medical multiple case study

• Search Menu
• Volume 2024, Issue 4, April 2024 (In Progress)
• Volume 2024, Issue 3, March 2024
• Case of the Year
• MSF Case Reports
• Audiovestibular medicine
• Cardiology and cardiovascular systems
• Critical care medicine
• Dermatology
• Emergency medicine
• Endocrinology and metabolism
• Gastroenterology and hepatology
• Geriatrics and gerontology
• Haematology
• Infectious diseases and tropical medicine
• Medical ophthalmology
• Medical disorders in pregnancy
• Paediatrics
• Palliative medicine
• Pharmacology and pharmacy
• Radiology, nuclear medicine, and medical imaging
• Respiratory disorders
• Rheumatology
• Sexual and reproductive health
• Sports medicine
• Substance abuse
• Author Guidelines
• Submission Site
• Open Access
• Editorial Board
• Advertising and Corporate Services
• Journals Career Network
• Self-Archiving Policy
• Journals on Oxford Academic
• Books on Oxford Academic

Article Contents

Answer to part 1, answer to part 2, answer to part 3, answer to part 4, answer to part 5.

• < Previous

Educational Case: A 57-year-old man with chest pain

Contributed equally.

• Article contents
• Figures & tables
• Supplementary Data

Nikhil Aggarwal, Subothini Selvendran, Vassilios Vassiliou, Educational Case: A 57-year-old man with chest pain, Oxford Medical Case Reports , Volume 2016, Issue 4, April 2016, Pages 62–65, https://doi.org/10.1093/omcr/omw008

• Permissions Icon Permissions

This is an educational case report including multiple choice questions and their answers. For the best educational experience we recommend the interactive web version of the exercise which is available via the following link: http://www.oxfordjournals.org/our_journals/omcr/ec01p1.html

A 57 year-old male lorry driver, presented to his local emergency department with a 20-minute episode of diaphoresis and chest pain. The chest pain was central, radiating to the left arm and crushing in nature. The pain settled promptly following 300 mg aspirin orally and 800 mcg glyceryl trinitrate (GTN) spray sublingually administered by paramedics in the community. He smoked 20 cigarettes daily (38 pack years) but was not aware of any other cardiovascular risk factors. On examination he appeared comfortable and was able to complete sentences fully. There were no heart murmurs present on cardiac auscultation. Blood pressure was 180/105 mmHg, heart rate was 83 bpm and regular, oxygen saturation was 97%.

What is the most likely diagnosis?

An ECG was requested and is shown in figure 1.

How would you manage the patient? (The patient has already received 300 mg aspirin).

30 minutes later the patient's chest pain returned with greater intensity whilst waiting in the emergency department. Now, he described the pain as though “an elephant is sitting on his chest”. The nurse has already done an ECG by the time you were called to see him. This is shown in figure 2.

ECG on admission.

ECG 30 minutes after admission.

What would be the optimal management for this patient?

He was taken to the catheterization lab where the left anterior descending coronary artery (LAD) was shown to be completely occluded. Following successful percutaneous intervention and one drug eluding stent implantation in the LAD normal flow is restored (Thrombosis in myocardial infarction, TIMI = 3). 72 hours later, he is ready to be discharged home. The patient is keen to return to work and asks when he could do so.

When would you advise him that he could return to work?

One week later, he receives a letter informing him that he is required to attend cardiac rehabilitation. The patient is confused as to what cardiac rehabilitation entails, although he does remember a nurse discussing this with him briefly before he was discharged. He phones the hospital in order to get some more information.

Which of the following can be addressed during cardiac rehabilitation?

A - Acute coronary syndrome

Although the presentation could be attributable to any of the above differential diagnoses, the most likely etiology given the clinical picture and risk factors is one of cardiac ischemia. Risk factors include gender, smoking status and age making the diagnosis of acute coronary syndrome the most likely one. The broad differential diagnosis in patients presenting with chest pain has been discussed extensively in the medical literature. An old but relevant review can be found freely available 1 as well as more recent reviews. 2 , 3

C - Atorvastatin 80 mg, Clopidogrel 300 mcg, GTN 500 mcg, Ramipril 2.5 mg,

In patients with ACS, medications can be tailored to the individual patient. Some medications have symptomatic benefit but some also have prognostic benefit. Aspirin 4 , Clopidogrel 5 , Atenolol 6 and Atorvastatin 7 have been found to improve prognosis significantly. ACE inhibitors have also been found to improve left ventricular modeling and function after an MI. 8 , 9 Furthermore, GTN 10 and morphine 11 have been found to be of only significant symptomatic benefit.

Oxygen should only to be used when saturations <95% and at the lowest concentration required to keep saturations >95%. 12

There is no evidence that diltiazem, a calcium channel blocker, is of benefit. 13

His ECG in figure 1 does not fulfil ST elevation myocardial infarction (STEMI) criteria and he should therefore be managed as a Non-STEMI. He would benefit prognostically from beta-blockade however his heart rate is only 42 bpm and therefore this is contraindicated. He should receive a loading dose of clopidogrel (300 mg) followed by daily maintenance dose (75 mg). 14 , 15 He might not require GTN if he is pain-free but out of the available answers 3 is the most correct.

D - Proceed to coronary angiography

The ECG shows ST elevation in leads V2-V6 and confirms an anterolateral STEMI, which suggests a completely occluded LAD. This ECG fulfils the criteria to initiate reperfusion therapy which traditionally require one of the three to be present: According to guidance, if the patient can undergo coronary angiography within 120 minutes from the onset of chest pain, then this represents the optimal management. If it is not possible to undergo coronary angiography and potentially percutaneous intervention within 2 hours, then thrombolysis is considered an acceptable alternative. 12 , 16

≥ 1 mm of ST change in at least two contiguous limb leads (II, III, AVF, I, AVL).

≥ 2 mm of ST change in at least two contiguous chest leads (V1-V6).

New left bundle branch block.

GTN and morphine administration can be considered in parallel but they do not have a prognostic benefit.

E - Not before an exercise test

This patient is a lorry driver and therefore has a professional heavy vehicle driving license. The regulation for driving initiation in a lorry driver following a NSTEMI/ STEMI may be different in various countries and therefore the local regulations should be followed.

In the UK, a lorry driver holds a category 2 driving license. He should therefore refrain from driving a lorry for at least 6 weeks and can only return to driving if he completes successfully an exercise evaluation. An exercise evaluation is performed on a bicycle or treadmill. Drivers should be able to complete 3 stages of the standard Bruce protocol 17 or equivalent (e.g. Myocardial perfusion scan) safely, having refrained from taking anti-anginal medication for 48 hours and should remain free from signs of cardiovascular dysfunction during the test, notably: angina pectoris, syncope, hypotension, sustained ventricular tachycardia, and/or electrocardiographic ST segment shift which is considered as being indicative of myocardial ischemia (usually >2 mm horizontal or down-sloping) during exercise or the recovery period. 18

For a standard car driving license (category 1), driving can resume one week after successful intervention providing that no other revascularization is planned within 4 weeks; left ventricular ejection fraction (LVEF) is at least 40% prior to hospital discharge and there is no other disqualifying condition.

Therefore if this patent was in the UK, he could restart driving a normal car one week later assuming an echocardiogram confirmed an EF > 40%. However, he could only continue lorry driving once he has passed the required tests. 18

E - All of the above

Cardiac rehabilitation bridges the gap between hospitals and patients' homes. The cardiac rehabilitation team consists of various healthcare professions and the programme is started during hospital admission or after diagnosis. Its aim is to educate patients about their cardiac condition in order to help them adopt a healthier lifestyle. This includes educating patients' about their diet, exercise, risk factors associated with their condition such as smoking and alcohol intake and finally, about the medication recommended. There is good evidence that adherence to cardiac rehabilitation programmes improves survival and leads to a reduction in future cardiovascular events.​ 19 , 20

Oille JA . Differential diagnosis of pain in the chest . Can Med Assoc J . 1937 ; 37 (3) : 209 – 216 . http://www.ncbi.nlm.nih.gov/pmc/articles/PMC536075/ .

Google Scholar

Lee TH , Goldman L . Evaluation of the patient with acute chest pain . N Engl J Med . 2000 ; 342 (16) : 1187 – 1195 . http://www.nejm.org/doi/full/10.1056/NEJM200004203421607 .

Douglas PS , Ginsburg GS . The evaluation of chest pain in women . N Engl J Med . 1996 ; 334 (20) : 1311 – 1315 . http://www.nejm.org/doi/full/10.1056/NEJM199605163342007 .

Baigent C , Collins R , Appleby P , Parish S , Sleight P , Peto R . ISIS-2: 10 year survival among patients with suspected acute myocardial infarction in randomised comparison of intravenous streptokinase, oral aspirin, both, or neither. the ISIS-2 (second international study of infarct survival) collaborative group . BMJ . 1998 ; 316 (7141) : 1337 – 1343 . http://www.ncbi.nlm.nih.gov/pmc/articles/PMC28530/ .

Yusuf S , Zhao F , Mehta S , Chrolavicius S , Tognoni G , Fox K . Clopidogrel in unstable angina to prevent recurrent events trail investigators . effects of clopidogrel in addition to aspirin in patients with acute coronary syndromes without ST-segment elevation . N Engl J Med . 2001 ; 345 (7) : 494 – 502 . http://www.nejm.org/doi/full/10.1056/NEJMoa010746#t=articleTop .

Yusuf S , Peto R , Lewis J , Collins R , Sleight P . Beta blockade during and after myocardial infarction: An overview of the randomized trials . Prog Cardiovasc Dis . 1985 ; 27 (5) : 335 – 371 . http://www.sciencedirect.com/science/article/pii/S0033062085800037 .

Schwartz GG , Olsson AG , Ezekowitz MD et al.  . Effects of atorvastatin on early recurrent ischemic events in acute coronary syndromes: The MIRACL study: A randomized controlled trial . JAMA . 2001 ; 285 (13) : 1711 – 1718 . http://jama.jamanetwork.com/article.aspx?articleid=193709 .

Pfeffer MA , Lamas GA , Vaughan DE , Parisi AF , Braunwald E . Effect of captopril on progressive ventricular dilatation after anterior myocardial infarction . N Engl J Med . 1988 ; 319 (2) : 80 – 86 . http://content.onlinejacc.org/article.aspx?articleid=1118054 .

Sharpe N , Smith H , Murphy J , Hannan S . Treatment of patients with symptomless left ventricular dysfunction after myocardial infarction . The Lancet . 1988 ; 331 (8580) : 255 – 259 . http://www.sciencedirect.com/science/article/pii/S0140673688903479 .

Ferreira JC , Mochly-Rosen D . Nitroglycerin use in myocardial infarction patients . Circ J . 2012 ; 76 (1) : 15 – 21 . http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3527093/ .

Herlitz J , Hjalmarson A , Waagstein F . Treatment of pain in acute myocardial infarction . Br Heart J . 1989 ; 61 (1) : 9 – 13 . http://www.ncbi.nlm.nih.gov/pmc/articles/PMC1216614/ .

Task Force on the management of ST-segment elevation acute myocardial infarction of the European Society of Cardiology (ESC), Steg PG, James SK, et al . ESC guidelines for the management of acute myocardial infarction in patients presenting with ST-segment elevation . Eur Heart J . 2012 ; 33 (20) : 2569 – 2619 . http://eurheartj.oxfordjournals.org/content/33/20/2569 .

The effect of diltiazem on mortality and reinfarction after myocardial infarction . the multicenter diltiazem postinfarction trial research group . N Engl J Med . 1988 ; 319 (7) : 385 – 392 . http://www.nejm.org/doi/full/10.1056/NEJM198808183190701 .

Jneid H , Anderson JL , Wright RS et al.  . 2012 ACCF/AHA focused update of the guideline for the management of patients with unstable angina/Non–ST-elevation myocardial infarction (updating the 2007 guideline and replacing the 2011 focused update) A report of the american college of cardiology foundation/american heart association task force on practice guidelines . J Am Coll Cardiol . 2012 ; 60 (7) : 645 – 681 . http://circ.ahajournals.org/content/123/18/2022.full .

Hamm CW , Bassand JP , Agewall S et al.  . ESC guidelines for the management of acute coronary syndromes in patients presenting without persistent ST-segment elevation: The task force for the management of acute coronary syndromes (ACS) in patients presenting without persistent ST-segment elevation of the european society of cardiology (ESC) . Eur Heart J . 2011 ; 32 (23) : 2999 – 3054 . http://eurheartj.oxfordjournals.org/content/32/23/2999.long .

