions and improve relationship skills . 

Therapy can also offer a safe space for the non-BPD partner to process their feelings and learn how to support themselves and their former partner healthily, facilitating BPD breakup recovery.

2. Establish boundaries

Setting clear and firm boundaries is crucial in managing the aftermath of a breakup, especially when considering how to break up with someone with BPD. Boundaries help define what you are comfortable with and protect your emotional well-being. 

It’s important to communicate these boundaries to your former partner and stick to them, even when it’s challenging. Boundaries might include limiting contact, specifying types of acceptable communication, or defining personal space needs.

3. Educate yourself

Understanding BPD can significantly impact how you perceive the breakup and your former partner’s actions. Education on the disorder can foster empathy, reduce frustration, and provide insight into the emotional turmoil your partner experiences, shedding light on why BPD breakups are so hard. 

Resources can include books, reputable online sources, and support groups for those affected by loved ones with BPD.

4. Practice self-care

Self-care is vital during the stressful period following a breakup, especially one complicated by BPD. Engage in activities that promote your mental, physical, and emotional health. This can include exercise, spending time with loved ones, pursuing hobbies, and ensuring you’re getting enough rest and nutrition.

5. Stay connected

Lean on your support network of friends and family during this time. Sharing your experiences and feelings with people who understand and support you can provide comfort and perspective. 

Support groups, either in-person or online, can also connect you with others who have gone through similar experiences, offering additional insights and coping strategies during a BPD breakup.

6. Avoid impulsive decisions

The heightened emotions following a BPD breakup can lead to impulsive decisions that you might later regret.

Research shows that anticipating risks is a significant deterrent in impulsive decisions taken by people.

Give yourself time to think decisions through and consider their long-term impact. This might include decisions about contacting your ex, making significant life changes, or how you express your emotions, which is a crucial aspect of navigating a borderline personality disorder breakup.

7. Communicate clearly

If communication with your former partner is necessary, strive for clarity, kindness, and honesty. Clear communication can help minimize misunderstandings and reduce the emotional intensity of interactions. 

It’s also important to listen actively and validate their feelings, even if you don’t agree with their perspective, which is key when figuring out how to break up with someone with BPD.

8. Focus on personal growth

A breakup, while challenging, can also be an opportunity for personal development. Reflect on your relationship and the breakup to understand what you can learn from the experience. 

Engage in activities that foster your growth, such as taking up new hobbies, advancing your career, or improving your physical health, which can be a silver lining after a BPD breakup.

9. Be patient

Healing from a breakup, especially one involving BPD, takes time. Allow yourself to grieve the loss of the relationship and understand that moving forward is a gradual process. 

Patience with yourself and the situation can help you navigate this challenging time with grace and resilience, which is essential for anyone going through BPD breakup recovery.

Watch this video to learn more about how patience is power:

Dealing with the complexities of relationships and breakups with someone who has Borderline Personality Disorder (BPD) can raise many questions. Here are some insights into common queries regarding BPD and relationships.

Can my ex-partner with BPD change?

Yes, your ex-partner with BPD can change with dedicated effort and professional help. Treatment options like Dialectical Behavior Therapy (DBT) have been effective in helping individuals with BPD develop healthier coping mechanisms and improve interpersonal skills. Change requires time, commitment, and the right therapeutic support.

Do people with BPD come back after a breakup?

People with BPD may attempt to rekindle relationships after a breakup due to their fear of abandonment and intense emotions. However, whether they come back varies by individual and the dynamics of the relationship. It’s crucial for both parties to consider their well-being and whether reuniting supports their mental health and growth.

Why are BPD breakups so hard?

BPD breakups are particularly challenging due to the intense emotional experiences and fear of abandonment associated with the disorder. Individuals with BPD may exhibit extreme reactions and behaviors during a breakup, making it a highly emotional and tumultuous process for both partners.

How long does it take to recover from a BPD ex?

Recovery from a relationship with a BPD ex varies greatly among individuals. It depends on the relationship’s intensity, the support system in place, and personal resilience. 

Healing is a gradual process that can be aided by therapy, self-care, and focusing on personal growth. There’s no set timeline, but progress and healing are possible with time and effort.

Final thoughts

Confronting the aftermath of a borderline personality disorder breakup requires resilience, understanding, and a commitment to personal growth. This unique challenge calls for an appreciation that healing is not a straightforward process but one filled with self-discovery and renewal. 

By adopting coping strategies, such as seeking professional guidance and setting clear boundaries, individuals can move toward emotional stability and well-being. It’s important to acknowledge that while the path may be filled with challenges, each step forward is a move towards reclaiming one’s sense of self and peace. 

In accepting this process, the experience of a borderline personality disorder breakup transforms from a period of pain to a significant milestone of profound personal change.

Share this article on

Owen Kessler is a talented writer with a knack for making complex topics easy to understand. He has a particular interest in psychology and personal growth, and his writing is known for its insightful commentary on these subjects. Read more When he’s not writing, Owen enjoys spending time camping in the beautiful mountains and forests that surround his home. He also loves to travel and has a deep appreciation for the diversity of cultures he encounters on his journeys. Read less

Want to have a happier, healthier marriage?