O'Gara PT , Kushner FG , Ascheim DD et al.  . 2013 ACCF/AHA guideline for the management of ST-elevation myocardial infarction: Executive summary: A report of the american college of cardiology foundation/american heart association task force on practice guidelines . J Am Coll Cardiol . 2013 ; 61 (4) : 485 – 510 . http://content.onlinejacc.org/article.aspx?articleid=1486115 .

BRUCE RA , LOVEJOY FW Jr . Normal respiratory and circulatory pathways of adaptation in exercise . J Clin Invest . 1949 ; 28 (6 Pt 2) : 1423 – 1430 . http://www.ncbi.nlm.nih.gov/pmc/articles/PMC439698/ .

DVLA . Https://Www.gov.uk/current-medical-guidelines-dvla-guidance-for-professionals-cardiovascular-chapter-appendix .

British Heart Foundation . Http://Www.bhf.org.uk/heart-health/living-with-heart-disease/cardiac-rehabilitation.aspx .

Kwan G , Balady GJ . Cardiac rehabilitation 2012: Advancing the field through emerging science . Circulation . 2012 ; 125 (7) : e369–73. http://circ.ahajournals.org/content/125/7/e369.full .

Author notes

• knowledge acquisition

Email alerts

Citing articles via, affiliations.

• Online ISSN 2053-8855
• Copyright © 2024 Oxford University Press
• About Oxford Academic
• Publish journals with us
• University press partners
• What we publish
• New features  
• Open access
• Institutional account management
• Rights and permissions
• Get help with access
• Accessibility
• Advertising
• Media enquiries
• Oxford University Press
• Oxford Languages
• University of Oxford

Oxford University Press is a department of the University of Oxford. It furthers the University's objective of excellence in research, scholarship, and education by publishing worldwide

• Copyright © 2024 Oxford University Press
• Cookie settings
• Cookie policy
• Privacy policy
• Legal notice

This Feature Is Available To Subscribers Only

Sign In or Create an Account

This PDF is available to Subscribers Only

For full access to this pdf, sign in to an existing account, or purchase an annual subscription.

• Open access
• Published: 27 June 2011

The case study approach

• Sarah Crowe 1 ,
• Kathrin Cresswell 2 ,
• Ann Robertson 2 ,
• Guro Huby 3 ,
• Anthony Avery 1 &
• Aziz Sheikh 2  

BMC Medical Research Methodology volume  11 , Article number:  100 ( 2011 ) Cite this article

772k Accesses

1036 Citations

37 Altmetric

Metrics details

The case study approach allows in-depth, multi-faceted explorations of complex issues in their real-life settings. The value of the case study approach is well recognised in the fields of business, law and policy, but somewhat less so in health services research. Based on our experiences of conducting several health-related case studies, we reflect on the different types of case study design, the specific research questions this approach can help answer, the data sources that tend to be used, and the particular advantages and disadvantages of employing this methodological approach. The paper concludes with key pointers to aid those designing and appraising proposals for conducting case study research, and a checklist to help readers assess the quality of case study reports.

Peer Review reports

Introduction

The case study approach is particularly useful to employ when there is a need to obtain an in-depth appreciation of an issue, event or phenomenon of interest, in its natural real-life context. Our aim in writing this piece is to provide insights into when to consider employing this approach and an overview of key methodological considerations in relation to the design, planning, analysis, interpretation and reporting of case studies.

The illustrative 'grand round', 'case report' and 'case series' have a long tradition in clinical practice and research. Presenting detailed critiques, typically of one or more patients, aims to provide insights into aspects of the clinical case and, in doing so, illustrate broader lessons that may be learnt. In research, the conceptually-related case study approach can be used, for example, to describe in detail a patient's episode of care, explore professional attitudes to and experiences of a new policy initiative or service development or more generally to 'investigate contemporary phenomena within its real-life context' [ 1 ]. Based on our experiences of conducting a range of case studies, we reflect on when to consider using this approach, discuss the key steps involved and illustrate, with examples, some of the practical challenges of attaining an in-depth understanding of a 'case' as an integrated whole. In keeping with previously published work, we acknowledge the importance of theory to underpin the design, selection, conduct and interpretation of case studies[ 2 ]. In so doing, we make passing reference to the different epistemological approaches used in case study research by key theoreticians and methodologists in this field of enquiry.

This paper is structured around the following main questions: What is a case study? What are case studies used for? How are case studies conducted? What are the potential pitfalls and how can these be avoided? We draw in particular on four of our own recently published examples of case studies (see Tables 1 , 2 , 3 and 4 ) and those of others to illustrate our discussion[ 3 – 7 ].

What is a case study?

A case study is a research approach that is used to generate an in-depth, multi-faceted understanding of a complex issue in its real-life context. It is an established research design that is used extensively in a wide variety of disciplines, particularly in the social sciences. A case study can be defined in a variety of ways (Table 5 ), the central tenet being the need to explore an event or phenomenon in depth and in its natural context. It is for this reason sometimes referred to as a "naturalistic" design; this is in contrast to an "experimental" design (such as a randomised controlled trial) in which the investigator seeks to exert control over and manipulate the variable(s) of interest.

Stake's work has been particularly influential in defining the case study approach to scientific enquiry. He has helpfully characterised three main types of case study: intrinsic , instrumental and collective [ 8 ]. An intrinsic case study is typically undertaken to learn about a unique phenomenon. The researcher should define the uniqueness of the phenomenon, which distinguishes it from all others. In contrast, the instrumental case study uses a particular case (some of which may be better than others) to gain a broader appreciation of an issue or phenomenon. The collective case study involves studying multiple cases simultaneously or sequentially in an attempt to generate a still broader appreciation of a particular issue.

These are however not necessarily mutually exclusive categories. In the first of our examples (Table 1 ), we undertook an intrinsic case study to investigate the issue of recruitment of minority ethnic people into the specific context of asthma research studies, but it developed into a instrumental case study through seeking to understand the issue of recruitment of these marginalised populations more generally, generating a number of the findings that are potentially transferable to other disease contexts[ 3 ]. In contrast, the other three examples (see Tables 2 , 3 and 4 ) employed collective case study designs to study the introduction of workforce reconfiguration in primary care, the implementation of electronic health records into hospitals, and to understand the ways in which healthcare students learn about patient safety considerations[ 4 – 6 ]. Although our study focusing on the introduction of General Practitioners with Specialist Interests (Table 2 ) was explicitly collective in design (four contrasting primary care organisations were studied), is was also instrumental in that this particular professional group was studied as an exemplar of the more general phenomenon of workforce redesign[ 4 ].

What are case studies used for?

According to Yin, case studies can be used to explain, describe or explore events or phenomena in the everyday contexts in which they occur[ 1 ]. These can, for example, help to understand and explain causal links and pathways resulting from a new policy initiative or service development (see Tables 2 and 3 , for example)[ 1 ]. In contrast to experimental designs, which seek to test a specific hypothesis through deliberately manipulating the environment (like, for example, in a randomised controlled trial giving a new drug to randomly selected individuals and then comparing outcomes with controls),[ 9 ] the case study approach lends itself well to capturing information on more explanatory ' how ', 'what' and ' why ' questions, such as ' how is the intervention being implemented and received on the ground?'. The case study approach can offer additional insights into what gaps exist in its delivery or why one implementation strategy might be chosen over another. This in turn can help develop or refine theory, as shown in our study of the teaching of patient safety in undergraduate curricula (Table 4 )[ 6 , 10 ]. Key questions to consider when selecting the most appropriate study design are whether it is desirable or indeed possible to undertake a formal experimental investigation in which individuals and/or organisations are allocated to an intervention or control arm? Or whether the wish is to obtain a more naturalistic understanding of an issue? The former is ideally studied using a controlled experimental design, whereas the latter is more appropriately studied using a case study design.

Case studies may be approached in different ways depending on the epistemological standpoint of the researcher, that is, whether they take a critical (questioning one's own and others' assumptions), interpretivist (trying to understand individual and shared social meanings) or positivist approach (orientating towards the criteria of natural sciences, such as focusing on generalisability considerations) (Table 6 ). Whilst such a schema can be conceptually helpful, it may be appropriate to draw on more than one approach in any case study, particularly in the context of conducting health services research. Doolin has, for example, noted that in the context of undertaking interpretative case studies, researchers can usefully draw on a critical, reflective perspective which seeks to take into account the wider social and political environment that has shaped the case[ 11 ].

How are case studies conducted?

Here, we focus on the main stages of research activity when planning and undertaking a case study; the crucial stages are: defining the case; selecting the case(s); collecting and analysing the data; interpreting data; and reporting the findings.

Defining the case

Carefully formulated research question(s), informed by the existing literature and a prior appreciation of the theoretical issues and setting(s), are all important in appropriately and succinctly defining the case[ 8 , 12 ]. Crucially, each case should have a pre-defined boundary which clarifies the nature and time period covered by the case study (i.e. its scope, beginning and end), the relevant social group, organisation or geographical area of interest to the investigator, the types of evidence to be collected, and the priorities for data collection and analysis (see Table 7 )[ 1 ]. A theory driven approach to defining the case may help generate knowledge that is potentially transferable to a range of clinical contexts and behaviours; using theory is also likely to result in a more informed appreciation of, for example, how and why interventions have succeeded or failed[ 13 ].

For example, in our evaluation of the introduction of electronic health records in English hospitals (Table 3 ), we defined our cases as the NHS Trusts that were receiving the new technology[ 5 ]. Our focus was on how the technology was being implemented. However, if the primary research interest had been on the social and organisational dimensions of implementation, we might have defined our case differently as a grouping of healthcare professionals (e.g. doctors and/or nurses). The precise beginning and end of the case may however prove difficult to define. Pursuing this same example, when does the process of implementation and adoption of an electronic health record system really begin or end? Such judgements will inevitably be influenced by a range of factors, including the research question, theory of interest, the scope and richness of the gathered data and the resources available to the research team.

Selecting the case(s)

The decision on how to select the case(s) to study is a very important one that merits some reflection. In an intrinsic case study, the case is selected on its own merits[ 8 ]. The case is selected not because it is representative of other cases, but because of its uniqueness, which is of genuine interest to the researchers. This was, for example, the case in our study of the recruitment of minority ethnic participants into asthma research (Table 1 ) as our earlier work had demonstrated the marginalisation of minority ethnic people with asthma, despite evidence of disproportionate asthma morbidity[ 14 , 15 ]. In another example of an intrinsic case study, Hellstrom et al.[ 16 ] studied an elderly married couple living with dementia to explore how dementia had impacted on their understanding of home, their everyday life and their relationships.

For an instrumental case study, selecting a "typical" case can work well[ 8 ]. In contrast to the intrinsic case study, the particular case which is chosen is of less importance than selecting a case that allows the researcher to investigate an issue or phenomenon. For example, in order to gain an understanding of doctors' responses to health policy initiatives, Som undertook an instrumental case study interviewing clinicians who had a range of responsibilities for clinical governance in one NHS acute hospital trust[ 17 ]. Sampling a "deviant" or "atypical" case may however prove even more informative, potentially enabling the researcher to identify causal processes, generate hypotheses and develop theory.

In collective or multiple case studies, a number of cases are carefully selected. This offers the advantage of allowing comparisons to be made across several cases and/or replication. Choosing a "typical" case may enable the findings to be generalised to theory (i.e. analytical generalisation) or to test theory by replicating the findings in a second or even a third case (i.e. replication logic)[ 1 ]. Yin suggests two or three literal replications (i.e. predicting similar results) if the theory is straightforward and five or more if the theory is more subtle. However, critics might argue that selecting 'cases' in this way is insufficiently reflexive and ill-suited to the complexities of contemporary healthcare organisations.

The selected case study site(s) should allow the research team access to the group of individuals, the organisation, the processes or whatever else constitutes the chosen unit of analysis for the study. Access is therefore a central consideration; the researcher needs to come to know the case study site(s) well and to work cooperatively with them. Selected cases need to be not only interesting but also hospitable to the inquiry [ 8 ] if they are to be informative and answer the research question(s). Case study sites may also be pre-selected for the researcher, with decisions being influenced by key stakeholders. For example, our selection of case study sites in the evaluation of the implementation and adoption of electronic health record systems (see Table 3 ) was heavily influenced by NHS Connecting for Health, the government agency that was responsible for overseeing the National Programme for Information Technology (NPfIT)[ 5 ]. This prominent stakeholder had already selected the NHS sites (through a competitive bidding process) to be early adopters of the electronic health record systems and had negotiated contracts that detailed the deployment timelines.

It is also important to consider in advance the likely burden and risks associated with participation for those who (or the site(s) which) comprise the case study. Of particular importance is the obligation for the researcher to think through the ethical implications of the study (e.g. the risk of inadvertently breaching anonymity or confidentiality) and to ensure that potential participants/participating sites are provided with sufficient information to make an informed choice about joining the study. The outcome of providing this information might be that the emotive burden associated with participation, or the organisational disruption associated with supporting the fieldwork, is considered so high that the individuals or sites decide against participation.

In our example of evaluating implementations of electronic health record systems, given the restricted number of early adopter sites available to us, we sought purposively to select a diverse range of implementation cases among those that were available[ 5 ]. We chose a mixture of teaching, non-teaching and Foundation Trust hospitals, and examples of each of the three electronic health record systems procured centrally by the NPfIT. At one recruited site, it quickly became apparent that access was problematic because of competing demands on that organisation. Recognising the importance of full access and co-operative working for generating rich data, the research team decided not to pursue work at that site and instead to focus on other recruited sites.

Collecting the data

In order to develop a thorough understanding of the case, the case study approach usually involves the collection of multiple sources of evidence, using a range of quantitative (e.g. questionnaires, audits and analysis of routinely collected healthcare data) and more commonly qualitative techniques (e.g. interviews, focus groups and observations). The use of multiple sources of data (data triangulation) has been advocated as a way of increasing the internal validity of a study (i.e. the extent to which the method is appropriate to answer the research question)[ 8 , 18 – 21 ]. An underlying assumption is that data collected in different ways should lead to similar conclusions, and approaching the same issue from different angles can help develop a holistic picture of the phenomenon (Table 2 )[ 4 ].

Brazier and colleagues used a mixed-methods case study approach to investigate the impact of a cancer care programme[ 22 ]. Here, quantitative measures were collected with questionnaires before, and five months after, the start of the intervention which did not yield any statistically significant results. Qualitative interviews with patients however helped provide an insight into potentially beneficial process-related aspects of the programme, such as greater, perceived patient involvement in care. The authors reported how this case study approach provided a number of contextual factors likely to influence the effectiveness of the intervention and which were not likely to have been obtained from quantitative methods alone.

In collective or multiple case studies, data collection needs to be flexible enough to allow a detailed description of each individual case to be developed (e.g. the nature of different cancer care programmes), before considering the emerging similarities and differences in cross-case comparisons (e.g. to explore why one programme is more effective than another). It is important that data sources from different cases are, where possible, broadly comparable for this purpose even though they may vary in nature and depth.

Analysing, interpreting and reporting case studies

Making sense and offering a coherent interpretation of the typically disparate sources of data (whether qualitative alone or together with quantitative) is far from straightforward. Repeated reviewing and sorting of the voluminous and detail-rich data are integral to the process of analysis. In collective case studies, it is helpful to analyse data relating to the individual component cases first, before making comparisons across cases. Attention needs to be paid to variations within each case and, where relevant, the relationship between different causes, effects and outcomes[ 23 ]. Data will need to be organised and coded to allow the key issues, both derived from the literature and emerging from the dataset, to be easily retrieved at a later stage. An initial coding frame can help capture these issues and can be applied systematically to the whole dataset with the aid of a qualitative data analysis software package.

The Framework approach is a practical approach, comprising of five stages (familiarisation; identifying a thematic framework; indexing; charting; mapping and interpretation) , to managing and analysing large datasets particularly if time is limited, as was the case in our study of recruitment of South Asians into asthma research (Table 1 )[ 3 , 24 ]. Theoretical frameworks may also play an important role in integrating different sources of data and examining emerging themes. For example, we drew on a socio-technical framework to help explain the connections between different elements - technology; people; and the organisational settings within which they worked - in our study of the introduction of electronic health record systems (Table 3 )[ 5 ]. Our study of patient safety in undergraduate curricula drew on an evaluation-based approach to design and analysis, which emphasised the importance of the academic, organisational and practice contexts through which students learn (Table 4 )[ 6 ].

Case study findings can have implications both for theory development and theory testing. They may establish, strengthen or weaken historical explanations of a case and, in certain circumstances, allow theoretical (as opposed to statistical) generalisation beyond the particular cases studied[ 12 ]. These theoretical lenses should not, however, constitute a strait-jacket and the cases should not be "forced to fit" the particular theoretical framework that is being employed.

When reporting findings, it is important to provide the reader with enough contextual information to understand the processes that were followed and how the conclusions were reached. In a collective case study, researchers may choose to present the findings from individual cases separately before amalgamating across cases. Care must be taken to ensure the anonymity of both case sites and individual participants (if agreed in advance) by allocating appropriate codes or withholding descriptors. In the example given in Table 3 , we decided against providing detailed information on the NHS sites and individual participants in order to avoid the risk of inadvertent disclosure of identities[ 5 , 25 ].

What are the potential pitfalls and how can these be avoided?

The case study approach is, as with all research, not without its limitations. When investigating the formal and informal ways undergraduate students learn about patient safety (Table 4 ), for example, we rapidly accumulated a large quantity of data. The volume of data, together with the time restrictions in place, impacted on the depth of analysis that was possible within the available resources. This highlights a more general point of the importance of avoiding the temptation to collect as much data as possible; adequate time also needs to be set aside for data analysis and interpretation of what are often highly complex datasets.

Case study research has sometimes been criticised for lacking scientific rigour and providing little basis for generalisation (i.e. producing findings that may be transferable to other settings)[ 1 ]. There are several ways to address these concerns, including: the use of theoretical sampling (i.e. drawing on a particular conceptual framework); respondent validation (i.e. participants checking emerging findings and the researcher's interpretation, and providing an opinion as to whether they feel these are accurate); and transparency throughout the research process (see Table 8 )[ 8 , 18 – 21 , 23 , 26 ]. Transparency can be achieved by describing in detail the steps involved in case selection, data collection, the reasons for the particular methods chosen, and the researcher's background and level of involvement (i.e. being explicit about how the researcher has influenced data collection and interpretation). Seeking potential, alternative explanations, and being explicit about how interpretations and conclusions were reached, help readers to judge the trustworthiness of the case study report. Stake provides a critique checklist for a case study report (Table 9 )[ 8 ].

Conclusions

The case study approach allows, amongst other things, critical events, interventions, policy developments and programme-based service reforms to be studied in detail in a real-life context. It should therefore be considered when an experimental design is either inappropriate to answer the research questions posed or impossible to undertake. Considering the frequency with which implementations of innovations are now taking place in healthcare settings and how well the case study approach lends itself to in-depth, complex health service research, we believe this approach should be more widely considered by researchers. Though inherently challenging, the research case study can, if carefully conceptualised and thoughtfully undertaken and reported, yield powerful insights into many important aspects of health and healthcare delivery.

Yin RK: Case study research, design and method. 2009, London: Sage Publications Ltd., 4

Google Scholar  

Keen J, Packwood T: Qualitative research; case study evaluation. BMJ. 1995, 311: 444-446.

Article   CAS   PubMed   PubMed Central   Google Scholar  

Sheikh A, Halani L, Bhopal R, Netuveli G, Partridge M, Car J, et al: Facilitating the Recruitment of Minority Ethnic People into Research: Qualitative Case Study of South Asians and Asthma. PLoS Med. 2009, 6 (10): 1-11.

Article   Google Scholar  

Pinnock H, Huby G, Powell A, Kielmann T, Price D, Williams S, et al: The process of planning, development and implementation of a General Practitioner with a Special Interest service in Primary Care Organisations in England and Wales: a comparative prospective case study. Report for the National Co-ordinating Centre for NHS Service Delivery and Organisation R&D (NCCSDO). 2008, [ http://www.sdo.nihr.ac.uk/files/project/99-final-report.pdf ]

Robertson A, Cresswell K, Takian A, Petrakaki D, Crowe S, Cornford T, et al: Prospective evaluation of the implementation and adoption of NHS Connecting for Health's national electronic health record in secondary care in England: interim findings. BMJ. 2010, 41: c4564-

Pearson P, Steven A, Howe A, Sheikh A, Ashcroft D, Smith P, the Patient Safety Education Study Group: Learning about patient safety: organisational context and culture in the education of healthcare professionals. J Health Serv Res Policy. 2010, 15: 4-10. 10.1258/jhsrp.2009.009052.

Article   PubMed   Google Scholar  

van Harten WH, Casparie TF, Fisscher OA: The evaluation of the introduction of a quality management system: a process-oriented case study in a large rehabilitation hospital. Health Policy. 2002, 60 (1): 17-37. 10.1016/S0168-8510(01)00187-7.

Stake RE: The art of case study research. 1995, London: Sage Publications Ltd.

Sheikh A, Smeeth L, Ashcroft R: Randomised controlled trials in primary care: scope and application. Br J Gen Pract. 2002, 52 (482): 746-51.

PubMed   PubMed Central   Google Scholar  

King G, Keohane R, Verba S: Designing Social Inquiry. 1996, Princeton: Princeton University Press

Doolin B: Information technology as disciplinary technology: being critical in interpretative research on information systems. Journal of Information Technology. 1998, 13: 301-311. 10.1057/jit.1998.8.

George AL, Bennett A: Case studies and theory development in the social sciences. 2005, Cambridge, MA: MIT Press

Eccles M, the Improved Clinical Effectiveness through Behavioural Research Group (ICEBeRG): Designing theoretically-informed implementation interventions. Implementation Science. 2006, 1: 1-8. 10.1186/1748-5908-1-1.

Article   PubMed Central   Google Scholar  

Netuveli G, Hurwitz B, Levy M, Fletcher M, Barnes G, Durham SR, Sheikh A: Ethnic variations in UK asthma frequency, morbidity, and health-service use: a systematic review and meta-analysis. Lancet. 2005, 365 (9456): 312-7.

Sheikh A, Panesar SS, Lasserson T, Netuveli G: Recruitment of ethnic minorities to asthma studies. Thorax. 2004, 59 (7): 634-

CAS   PubMed   PubMed Central   Google Scholar  

Hellström I, Nolan M, Lundh U: 'We do things together': A case study of 'couplehood' in dementia. Dementia. 2005, 4: 7-22. 10.1177/1471301205049188.

Som CV: Nothing seems to have changed, nothing seems to be changing and perhaps nothing will change in the NHS: doctors' response to clinical governance. International Journal of Public Sector Management. 2005, 18: 463-477. 10.1108/09513550510608903.

Lincoln Y, Guba E: Naturalistic inquiry. 1985, Newbury Park: Sage Publications

Barbour RS: Checklists for improving rigour in qualitative research: a case of the tail wagging the dog?. BMJ. 2001, 322: 1115-1117. 10.1136/bmj.322.7294.1115.

Mays N, Pope C: Qualitative research in health care: Assessing quality in qualitative research. BMJ. 2000, 320: 50-52. 10.1136/bmj.320.7226.50.

Mason J: Qualitative researching. 2002, London: Sage

Brazier A, Cooke K, Moravan V: Using Mixed Methods for Evaluating an Integrative Approach to Cancer Care: A Case Study. Integr Cancer Ther. 2008, 7: 5-17. 10.1177/1534735407313395.

Miles MB, Huberman M: Qualitative data analysis: an expanded sourcebook. 1994, CA: Sage Publications Inc., 2

Pope C, Ziebland S, Mays N: Analysing qualitative data. Qualitative research in health care. BMJ. 2000, 320: 114-116. 10.1136/bmj.320.7227.114.

Cresswell KM, Worth A, Sheikh A: Actor-Network Theory and its role in understanding the implementation of information technology developments in healthcare. BMC Med Inform Decis Mak. 2010, 10 (1): 67-10.1186/1472-6947-10-67.

Article   PubMed   PubMed Central   Google Scholar  

Malterud K: Qualitative research: standards, challenges, and guidelines. Lancet. 2001, 358: 483-488. 10.1016/S0140-6736(01)05627-6.

Article   CAS   PubMed   Google Scholar  

Yin R: Case study research: design and methods. 1994, Thousand Oaks, CA: Sage Publishing, 2

Yin R: Enhancing the quality of case studies in health services research. Health Serv Res. 1999, 34: 1209-1224.

Green J, Thorogood N: Qualitative methods for health research. 2009, Los Angeles: Sage, 2

Howcroft D, Trauth E: Handbook of Critical Information Systems Research, Theory and Application. 2005, Cheltenham, UK: Northampton, MA, USA: Edward Elgar

Book   Google Scholar  

Blakie N: Approaches to Social Enquiry. 1993, Cambridge: Polity Press

Doolin B: Power and resistance in the implementation of a medical management information system. Info Systems J. 2004, 14: 343-362. 10.1111/j.1365-2575.2004.00176.x.