If you feel disconnected or frustrated about the state of your marriage but want to avoid separation and/or divorce, the marriage.com course meant for married couples is an excellent resource to help you overcome the most challenging aspects of being married.

Take Course

Learn More On This Topic

Relationship

By marriage.com editorial team, relationship & marriage advice.

Forgiveness

Approved By Mert Şeker, Psychologist

Marriage Preparation

By shellie r. warren.

Pre Marriage

You may also like.

Approved By Jenni Jacobsen, Licensed Clinical Social Worker

Save Your Marriage

Approved by angela welch, marriage & family therapist.

Approved By Jeannie Sytsma, Marriage & Family Therapist Associate

Approved By Shannon McHugh, Psychologist

Recent Articles

Mental Health

By kaida hollister.

By Callen Winslow

By Draven Porter

Popular topics on marriage help.

• International
• Today’s Paper
• Premium Stories
• Express Shorts
• Health & Wellness
• Brand Solutions

This 18-year-old diagnosed with ‘love brain’ after calling her boyfriend more than 100 times in a day

According to dr shaunak ajinkya, consultant psychiatrist, kokilaben dhirubhai ambani hospital, mumbai, love brain is a colloquial term to describe the neurophysiological changes that occur in the brain when someone experiences romantic love..

An 18-year-old woman in China, going by the alias Xiaoyu, recently landed in the hospital due to concerning behaviour towards her boyfriend. Doctors suspect borderline personality disorder might be the culprit, according to The South China Morning Post.

Local reports detail how Xiaoyu’s behaviour began during her freshman year when she allegedly developed an unhealthy dependence on her boyfriend , constantly requiring updates on his whereabouts and needing to be in frequent communication. This possessiveness ultimately strained the relationship, leaving her boyfriend feeling suffocated.

The situation reached a boiling point when Xiaoyu bombarded her boyfriend with over 100 calls in a single day, only to be met with silence. Devastated, she lashed out, damaging objects in their home. The boyfriend, fearing for her safety, alerted the authorities.

Police arrived to find Xiaoyu on the verge of jumping from their balcony. They promptly took her to the hospital, where she received a diagnosis of borderline personality disorder (BPD) , as reported by the publication.

Let’s understand more.

According to Dr Shaunak Ajinkya, consultant psychiatrist, Kokilaben Dhirubhai Ambani Hospital, Mumbai , love brain is a colloquial term to describe the neurophysiological changes that occur in the brain when someone experiences romantic love.

He explained that when you fall in love, the brain releases certain chemicals and hormones, such as dopamine, oxytocin, adrenaline, and serotonin, which can lead to a range of feelings including elation, exhilaration, excitement, affection and feelings of attachment. The neurophysiological changes that occur in the brain can happen with anyone when they experience romantic love, regardless of whether or not they have BPD.

“However, people with BPD may experience love and relationships in a different and a more extreme way than those without the disorder. They have intense, unstable relationships, difficulty trusting others, and fears of abandonment, which influences their relationships and how they experience romantic love,” Dr Ajinkya said in an interaction with  indianexpress.com

What are the warning signs and symptoms of love brain?

Dr Ajinkya explained some of the symptoms, adding that experiencing “love brain” does not mean that someone has BPD, and having BPD does not mean that someone cannot experience romantic love and related emotional upheavals.

Intense attraction: Feeling intensely drawn to someone, often characterized by infatuation, elation, and a strong desire for emotional and physical closeness.

Obsessive thoughts: Constantly thinking about the person you’re in love with, feeling preoccupied with them, and idealizing them.

Sudden changes in energy levels: F eeling extremely energetic, excited, and euphoric when thinking about or being with the person you love.

Sudden changes in mood: Experiencing mood swings, feeling elated one moment and down the next, depending on the state of relationship with the loved person.

Increased focus on the relationship to the exclusion of other routine daily activities: Spending a lot of time thinking about the relationship and the person you’re in love with, and wanting to spend as much time with them as possible.

• mental health
• relationships

Amid row over several controversial remarks, Sam Pitroda on Wednesday stepped down as the Chairman of the Indian Overseas Congress "of his own accord." His resignation was accepted by party President Mallikarjun Kharge, Congress General Secretary in-charge (Communications) Jairam Ramesh said.

UPSC Magazine

Read UPSC Magazine

More Lifestyle

Buzzing Now

May 09: Latest News

• 01 7 hours ago Bribery charges against Cognizant, L&T: FIR lodged with ACB
• 02 2 hours ago IPL 2024: SRH Head & shoulders above LSG as Aussie and Abhishek Sharma make mockery of chase
• 03 3 hours ago Maharashtra: BJP says NCP (SP), Sena UBT likely to merge with Congress
• 04 8 hours ago Bombay High Court permits 7/11 blasts case convict to give second semester LL.B exams
• 05 54 years ago GSEB HSC 12th Result 2024 Live Updates: Class 12 science, general stream results at gseb.org today
• Elections 2024
• Political Pulse
• Entertainment
• Movie Review
• Newsletters
• Web Stories