Bloomfield BP, Best A: Management consultants: systems development, power and the translation of problems. Sociological Review. 1992, 40: 533-560.

Shanks G, Parr A: Positivist, single case study research in information systems: A critical analysis. Proceedings of the European Conference on Information Systems. 2003, Naples

Pre-publication history

The pre-publication history for this paper can be accessed here: http://www.biomedcentral.com/1471-2288/11/100/prepub

Download references

Acknowledgements

We are grateful to the participants and colleagues who contributed to the individual case studies that we have drawn on. This work received no direct funding, but it has been informed by projects funded by Asthma UK, the NHS Service Delivery Organisation, NHS Connecting for Health Evaluation Programme, and Patient Safety Research Portfolio. We would also like to thank the expert reviewers for their insightful and constructive feedback. Our thanks are also due to Dr. Allison Worth who commented on an earlier draft of this manuscript.

Author information

Authors and affiliations.

Division of Primary Care, The University of Nottingham, Nottingham, UK

Sarah Crowe & Anthony Avery

Centre for Population Health Sciences, The University of Edinburgh, Edinburgh, UK

Kathrin Cresswell, Ann Robertson & Aziz Sheikh

School of Health in Social Science, The University of Edinburgh, Edinburgh, UK

You can also search for this author in PubMed   Google Scholar

Corresponding author

Correspondence to Sarah Crowe .

Additional information

Competing interests.

The authors declare that they have no competing interests.

Authors' contributions

AS conceived this article. SC, KC and AR wrote this paper with GH, AA and AS all commenting on various drafts. SC and AS are guarantors.

Rights and permissions

This article is published under license to BioMed Central Ltd. This is an Open Access article distributed under the terms of the Creative Commons Attribution License ( http://creativecommons.org/licenses/by/2.0 ), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Reprints and permissions

About this article

Cite this article.

Crowe, S., Cresswell, K., Robertson, A. et al. The case study approach. BMC Med Res Methodol 11 , 100 (2011). https://doi.org/10.1186/1471-2288-11-100

Download citation

Received : 29 November 2010

Accepted : 27 June 2011

Published : 27 June 2011

DOI : https://doi.org/10.1186/1471-2288-11-100

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

• Case Study Approach
• Electronic Health Record System
• Case Study Design
• Case Study Site
• Case Study Report

BMC Medical Research Methodology

ISSN: 1471-2288

• General enquiries: [email protected]

Clinical Presentation: Case History # 1 Ms. C is a 35 year old white female. She came to Neurology Clinic for evaluation of her long-term neurologic complaints. The patient relates that for many years she had noticed some significant changes in neurologic functions, particularly heat intolerance precipitating a stumbling gait and a tendency to fall. Her visual acuity also seemed to change periodically during several years. Two months ago the patient was working very hard and was under a lot of stress. She got sick with a flu and her neurologic condition worsened. At that time, she could not hold objects in her hands, had significant tremors and severe exhaustion. She also had several bad falls. Since that time she had noticed arthralgia on the right and subsequently on the left side of her body. Then, the patient abruptly developed a right hemisensory deficit after several days of work. The MRI scan was performed at that time and revealed a multifocal white matter disease - areas of increased T2 signal in both cerebral hemispheres. Spinal tap was also done which revealed the presence of oligoclonal bands in CSF. Visual evoked response testing was abnormal with slowed conduction in optic nerves.    (Q.1)    (Q. 2)    (Q.3) Today, the patient has multiple problems related to her disease: she remains weak and numb on the right side; she has impaired urinary bladder function which requires multiple voids in the mornings, and nocturia times 3. She became incontinent and now has to wear a pad during the day.   (Q.4)   She also has persistent balance problems with some sensation of spinning, and she is extremely fatigued. REVIEW OF SYSTEMS is also significant for a number of problems related to her suspected MS. The patient has a tendency to aspirate liquids and also solids.    (Q.5)   (Q.6) She complains of tinnitus which is continuous and associated with hearing loss, more prominent on the left. She has decreased finger dexterity and weakness of the hands bilaterally. She also complains of impaired short-term memory and irritability. FAMILY HISTORY is significant for high blood pressure, cancer and heart disease in the immediate family. PERSONAL HISTORY is significant for mumps and chicken pox as a child, and anemia and allergies with hives later in life. She also had a tubal ligation. NEUROLOGIC EXAMINATION: Cranial Nerve II - disks are sharp and of normal color. Funduscopic examination is normal. Cranial Nerves III, IV, VI - no extraocular motor palsy or difficulties with smooth pursuit or saccades are seen. Remainder of the cranial nerve exam is normal except for decreased hearing on the left, and numbness in the right face, which extends down into the entire right side. The Weber test reveals greater conductance to the right. Rinne's test reveals air greater than bone bilaterally.   (Q.7) The palate elevates well. Swallow appears to be intact. Tongue movements are slowed, but tongue power appears to be intact. Motor examination reveals relatively normal strength in the upper extremities throughout. However, rapid alternating movements are decreased in both upper extremities and the patient has dysdiadochokinesia in the left hand.   (Q.8) Mild paraparesis is noted in both legs without severe spasticity. Deep tendon reflexes are +2 and symmetrical in the arms, +3 at the ankles and at the knees. Bilateral extensor toe sign are present. Sensory exam reveals paresthesia on the right to touch and decreased pin sensation on the right diffusely. The patient has mild vibratory sense loss in the distal lower extremities. Romberg's is negative.   (Q.9) Tandem gait is mildly unstable. Ambulation index is 7.0 seconds for 25 feet. (The patient takes 7.0 seconds to walk 25 feet.) Diagnosis: Multiple Sclerosis with laboratory support.   ©   John W.Rose, M.D.,   Maria Houtchens, MSIII,   Sharon G. Lynch, M.D.

• ASH Foundation
• Log in or create an account
• Publications
• Diversity Equity and Inclusion
• Global Initiatives
• Resources for Hematology Fellows
• American Society of Hematology
• Hematopoiesis Case Studies

Case Study: 55-Year-Old Male With Multiple Myeloma and Prognosis of Undetermined Significance

• Agenda for Nematology Research
• Precision Medicine
• Genome Editing and Gene Therapy
• Immunologic Treatment
• Research Support and Funding

The following case study focuses on a 55-year-old male with multiple myeloma and prognosis of undetermined significance. Test your knowledge by reading the background information below and making the proper selection.

A 55-year-old male presents to your office with new symptoms of exertional fatigue. He is otherwise well with no significant past medical history. His hemoglobin is found to be low at 10.6g/dl, with an MCV of 92. He has normal serum ferritin, vitamin B12, and folic acid levels. Absolute neutrophil count is 1.3 x 10 3 /ul and platelets 117 x 10 9 /uL. He has a creatinine of 0.9 mg/dL, calcium of 9.2 mg/dL, and albumin of 3.8 g/dL. A serum protein electrophoresis is performed that demonstrates a monoclonal IgA protein of 1.5 g/dL. A skeletal survey shows occult lytic lesions in the skull and bilateral humeri, and a bone marrow biopsy shows 30 percent involvement by abnormal appearing plasma cells, confirmed by CD138+ immunohistochemical stain.

You make a diagnosis of symptomatic multiple myeloma and review the findings and need for treatment with the patient. The patient wishes to know more about his prognosis and chances of responding to therapy. You explain that you are awaiting a few additional test results that will help you answer his question. Which result would not be considered a poor prognostic feature in this patient with newly diagnosed multiple myeloma?

• (4;14) by FISH
• Beta-2 microglobulin of 7mg/L
• t(11;14) by FISH
• Deletion 13 abnormality by standard karyotype

Explanation

Initial diagnostic work-up for patients with multiple myeloma (MM) should include both conventional karyotyping as well as fluorescence in situ hybridization (FISH) of plasma cells obtained from bone marrow aspiration. FISH should be assessed for poor-risk translocations, including t(4;14) (MMSET translocation; 75 percent of which express FGFR3), t(14;16) (MAF translocation), and deletion 17p (loss of p53). The presence of a chromosome 13 abnormality (monoallelic loss of chromosome 13 or deletion of its long arm 13q) by standard karyotype also confers a poor prognosis. However, when a chromosome 13 abnormality is detected only by FISH the significance is less clear and does not seem to confer the same poor prognosis. It has been suggested that detection of del 13 on karyotype analysis is a surrogate for the proliferative rate of the tumor clone. The t(11;14) translocation, which juxtaposes the cyclin D1 gene with the IgH promoter, is associated with a neutral to favorable prognosis in multiple myeloma. Additionally, a hyperdiploid karyotype also carries a more favorable prognosis in multiple myeloma and is a distinct biologic entity from non-hyperdiploid MM. 1-4

The International Staging System (ISS) for multiple myeloma uses β-2 microglobulin and serum albumin to divide patients into stage I, II, or III disease. A β-2 microglobulin level ≥ 5.5 mg/L would classify a patient as stage III disease, with a median survival of 29 months with conventional chemotherapy (about 80 percent of studied patients) or upfront high-dose chemotherapy and autologous stem cell transplantation (about 20 percent of studied patients). This is compared to a median survival of 62 months for those with stage I disease (β-2 microglobulin &lt; 3.5 mg/L and serum albumin ≥ 3.5 g/dL). 5 Therefore, the ISS remains a powerful and simple non-genetic model to stratify MM patients. However, it should be noted that the ISS prognostic model will need to be validated in the era of novel agents, since drugs such as bortezomib and lenalidomide may overcome the negative predictors in this model.

Currently, there is not a standard recommendation to treat poor-risk patients differently from standard-risk patients, however this is the subject of ongoing clinical studies. It is important to note though that bortezomib appears to ameliorate or eliminate the prognostic significance of these historically poor-risk features (particularly deletion 13, and translocation 4;14) and is generally recommended as part of the induction strategy in such patients. The ability of immunomodulatory drugs such as lenalidomide to overcome poor-risk features has not been as clearly shown to date. 6-8

Note: The true teaching point of this case study is that t(11;14) exists in mantle cell lymphoma and multiple myeloma, and it may identify a possibly good prognostic group.

• Fonseca R, Barlogie B, Bataille R, et al. Genetics and cytogenetics of multiple myeloma: a workshop report . Cancer Res. 2004;64:1546-1558.
• Avet-Loiseau H, Attal M, Moreau P, et al. Genetic abnormalities and survival in multiple myeloma: the experience of the Intergroupe Francophone du Myélome . Blood. 2007;109:3489-3495.
• Chng WJ, Santana-Dávila R, Van Wier SA, et al. Prognostic factors for hyperdiploid-myeloma: effects of chromosome 13 deletions and IgH translocations . Leukemia. 2006;20:807-813.
• Fonseca R, Bergsagel PL, Drach J, et al. International Myeloma Working Group molecular classification of multiple myeloma: spotlight review . Leukemia. 2009;23:2210-2221.
• Greipp PR, San Miguel J, Durie BG, et al. International staging system for multiple myeloma . J Clin Oncol. 2005;23:3412-3420.
• Jagannath S, Richardson PG, Sonneveld P, et al. Bortezomib appears to overcome the poor prognosis conferred by chromosome 13 deletion in phase 2 and 3 trials . Leukemia. 2007;21:151-157.
• San Miguel JF, Schlag R, Khuageva NK, et al. Bortezomib plus melphalan and prednisone for initial treatment of multiple myeloma . N Engl J Med. 2008;359:906-917.
• Kumar SK, Mikhael JR, Buadi FK, et al. Management of newly diagnosed symptomatic multiple myeloma: updated Mayo Stratification of Myeloma and Risk-Adapted Therapy (mSMART) consensus guidelines . Mayo Clin Proc. 2009;84:1095-1110.

Case study submitted by Nicholas Burwick, MD, Hematology/Oncology Fellow, University of Washington, Fred Hutchinson Cancer Research Center.

American Society of Hematology. (1). Case Study: 55-Year-Old Male With Multiple Myeloma and Prognosis of Undetermined Significance. Retrieved from https://www.hematology.org/education/trainees/fellows/case-studies/male-multiple-myeloma .

American Society of Hematology. "Case Study: 55-Year-Old Male With Multiple Myeloma and Prognosis of Undetermined Significance." Hematology.org. https://www.hematology.org/education/trainees/fellows/case-studies/male-multiple-myeloma (label-accessed April 28, 2024).

"American Society of Hematology." Case Study: 55-Year-Old Male With Multiple Myeloma and Prognosis of Undetermined Significance, 28 Apr. 2024 , https://www.hematology.org/education/trainees/fellows/case-studies/male-multiple-myeloma .

Citation Manager Formats

Collective Case Study

This chapter focuses on collective case study: (1) what it is, (2) what separates it from other case study formats (case study and multiple case study), and (3) how to effectively use collective case study design for research. This chapter walks researchers through the overarching components necessary in conducting research using collective case study design, providing helpful strategies and examples the authors have found useful in their own research. While highly useful in qualitative research, this chapter also notes possible challenges to using collective case study design. This chapter concludes with a list of additional resources for more in-depth explorations of the procedural elements addressed.

• Related Documents

Reality orientation programme for long-stay residents: A multiple case study design

(multiple) case study design in (special) education research, the reality of pain scoring in the emergency department: findings from a multiple case study design, mapping spontaneous facial expression in people with parkinson’s disease: a multiple case study design, an evaluation of a parent education program: multiple case study design, social media strategies for health promotion by nonprofit organizations: multiple case study design.

Background Nonprofit organizations have always played an important role in health promotion. Social media is widely used in health promotion efforts. However, there is a lack of evidence on how decisions regarding the use of social media are undertaken by nonprofit organizations that want to increase their impact in terms of health promotion. Objective The aim of this study was to understand why and how nonprofit health care organizations put forth social media strategies to achieve health promotion goals. Methods A multiple case study design, using in-depth interviews and a content analysis of each social media strategy, was employed to analyze the use of social media tools by six North American nonprofit organizations dedicated to cancer prevention and management. Results The resulting process model demonstrates how social media strategies are enacted by nonprofit organizations to achieve health promotion goals. They put forth three types of social media strategies relative to their use of existing information and communication technologies (ICT)—replicate, transform, or innovate—each affecting the content, format, and delivery of the message differently. Organizations make sense of the social media innovation in complementarity with existing ICT. Conclusions For nonprofit organizations, implementing a social media strategy can help achieve health promotion goals. The process of social media strategy implementation could benefit from understanding the rationale, the opportunities, the challenges, and the potentially complementary role of existing ICT strategies.

Retention in group-based diabetes care programs: a multiple-case study design

A multiple case-study design in education to investigate historical integrity and curriculum management in three english primary schools, researching ethics in cross-category brand alliances using a multiple case study design, efficacy of emotion-regulating improvisational music therapy to reduce depressive symptoms in young adult students: a multiple-case study design, export citation format, share document.

Relationship between medical history and multiple sclerosis: A-case-control study

Affiliations.

• 1 Student Research Committee, Mazandaran University of Medical Sciences, Sari, Iran.
• 2 Thalassemia Research Center (TRC), Hemoglobinopathy Institute, Department of Research, Faculty of Medicine, Mazandaran University of Medical Sciences, Sari, Iran.
• 3 Neurology Department, Faculty of Medicine, Mazandaran University of Medical Sciences, Sari, Iran.
• PMID: 37335649
• PMCID: PMC10256330
• DOI: 10.1097/MD.0000000000033906

This project sought to explore the potential association between medical history and the development of multiple sclerosis (MS) by conducting a retrospective study. This population-based case-control study included 200 MS cases and 2 control groups of 200 patients and healthy individuals each. Data was collected through face-to-face interviews, medical file reviews, and an electronic checklist. Multivariable analysis was used to calculate odds ratios and 95% confidence intervals to estimate the risk of each medical history on MS occurrences. Of 600 participants, 381 (63.5%) individuals were female. The mean age of the participants was 36.5 ± 11.9 years. The adjusted risks of MS were 4.40; 95% CI: 1.73 to 11.1 for measles and 4.75; 95% CI: 2.05 to 11 for amoxicillin consumption. The adjusted MS odds for autoimmune disease including 4.63; 95% CI: 0.35 to 60.6 for psoriasis and 7.15; 95% CI: 1.87 to 27.2 for myasthenia gravis. On the other hand, the calculated adjusted odds of MS occurrence were 0.14; 95% CI: 0.03 to 0.69 for seizure and 0.17; 95% CI: 0.02 to 1.49 for epilepsy. This study suggested that individuals with autoimmune diseases should be monitored more closely, as they may be at an increased risk of developing other autoimmune conditions, particularly MS.

Copyright © 2023 the Author(s). Published by Wolters Kluwer Health, Inc.

• Case-Control Studies
• Middle Aged
• Multiple Sclerosis* / epidemiology
• Myasthenia Gravis*
• Retrospective Studies
• Young Adult

• Open access
• Published: 22 April 2024

Artificial intelligence and medical education: application in classroom instruction and student assessment using a pharmacology & therapeutics case study

• Kannan Sridharan 1 &
• Reginald P. Sequeira 1  

BMC Medical Education volume  24 , Article number:  431 ( 2024 ) Cite this article

454 Accesses

1 Altmetric

Metrics details

Artificial intelligence (AI) tools are designed to create or generate content from their trained parameters using an online conversational interface. AI has opened new avenues in redefining the role boundaries of teachers and learners and has the potential to impact the teaching-learning process.

In this descriptive proof-of- concept cross-sectional study we have explored the application of three generative AI tools on drug treatment of hypertension theme to generate: (1) specific learning outcomes (SLOs); (2) test items (MCQs- A type and case cluster; SAQs; OSPE); (3) test standard-setting parameters for medical students.

Analysis of AI-generated output showed profound homology but divergence in quality and responsiveness to refining search queries. The SLOs identified key domains of antihypertensive pharmacology and therapeutics relevant to stages of the medical program, stated with appropriate action verbs as per Bloom’s taxonomy. Test items often had clinical vignettes aligned with the key domain stated in search queries. Some test items related to A-type MCQs had construction defects, multiple correct answers, and dubious appropriateness to the learner’s stage. ChatGPT generated explanations for test items, this enhancing usefulness to support self-study by learners. Integrated case-cluster items had focused clinical case description vignettes, integration across disciplines, and targeted higher levels of competencies. The response of AI tools on standard-setting varied. Individual questions for each SAQ clinical scenario were mostly open-ended. The AI-generated OSPE test items were appropriate for the learner’s stage and identified relevant pharmacotherapeutic issues. The model answers supplied for both SAQs and OSPEs can aid course instructors in planning classroom lessons, identifying suitable instructional methods, establishing rubrics for grading, and for learners as a study guide. Key lessons learnt for improving AI-generated test item quality are outlined.

Conclusions

AI tools are useful adjuncts to plan instructional methods, identify themes for test blueprinting, generate test items, and guide test standard-setting appropriate to learners’ stage in the medical program. However, experts need to review the content validity of AI-generated output. We expect AIs to influence the medical education landscape to empower learners, and to align competencies with curriculum implementation. AI literacy is an essential competency for health professionals.

Peer Review reports

Artificial intelligence (AI) has great potential to revolutionize the field of medical education from curricular conception to assessment [ 1 ]. AIs used in medical education are mostly generative AI large language models that were developed and validated based on billions to trillions of parameters [ 2 ]. AIs hold promise in the incorporation of history-taking, assessment, diagnosis, and management of various disorders [ 3 ]. While applications of AIs in undergraduate medical training are being explored, huge ethical challenges remain in terms of data collection, maintaining anonymity, consent, and ownership of the provided data [ 4 ]. AIs hold a promising role amongst learners because they can deliver a personalized learning experience by tracking their progress and providing real-time feedback, thereby enhancing their understanding in the areas they are finding difficult [ 5 ]. Consequently, a recent survey has shown that medical students have expressed their interest in acquiring competencies related to the use of AIs in healthcare during their undergraduate medical training [ 6 ].

Pharmacology and Therapeutics (P & T) is a core discipline embedded in the undergraduate medical curriculum, mostly in the pre-clerkship phase. However, the application of therapeutic principles forms one of the key learning objectives during the clerkship phase of the undergraduate medical career. Student assessment in pharmacology & therapeutics (P&T) is with test items such as multiple-choice questions (MCQs), integrated case cluster questions, short answer questions (SAQs), and objective structured practical examination (OSPE) in the undergraduate medical curriculum. It has been argued that AIs possess the ability to communicate an idea more creatively than humans [ 7 ]. It is imperative that with access to billions of trillions of datasets the AI platforms hold promise in playing a crucial role in the conception of various test items related to any of the disciplines in the undergraduate medical curriculum. Additionally, AIs provide an optimized curriculum for a program/course/topic addressing multidimensional problems [ 8 ], although robust evidence for this claim is lacking.

The existing literature has evaluated the knowledge, attitude, and perceptions of adopting AI in medical education. Integration of AIs in medical education is the need of the hour in all health professional education. However, the academic medical fraternity facing challenges in the incorporation of AIs in the medical curriculum due to factors such as inadequate grounding in data analytics, lack of high-quality firm evidence favoring the utility of AIs in medical education, and lack of funding [ 9 ]. Open-access AI platforms are available free to users without any restrictions. Hence, as a proof-of-concept, we chose to explore the utility of three AI platforms to identify specific learning objectives (SLOs) related to pharmacology discipline in the management of hypertension for medical students at different stages of their medical training.

Study design and ethics

The present study is observational, cross-sectional in design, conducted in the Department of Pharmacology & Therapeutics, College of Medicine and Medical Sciences, Arabian Gulf University, Kingdom of Bahrain, between April and August 2023. Ethical Committee approval was not sought given the nature of this study that neither had any interaction with humans, nor collection of any personal data was involved.

Study procedure

We conducted the present study in May-June 2023 with the Poe© chatbot interface created by Quora© that provides access to the following three AI platforms:

Sage Poe [ 10 ]: A generative AI search engine developed by Anthropic © that conceives a response based on the written input provided. Quora has renamed Sage Poe as Assistant © from July 2023 onwards.

Claude-Instant [ 11 ]: A retrieval-based AI search engine developed by Anthropic © that collates a response based on pre-written responses amongst the existing databases.

ChatGPT version 3.5 [ 12 ]: A generative architecture-based AI search engine developed by OpenAI © trained on large and diverse datasets.

We queried the chatbots to generate SLOs, A-type MCQs, integrated case cluster MCQs, integrated SAQs, and OSPE test items in the domain of systemic hypertension related to the P&T discipline. Separate prompts were used to generate outputs for pre-clerkship (preclinical) phase students, and at the time of graduation (before starting residency programs). Additionally, we have also evaluated the ability of these AI platforms to estimate the proportion of students correctly answering these test items. We used the following queries for each of these objectives:

Specific learning objectives

Can you generate specific learning objectives in the pharmacology discipline relevant to undergraduate medical students during their pre-clerkship phase related to anti-hypertensive drugs?

Can you generate specific learning objectives in the pharmacology discipline relevant to undergraduate medical students at the time of graduation related to anti-hypertensive drugs?

A-type MCQs

In the initial query used for A-type of item, we specified the domains (such as the mechanism of action, pharmacokinetics, adverse reactions, and indications) so that a sample of test items generated without any theme-related clutter, shown below:

Write 20 single best answer MCQs with 5 choices related to anti-hypertensive drugs for undergraduate medical students during the pre-clerkship phase of which 5 MCQs should be related to mechanism of action, 5 MCQs related to pharmacokinetics, 5 MCQs related to adverse reactions, and 5 MCQs should be related to indications.

The MCQs generated with the above search query were not based on clinical vignettes. We queried again to generate MCQs using clinical vignettes specifically because most medical schools have adopted problem-based learning (PBL) in their medical curriculum.

Write 20 single best answer MCQs with 5 choices related to anti-hypertensive drugs for undergraduate medical students during the pre-clerkship phase using a clinical vignette for each MCQ of which 5 MCQs should be related to the mechanism of action, 5 MCQs related to pharmacokinetics, 5 MCQs related to adverse reactions, and 5 MCQs should be related to indications.

We attempted to explore whether AI platforms can provide useful guidance on standard-setting. Hence, we used the following search query.

Can you do a simulation with 100 undergraduate medical students to take the above questions and let me know what percentage of students got each MCQ correct?

Integrated case cluster MCQs

Write 20 integrated case cluster MCQs with 2 questions in each cluster with 5 choices for undergraduate medical students during the pre-clerkship phase integrating pharmacology and physiology related to systemic hypertension with a case vignette.

Write 20 integrated case cluster MCQs with 2 questions in each cluster with 5 choices for undergraduate medical students during the pre-clerkship phase integrating pharmacology and physiology related to systemic hypertension with a case vignette. Please do not include ‘none of the above’ as the choice. (This modified search query was used because test items with ‘None of the above’ option were generated with the previous search query).

Write 20 integrated case cluster MCQs with 2 questions in each cluster with 5 choices for undergraduate medical students at the time of graduation integrating pharmacology and physiology related to systemic hypertension with a case vignette.

Integrated short answer questions

Write a short answer question scenario with difficult questions based on the theme of a newly diagnosed hypertensive patient for undergraduate medical students with the main objectives related to the physiology of blood pressure regulation, risk factors for systemic hypertension, pathophysiology of systemic hypertension, pathological changes in the systemic blood vessels in hypertension, pharmacological management, and non-pharmacological treatment of systemic hypertension.

Write a short answer question scenario with moderately difficult questions based on the theme of a newly diagnosed hypertensive patient for undergraduate medical students with the main objectives related to the physiology of blood pressure regulation, risk factors for systemic hypertension, pathophysiology of systemic hypertension, pathological changes in the systemic blood vessels in hypertension, pharmacological management, and non-pharmacological treatment of systemic hypertension.

Write a short answer question scenario with questions based on the theme of a newly diagnosed hypertensive patient for undergraduate medical students at the time of graduation with the main objectives related to the physiology of blood pressure regulation, risk factors for systemic hypertension, pathophysiology of systemic hypertension, pathological changes in the systemic blood vessels in hypertension, pharmacological management, and non-pharmacological treatment of systemic hypertension.

Can you generate 5 OSPE pharmacology and therapeutics prescription writing exercises for the assessment of undergraduate medical students at the time of graduation related to anti-hypertensive drugs?

Can you generate 5 OSPE pharmacology and therapeutics prescription writing exercises containing appropriate instructions for the patients for the assessment of undergraduate medical students during their pre-clerkship phase related to anti-hypertensive drugs?

Can you generate 5 OSPE pharmacology and therapeutics prescription writing exercises containing appropriate instructions for the patients for the assessment of undergraduate medical students at the time of graduation related to anti-hypertensive drugs?

Both authors independently evaluated the AI-generated outputs, and a consensus was reached. We cross-checked the veracity of answers suggested by AIs as per the Joint National Commission Guidelines (JNC-8) and Goodman and Gilman’s The Pharmacological Basis of Therapeutics (2023), a reference textbook [ 13 , 14 ]. Errors in the A-type MCQs were categorized as item construction defects, multiple correct answers, and uncertain appropriateness to the learner’s level. Test items in the integrated case cluster MCQs, SAQs and OSPEs were evaluated with the Preliminary Conceptual Framework for Establishing Content Validity of AI-Generated Test Items based on the following domains: technical accuracy, comprehensiveness, education level, and lack of construction defects (Table  1 ). The responses were categorized as complete and deficient for each domain.

The pre-clerkship phase SLOs identified by Sage Poe, Claude-Instant, and ChatGPT are listed in the electronic supplementary materials 1 – 3 , respectively. In general, a broad homology in SLOs generated by the three AI platforms was observed. All AI platforms identified appropriate action verbs as per Bloom’s taxonomy to state the SLO; action verbs such as describe, explain, recognize, discuss, identify, recommend, and interpret are used to state the learning outcome. The specific, measurable, achievable, relevant, time-bound (SMART) SLOs generated by each AI platform slightly varied. All key domains of antihypertensive pharmacology to be achieved during the pre-clerkship (pre-clinical) years were relevant for graduating doctors. The SLOs addressed current JNC Treatment Guidelines recommended classes of antihypertensive drugs, the mechanism of action, pharmacokinetics, adverse effects, indications/contraindications, dosage adjustments, monitoring therapy, and principles of monotherapy and combination therapy.

The SLOs to be achieved by undergraduate medical students at the time of graduation identified by Sage Poe, Claude-Instant, and ChatGPT listed in electronic supplementary materials 4 – 6 , respectively. The identified SLOs emphasize the application of pharmacology knowledge within a clinical context, focusing on competencies needed to function independently in early residency stages. These SLOs go beyond knowledge recall and mechanisms of action to encompass competencies related to clinical problem-solving, rational prescribing, and holistic patient management. The SLOs generated require higher cognitive ability of the learner: action verbs such as demonstrate, apply, evaluate, analyze, develop, justify, recommend, interpret, manage, adjust, educate, refer, design, initiate & titrate were frequently used.

The MCQs for the pre-clerkship phase identified by Sage Poe, Claude-Instant, and ChatGPT listed in the electronic supplementary materials 7 – 9 , respectively, and those identified with the search query based on the clinical vignette in electronic supplementary materials ( 10 – 12 ).

All MCQs generated by the AIs in each of the four domains specified [mechanism of action (MOA); pharmacokinetics; adverse drug reactions (ADRs), and indications for antihypertensive drugs] are quality test items with potential content validity. The test items on MOA generated by Sage Poe included themes such as renin-angiotensin-aldosterone (RAAS) system, beta-adrenergic blockers (BB), calcium channel blockers (CCB), potassium channel openers, and centrally acting antihypertensives; on pharmacokinetics included high oral bioavailability/metabolism in liver [angiotensin receptor blocker (ARB)-losartan], long half-life and renal elimination [angiotensin converting enzyme inhibitors (ACEI)-lisinopril], metabolism by both liver and kidney (beta-blocker (BB)-metoprolol], rapid onset- short duration of action (direct vasodilator-hydralazine), and long-acting transdermal drug delivery (centrally acting-clonidine). Regarding the ADR theme, dry cough, angioedema, and hyperkalemia by ACEIs in susceptible patients, reflex tachycardia by CCB/amlodipine, and orthostatic hypotension by CCB/verapamil addressed. Clinical indications included the drug of choice for hypertensive patients with concomitant comorbidity such as diabetics (ACEI-lisinopril), heart failure and low ejection fraction (BB-carvedilol), hypertensive urgency/emergency (alpha cum beta receptor blocker-labetalol), stroke in patients with history recurrent stroke or transient ischemic attack (ARB-losartan), and preeclampsia (methyldopa).

Almost similar themes under each domain were identified by the Claude-Instant AI platform with few notable exceptions: hydrochlorothiazide (instead of clonidine) in MOA and pharmacokinetics domains, respectively; under the ADR domain ankle edema/ amlodipine, sexual dysfunction and fatigue in male due to alpha-1 receptor blocker; under clinical indications the best initial monotherapy for clinical scenarios such as a 55-year old male with Stage-2 hypertension; a 75-year-old man Stage 1 hypertension; a 35-year-old man with Stage I hypertension working on night shifts; and a 40-year-old man with stage 1 hypertension and hyperlipidemia.

As with Claude-Instant AI, ChatGPT-generated test items on MOA were mostly similar. However, under the pharmacokinetic domain, immediate- and extended-release metoprolol, the effect of food to enhance the oral bioavailability of ramipril, and the highest oral bioavailability of amlodipine compared to other commonly used antihypertensives were the themes identified. Whereas the other ADR themes remained similar, constipation due to verapamil was a new theme addressed. Notably, in this test item, amlodipine was an option that increased the difficulty of this test item because amlodipine therapy is also associated with constipation, albeit to a lesser extent, compared to verapamil. In the clinical indication domain, the case description asking “most commonly used in the treatment of hypertension and heart failure” is controversial because the options listed included losartan, ramipril, and hydrochlorothiazide but the suggested correct answer was ramipril. This is a good example to stress the importance of vetting the AI-generated MCQ by experts for content validity and to assure robust psychometrics. The MCQ on the most used drug in the treatment of “hypertension and diabetic nephropathy” is more explicit as opposed to “hypertension and diabetes” by Claude-Instant because the therapeutic concept of reducing or delaying nephropathy must be distinguished from prevention of nephropathy, although either an ACEI or ARB is the drug of choice for both indications.

It is important to align student assessment to the curriculum; in the PBL curriculum, MCQs with a clinical vignette are preferred. The modification of the query specifying the search to generate MCQs with a clinical vignette on domains specified previously gave appropriate output by all three AI platforms evaluated (Sage Poe; Claude- Instant; Chat GPT). The scenarios generated had a good clinical fidelity and educational fit for the pre-clerkship student perspective.

The errors observed with AI outputs on the A-type MCQs are summarized in Table  2 . No significant pattern was observed except that Claude-Instant© generated test items in a stereotyped format such as the same choices for all test items related to pharmacokinetics and indications, and all the test items in the ADR domain are linked to the mechanisms of action of drugs. This illustrates the importance of reviewing AI-generated test items by content experts for content validity to ensure alignment with evidence-based medicine and up-to-date treatment guidelines.

The test items generated by ChatGPT had the advantage of explanations supplied rendering these more useful for learners to support self-study. The following examples illustrate this assertion: “ A patient with hypertension is started on a medication that works by blocking beta-1 receptors in the heart (metoprolol)”. Metoprolol is a beta blocker that works by blocking beta-1 receptors in the heart, which reduces heart rate and cardiac output, resulting in a decrease in blood pressure. However, this explanation is incomplete because there is no mention of other less important mechanisms, of beta receptor blockers on renin release. Also, these MCQs were mostly recall type: Which of the following medications is known to have a significant first-pass effect? The explanation reads: propranolol is known to have a significant first pass-effect, meaning that a large portion of the drug is metabolized by the liver before it reaches systemic circulation. Losartan, amlodipine, ramipril, and hydrochlorothiazide do not have significant first-pass effect. However, it is also important to extend the explanation further by stating that the first-pass effect of propranolol does not lead to total loss of pharmacological activity because the metabolite hydroxy propranolol also has potent beta-blocking activity. Another MCQ test item had a construction defect: “A patient with hypertension is started on a medication that can cause photosensitivity. Which of the following medications is most likely responsible?” Options included: losartan, amlodipine, ramipril, hydrochlorothiazide, hydrochlorothiazide/triamterene. The explanation states that hydrochlorothiazide (HCTZ) can cause photosensitivity, which is increased sensitivity to sunlight that can cause skin rashes and sunburns. Losartan, amlodipine, ramipril, and HCTZ/triamterene are less likely to cause photosensitivity. However, it is irrational to claim that HCTZ/triamterene, one of the wrong options, is less likely to cause photosensitivity. The difficulty index of such test items is likely unacceptable in high-stake tests to make equitable psychometric decisions.

The responses from Sage Poe, Claude-Instant, and ChatGPT on guidance for standard-setting methods are listed in the electronic supplementary materials 13 – 15 . Sage Poe offered this information with the caveat that “the results of this simulation were purely hypothetical and do not reflect the actual performance of any real students”. The simulation estimates of examinees correctly answering test items ranged from 60 to 90% for the mechanism of action, 65–85% for pharmacokinetics, 60–80% for adverse reactions, and 75–90% for clinical indications of antihypertensives.

In contrast, Claude-Instant admitted that “Performing a full simulation with 100 medical students is beyond the scope of what I can do as an AI assistant. I can generate sample MCQ questions and answers, but I do not have access to a population of medical students to administer the questions. A true simulation that administers questions to real students and analyzes the results would require access to a database of medical students, a platform to deliver the questions, and code to analyze the responses. As an AI assistant, I lack these capabilities. While I cannot perform a full simulation, here are some considerations for administering MCQ questions to medical students: provide details on the purpose and instructions for the test to ensure students understand what is expected out of them; consider including some easier questions in addition to more challenging ones to boost students’ confidence and motivation; avoid ambiguous wording and ensure each question has only one unambiguously correct answer option; when analyzing results, look for questions factors that may have impacted performance, like unclear wording or answer options that are too similar. Focusing on weak questions can help improve future tests; compare performance across different student groups to identify areas where more teaching may be needed; provide detailed answer explanations and review sessions after the test to help students learn from any errors and reinforce correct concepts”. However, ChatGPT offered the simulation result estimates for the 20 MCQ on antihypertensive drugs: mechanism of action ranged from 67 to 92%, pharmacokinetics 63–86%, adverse effects 65–82%, and clinical indications 64–89%. Furthermore, it also stated that “Overall, the performance of the students was quite good, with most questions having a response rate of over 70%. However, there were some questions where the projected correct response rate was rather low, such as Question #5 (Mechanism of Action of Hydrochlorothiazide; see Electronic Supplementary Material 12 ) and Question 18 (Indications for Verapamil; see Electronic Supplementary Material 10 ). This may suggest areas where students need more focused education or review.”

We asked AI assistants to generate 20 integrated case cluster MCQs with 2 test items in each cluster with five options for undergraduate medical students in the pre-clerkship phase integrating pharmacology and physiology related to systemic hypertension with a case vignette and the responses by Sage Poe, Claude-Instant, and ChatGPT are listed in the electronic supplementary materials ( 16 – 18 ). In all instances, the test items generated had focused case descriptions in the form of a clinical vignette, and horizontal integration across the pathophysiology of hypertension and pharmacology of antihypertensive drugs. These test items mostly targeted the ‘knows (knowledge)’ or ‘knows how (competence)’ level on Miller’s pyramid and are suitable for assessing the clinical competence of pre-clerkship medical students, especially in an integrated PBL curriculum. Both the AI assistants generated excellent clinical vignettes and themes; however, most of the cluster MCQs by ChatGPT had “None of the above” as an option, which is often considered a test item construction flaw. Notwithstanding these limitations, case cluster integrated test items are valuable for learners to integrate their knowledge of different basic medical sciences and their application to clinical sciences. This integrated approach can be used for both instructional and student assessment purposes to make the course more meaningful. Indeed, one of the basic tenets of PBL is curriculum integration.

In the next query, we asked AI assistants to write integrated case cluster MCQs with 2 test items in each cluster with 5 options for undergraduate medical students at the time of graduation integrating pharmacology and physiology of hypertension with a case vignette. The responses are listed in the electronic supplementary materials 19 – 21 . Claude-Instant has provided only partial responses to both the queries. Overall, the information provided in case vignettes requires the learner to interpret the clinical information and make therapeutic decisions. Such test items are appropriate for assessing the minimum competency of medical school graduates to start internship or residency programs; these MCQs are generally comparable to test items used in USMLE Part 2. The evaluation of the integrated case cluster test items provided by all the AI platforms is summarized in Table  3 . In general, the AI outputs had at least one construction defect, and did not include all the core sub-topics to a sufficient degree.

When asked to simulate the above-generated test items to 100 undergraduate medical students at the time of graduation and provide a percentage of students who are likely to correctly answer each item, the AI assistant responded:

“ As an AI language model, I cannot simulate the responses of 100 undergraduate medical students likely to obtain the correct answer for each question. However, I can provide some general information about the difficulty level of each question based on the complexity of the concepts being tested and the level of integration between pharmacology and physiology ”.

AI assistant went on to clarify that questions that require knowledge of basic pharmacology principles, such as the mechanism of action of specific drugs, are likely to be easier for students to answer correctly. Test items that require an understanding of the physiological mechanisms underlying hypertension and correlating with symptoms are likely to be more challenging for students. The AI assistant sorted these test items into two categories accordingly. Overall, the difficulty level of the test item is based on the level of integration between pharmacology and pathophysiology. Test items that require an understanding of both pharmacological and physiological mechanisms are likely to be more challenging for students requiring a strong foundation in both pharmacology and physiology concepts to be able to correctly answer integrated case-cluster MCQs.

Short answer questions

The responses to a search query on generating SAQs appropriate to the pre-clerkship phase Sage Poe, Claude-Instant, and ChatGPT generated items are listed in the electronic supplementary materials 22 – 24 for difficult questions and 25–27 for moderately difficult questions.

It is apparent from these case vignette descriptions that the short answer question format varied. Accordingly, the scope for asking individual questions for each scenario is open-ended. In all instances, model answers are supplied which are helpful for the course instructor to plan classroom lessons, identify appropriate instructional methods, and establish rubrics for grading the answer scripts, and as a study guide for students.

We then wanted to see to what extent AI can differentiate the difficulty of the SAQ by replacing the search term “difficult” with “moderately difficult” in the above search prompt: the changes in the revised case scenarios are substantial. Perhaps the context of learning and practice (and the level of the student in the MD/medical program) may determine the difficulty level of SAQ generated. It is worth noting that on changing the search from cardiology to internal medicine rotation in Sage Poe the case description also changed. Thus, it is essential to select an appropriate AI assistant, perhaps by trial and error, to generate quality SAQs. Most of the individual questions tested stand-alone knowledge and did not require students to demonstrate integration.

The responses of Sage Poe, Claude-Instant, and ChatGPT for the search query to generate SAQs at the time of graduation are listed in the electronic supplementary materials 28 – 30 . It is interesting to note how AI assistants considered the stage of the learner while generating the SAQ. The response by Sage Poe is illustrative for comparison. “You are a newly graduated medical student who is working in a hospital” versus “You are a medical student in your pre-clerkship.”

Some questions were retained, deleted, or modified to align with competency appropriate to the context (Electronic Supplementary Materials 28 – 30 ). Overall, the test items at both levels from all AI platforms were technically accurate and thorough addressing the topics related to different disciplines (Table  3 ). The differences in learning objective transition are summarized in Table  4 . A comparison of learning objectives revealed that almost all objectives remained the same except for a few (Table  5 ).

A similar trend was apparent with test items generated by other AI assistants, such as ChatGPT. The contrasting differences in questions are illustrated by the vertical integration of basic sciences and clinical sciences (Table  6 ).

Taken together, these in-depth qualitative comparisons suggest that AI assistants such as Sage Poe and ChatGPT consider the learner’s stage of training in designing test items, learning outcomes, and answers expected from the examinee. It is critical to state the search query explicitly to generate quality output by AI assistants.

The OSPE test items generated by Claude-Instant and ChatGPT appropriate to the pre-clerkship phase (without mentioning “appropriate instructions for the patients”) are listed in the electronic supplementary materials 31 and 32 and with patient instructions on the electronic supplementary materials 33 and 34 . For reasons unknown, Sage Poe did not provide any response to this search query.

The five OSPE items generated were suitable to assess the prescription writing competency of pre-clerkship medical students. The clinical scenarios identified by the three AI platforms were comparable; these scenarios include patients with hypertension and impaired glucose tolerance in a 65-year-old male, hypertension with chronic kidney disease (CKD) in a 55-year-old woman, resistant hypertension with obstructive sleep apnea in a 45-year-old man, and gestational hypertension at 32 weeks in a 35-year-old (Claude-Instant AI). Incorporating appropriate instructions facilitates the learner’s ability to educate patients and maximize safe and effective therapy. The OSPE item required students to write a prescription with guidance to start conservatively, choose an appropriate antihypertensive drug class (drug) based on the patients’ profile, specifying drug name, dose, dosing frequency, drug quantity to be dispensed, patient name, date, refill, and caution as appropriate, in addition to prescribers’ name, signature, and license number. In contrast, ChatGPT identified clinical scenarios to include patients with hypertension and CKD, hypertension and bronchial asthma, gestational diabetes, hypertension and heart failure, and hypertension and gout (ChatGPT). Guidance for dosage titration, warnings to be aware, safety monitoring, and frequency of follow-up and dose adjustment. These test items are designed to assess learners’ knowledge of P & T of antihypertensives, as well as their ability to provide appropriate instructions to patients. These clinical scenarios for writing prescriptions assess students’ ability to choose an appropriate drug class, write prescriptions with proper labeling and dosing, reflect drug safety profiles, and risk factors, and make modifications to meet the requirements of special populations. The prescription is required to state the drug name, dose, dosing frequency, patient name, date, refills, and cautions or instructions as needed. A conservative starting dose, once or twice daily dosing frequency based on the drug, and instructions to titrate the dose slowly if required.

The responses from Claude-Instant and ChatGPT for the search query related to generating OSPE test items at the time of graduation are listed in electronic supplementary materials 35 and 36 . In contrast to the pre-clerkship phase, OSPEs generated for graduating doctors’ competence assessed more advanced drug therapy comprehension. For example, writing a prescription for:

(1) A 65-year- old male with resistant hypertension and CKD stage 3 to optimize antihypertensive regimen required the answer to include starting ACEI and diuretic, titrating the dosage over two weeks, considering adding spironolactone or substituting ACEI with an ARB, and need to closely monitor serum electrolytes and kidney function closely.

(2) A 55-year-old woman with hypertension and paroxysmal arrhythmia required the answer to include switching ACEI to ARB due to cough, adding a CCB or beta blocker for rate control needs, and adjusting the dosage slowly and monitoring for side effects.

(3) A 45-year-old man with masked hypertension and obstructive sleep apnea require adding a centrally acting antihypertensive at bedtime and increasing dosage as needed based on home blood pressure monitoring and refer to CPAP if not already using one.

(4) A 75-year-old woman with isolated systolic hypertension and autonomic dysfunction to require stopping diuretic and switching to an alpha blocker, upward dosage adjustment and combining with other antihypertensives as needed based on postural blood pressure changes and symptoms.

(5) A 35-year-old pregnant woman with preeclampsia at 29 weeks require doubling methyldopa dose and consider adding labetalol or nifedipine based on severity and educate on signs of worsening and to follow-up immediately for any concerning symptoms.

These case scenarios are designed to assess the ability of the learner to comprehend the complexity of antihypertensive regimens, make evidence-based regimen adjustments, prescribe multidrug combinations based on therapeutic response and tolerability, monitor complex patients for complications, and educate patients about warning signs and follow-up.

A similar output was provided by ChatGPT, with clinical scenarios such as prescribing for patients with hypertension and myocardial infarction; hypertension and chronic obstructive pulmonary airway disease (COPD); hypertension and a history of angina; hypertension and a history of stroke, and hypertension and advanced renal failure. In these cases, wherever appropriate, pharmacotherapeutic issues like taking ramipril after food to reduce side effects such as giddiness; selection of the most appropriate beta-blocker such as nebivolol in patients with COPD comorbidity; the importance of taking amlodipine at the same time every day with or without food; preference for telmisartan among other ARBs in stroke; choosing furosemide in patients with hypertension and edema and taking the medication with food to reduce the risk of gastrointestinal adverse effect are stressed.

The AI outputs on OSPE test times were observed to be technically accurate, thorough in addressing core sub-topics suitable for the learner’s level and did not have any construction defects (Table  3 ). Both AIs provided the model answers with explanatory notes. This facilitates the use of such OSPEs for self-assessment by learners for formative assessment purposes. The detailed instructions are helpful in creating optimized therapy regimens, and designing evidence-based regimens, to provide appropriate instructions to patients with complex medical histories. One can rely on multiple AI sources to identify, shortlist required case scenarios, and OSPE items, and seek guidance on expected model answers with explanations. The model answer guidance for antihypertensive drug classes is more appropriate (rather than a specific drug of a given class) from a teaching/learning perspective. We believe that these scenarios can be refined further by providing a focused case history along with relevant clinical and laboratory data to enhance clinical fidelity and bring a closer fit to the competency framework.

In the present study, AI tools have generated SLOs that comply with the current principles of medical education [ 15 ]. AI tools are valuable in constructing SLOs and so are especially useful for medical fraternities where training in medical education is perceived as inadequate, more so in the early stages of their academic career. Data suggests that only a third of academics in medical schools have formal training in medical education [ 16 ] which is a limitation. Thus, the credibility of alternatives, such as the AIs, is evaluated to generate appropriate course learning outcomes.

We observed that the AI platforms in the present study generated quality test items suitable for different types of assessment purposes. The AI-generated outputs were similar with minor variation. We have used generative AIs in the present study that could generate new content from their training dataset [ 17 ]. Problem-based and interactive learning approaches are referred to as “bottom-up” where learners obtain first-hand experience in solving the cases first and then indulge in discussion with the educators to refine their understanding and critical thinking skills [ 18 ]. We suggest that AI tools can be useful for this approach for imparting the core knowledge and skills related to Pharmacology and Therapeutics to undergraduate medical students. A recent scoping review evaluating the barriers to writing quality test items based on 13 studies has concluded that motivation, time constraints, and scheduling were the most common [ 19 ]. AI tools can be valuable considering the quick generation of quality test items and time management. However, as observed in the present study, the AI-generated test items nevertheless require scrutiny by faculty members for content validity. Moreover, it is important to train faculty in AI technology-assisted teaching and learning. The General Medical Council recommends taking every opportunity to raise the profile of teaching in medical schools [ 20 ]. Hence, both the academic faculty and the institution must consider investing resources in AI training to ensure appropriate use of the technology [ 21 ].

The AI outputs assessed in the present study had errors, particularly with A-type MCQs. One notable observation was that often the AI tools were unable to differentiate the differences between ACEIs and ARBs. AI platforms access several structured and unstructured data, in addition to images, audio, and videos. Hence, the AI platforms can commit errors due to extracting details from unauthenticated sources [ 22 ] created a framework identifying 28 factors for reconstructing the path of AI failures and for determining corrective actions. This is an area of interest for AI technical experts to explore. Also, this further iterates the need for human examination of test items before using them for assessment purposes.

There are concerns that AIs can memorize and provide answers from their training dataset, which they are not supposed to do [ 23 ]. Hence, the use of AIs-generated test items for summative examinations is debatable. It is essential to ensure and enhance the security features of AI tools to reduce or eliminate cross-contamination of test items. Researchers have emphasized that AI tools will only reach their potential if developers and users can access full-text non-PDF formats that help machines comprehend research papers and generate the output [ 24 ].

AI platforms may not always have access to all standard treatment guidelines. However, in the present study, it was observed that all three AI platforms generally provided appropriate test items regarding the choice of medications, aligning with recommendations from contemporary guidelines and standard textbooks in pharmacology and therapeutics. The prompts used in the study were specifically focused on the pre-clerkship phase of the undergraduate medical curriculum (and at the time of their graduation) and assessed fundamental core concepts, which were also reflected in the AI outputs. Additionally, the recommended first-line antihypertensive drug classes have been established for several decades, and information regarding their pharmacokinetics, ADRs, and indications is well-documented in the literature.

Different paradigms and learning theories have been proposed to support AI in education. These paradigms include AI- directed (learner as recipient), AI-supported (learner as collaborator), and AI-empowered (learner as leader) that are based on Behaviorism, Cognitive-Social constructivism, and Connectivism-Complex adaptive systems, respectively [ 25 ]. AI techniques have potential to stimulate and advance instructional and learning sciences. More recently a three- level model that synthesizes and unifies existing learning theories to model the roles of AIs in promoting learning process has been proposed [ 26 ]. The different components of our study rely upon these paradigms and learning theories as the theoretical underpinning.

Strengths and limitations

To the best of our knowledge, this is the first study evaluating the utility of AI platforms in generating test items related to a discipline in the undergraduate medical curriculum. We have evaluated the AI’s ability to generate outputs related to most types of assessment in the undergraduate medical curriculum. The key lessons learnt for improving the AI-generated test item quality from the present study are outlined in Table  7 . We used a structured framework for assessing the content validity of the test items. However, we have demonstrated using a single case study (hypertension) as a pilot experiment. We chose to evaluate anti-hypertensive drugs as it is a core learning objective and one of the most common disorders relevant to undergraduate medical curricula worldwide. It would be interesting to explore the output from AI platforms for other common (and uncommon/region-specific) disorders, non-/semi-core objectives, and disciplines other than Pharmacology and Therapeutics. An area of interest would be to look at the content validity of the test items generated for different curricula (such as problem-based, integrated, case-based, and competency-based) during different stages of the learning process. Also, we did not attempt to evaluate the generation of flowcharts, algorithms, or figures for generating test items. Another potential area for exploring the utility of AIs in medical education would be repeated procedural practices such as the administration of drugs through different routes by trainee residents [ 27 ]. Several AI tools have been identified for potential application in enhancing classroom instructions and assessment purposes pending validation in prospective studies [ 28 ]. Lastly, we did not administer the AI-generated test items to students and assessed their performance and so could not comment on the validity of test item discrimination and difficulty indices. Additionally, there is a need to confirm the generalizability of the findings to other complex areas in the same discipline as well as in other disciplines that pave way for future studies. The conceptual framework used in the present study for evaluating the AI-generated test items needs to be validated in a larger population. Future studies may also try to evaluate the variations in the AI outputs with repetition of the same queries.

Notwithstanding ongoing discussions and controversies, AI tools are potentially useful adjuncts to optimize instructional methods, test blueprinting, test item generation, and guidance for test standard-setting appropriate to learners’ stage in the medical program. However, experts need to critically review the content validity of AI-generated output. These challenges and caveats are to be addressed before the use of widespread use of AIs in medical education can be advocated.

Data availability

All the data included in this study are provided as Electronic Supplementary Materials.

Tolsgaard MG, Pusic MV, Sebok-Syer SS, Gin B, Svendsen MB, Syer MD, Brydges R, Cuddy MM, Boscardin CK. The fundamentals of Artificial Intelligence in medical education research: AMEE Guide 156. Med Teach. 2023;45(6):565–73.

Article   Google Scholar  

Sriwastwa A, Ravi P, Emmert A, Chokshi S, Kondor S, Dhal K, Patel P, Chepelev LL, Rybicki FJ, Gupta R. Generative AI for medical 3D printing: a comparison of ChatGPT outputs to reference standard education. 3D Print Med. 2023;9(1):21.

Azer SA, Guerrero APS. The challenges imposed by artificial intelligence: are we ready in medical education? BMC Med Educ. 2023;23(1):680.

Masters K. Ethical use of Artificial Intelligence in Health Professions Education: AMEE Guide 158. Med Teach. 2023;45(6):574–84.

Nagi F, Salih R, Alzubaidi M, Shah H, Alam T, Shah Z, Househ M. Applications of Artificial Intelligence (AI) in Medical Education: a scoping review. Stud Health Technol Inf. 2023;305:648–51.

Google Scholar  

Mehta N, Harish V, Bilimoria K, et al. Knowledge and attitudes on artificial intelligence in healthcare: a provincial survey study of medical students. MedEdPublish. 2021;10(1):75.

Mir MM, Mir GM, Raina NT, Mir SM, Mir SM, Miskeen E, Alharthi MH, Alamri MMS. Application of Artificial Intelligence in Medical Education: current scenario and future perspectives. J Adv Med Educ Prof. 2023;11(3):133–40.

Garg T. Artificial Intelligence in Medical Education. Am J Med. 2020;133(2):e68.

Matheny ME, Whicher D, Thadaney IS. Artificial intelligence in health care: a report from the National Academy of Medicine. JAMA. 2020;323(6):509–10.

Sage Poe. Available at: https://poe.com/Assistant (Accessed on. 3rd June 2023).

Claude-Instant: Available at: https://poe.com/Claude-instant (Accessed on 3rd. June 2023).

ChatGPT: Available at: https://poe.com/ChatGPT (Accessed on 3rd. June 2023).

James PA, Oparil S, Carter BL, Cushman WC, Dennison-Himmelfarb C, Handler J, Lackland DT, LeFevre ML, MacKenzie TD, Ogedegbe O, Smith SC Jr, Svetkey LP, Taler SJ, Townsend RR, Wright JT Jr, Narva AS, Ortiz E. 2014 evidence-based guideline for the management of high blood pressure in adults: report from the panel members appointed to the Eighth Joint National Committee (JNC 8). JAMA. 2014;311(5):507–20.

Eschenhagen T. Treatment of hypertension. In: Brunton LL, Knollmann BC, editors. Goodman & Gilman’s the pharmacological basis of therapeutics. 14th ed. New York: McGraw Hill; 2023.

Shabatura J. September. Using Bloom’s taxonomy to write effective learning outcomes. https://tips.uark.edu/using-blooms-taxonomy/ (Accessed on 19th 2023).

Trainor A, Richards JB. Training medical educators to teach: bridging the gap between perception and reality. Isr J Health Policy Res. 2021;10(1):75.

Boscardin C, Gin B, Golde PB, Hauer KE. ChatGPT and generative artificial intelligence for medical education: potential and opportunity. Acad Med. 2023. https://doi.org/10.1097/ACM.0000000000005439 . (Published ahead of print).

Duong MT, Rauschecker AM, Rudie JD, Chen PH, Cook TS, Bryan RN, Mohan S. Artificial intelligence for precision education in radiology. Br J Radiol. 2019;92(1103):20190389.

Karthikeyan S, O’Connor E, Hu W. Barriers and facilitators to writing quality items for medical school assessments - a scoping review. BMC Med Educ. 2019;19(1):123.

Developing teachers and trainers in undergraduate medical education. Advice supplementary to Tomorrow’s Doctors. (2009). https://www.gmc-uk.org/-/media/documents/Developing_teachers_and_trainers_in_undergraduate_medical_education___guidance_0815.pdf_56440721.pdf (Accessed on 19th September 2023).

Cooper A, Rodman A. AI and Medical Education - A 21st-Century Pandora’s Box. N Engl J Med. 2023;389(5):385–7.

Chanda SS, Banerjee DN. Omission and commission errors underlying AI failures. AI Soc. 2022;17:1–24.

Narayanan A, Kapoor S. ‘GPT-4 and Professional Benchmarks: The Wrong Answer to the Wrong Question’. Substack newsletter. AI Snake Oil (blog). https://aisnakeoil.substack.com/p/gpt-4-and-professional-benchmarks (Accessed on 19th September 2023).

Brainard J. November. As scientists face a flood of papers, AI developers aim to help. Science, 21 2023. doi.10.1126/science.adn0669.

Ouyang F, Jiao P. Artificial intelligence in education: the three paradigms. Computers Education: Artif Intell. 2021;2:100020.

Gibson D, Kovanovic V, Ifenthaler D, Dexter S, Feng S. Learning theories for artificial intelligence promoting learning processes. Br J Edu Technol. 2023;54(5):1125–46.

Guerrero DT, Asaad M, Rajesh A, Hassan A, Butler CE. Advancing Surgical Education: the Use of Artificial Intelligence in Surgical Training. Am Surg. 2023;89(1):49–54.

Lee S. AI tools for educators. EIT InnoEnergy Master School Teachers Conference. 2023. https://www.slideshare.net/ignatia/ai-toolkit-for-educators?from_action=save (Accessed on 24th September 2023).

Download references

Author information

Authors and affiliations.

Department of Pharmacology & Therapeutics, College of Medicine & Medical Sciences, Arabian Gulf University, Manama, Kingdom of Bahrain

Kannan Sridharan & Reginald P. Sequeira

You can also search for this author in PubMed   Google Scholar

Contributions

RPS– Conceived the idea; KS– Data collection and curation; RPS and KS– Data analysis; RPS and KS– wrote the first draft and were involved in all the revisions.

Corresponding author

Correspondence to Kannan Sridharan .

Ethics declarations

Ethics approval and consent to participate.

Not applicable as neither there was any interaction with humans, nor any personal data was collected in this research study.

Consent for publication

Not applicable.

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.

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary Material 1

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.

Sridharan, K., Sequeira, R.P. Artificial intelligence and medical education: application in classroom instruction and student assessment using a pharmacology & therapeutics case study. BMC Med Educ 24 , 431 (2024). https://doi.org/10.1186/s12909-024-05365-7

Download citation

Received : 26 September 2023

Accepted : 28 March 2024

Published : 22 April 2024

DOI : https://doi.org/10.1186/s12909-024-05365-7

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

• Medical education
• Pharmacology
• Therapeutics

BMC Medical Education

ISSN: 1472-6920

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

Idaho and Moyle, et al. v. United States

What's at stake.

Idaho and Moyle, et al. v. United States was appealed to the U.S. Supreme Court by Idaho politicians seeking to disregard a federal statute — the Emergency Medical Treatment and Labor Act (EMTALA) — and put doctors in jail for providing pregnant patients necessary emergency medical care. The Supreme Court heard oral arguments on this case on April 24, 2024. The Court’s ultimate decision will impact access to this essential care across the country.

Enacted in 1986, EMTALA requires any hospital with an emergency room that receives Medicare funds (virtually all hospitals) to provide stabilizing treatment to anyone who comes to the hospital experiencing an emergency medical condition. Following the U.S. Supreme Court’s 2022 decision in Dobbs v. Jackson Women’s Health Organization , one of the most restrictive abortion bans in the country went into effect in Idaho.

The Department of Justice (DOJ) filed this lawsuit against Idaho in August 2022, seeking an injunction to allow patients to receive emergency abortions, as required under this federal law. A lower court granted the injunction, but anti-abortion politicians appealed that ruling to the Supreme Court, which lifted the injunction and took the case in January.

In March 2024, the American Civil Liberties Union (ACLU), ACLU of Idaho, and the law firm Cooley LLP filed an amicus brief in the case explaining that Idaho’s arguments cannot be justified under the Supreme Court’s own precedents, and that all three branches of government have long recognized that hospitals are required under EMTALA to provide emergency abortion care to any patient who needs it.

As a result of this ban, medical providers have found themselves having to decide between providing necessary emergency care to a pregnant patient and facing criminal prosecution from the state, or declining medical care and leaving a patient in crisis while facing federal sanctions for violating EMTALA.

Since Idaho’s extreme abortion ban took effect, Idaho has lost nearly 1 in 5 obstetricians and gynecologists who have chosen to leave the state and practice elsewhere, which has led to hospital obstetrics programs around the state shuttering their doors.

Medical professionals, from the American College of Emergency Physicians and American Hospital Association to the American Medical Association and the American College of Obstetricians and Gynecologists , have underscored that doctors must be able to provide their patients with the emergency abortion care they need.

Press Releases

Supreme Court to Determine Whether Politicians Can Deny Emergency Medical Care to Pregnant People

ACLU Brief in Emergency Abortion Care Case Highlights Idaho Politicians' Deeply Flawed Legal Arguments

Other Documents

Aclu et al. amicus brief, idaho and moyle, et al. v. united states, aclu's vision.

Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Tristique senectus et netus et malesuada fames ac turpis. Pharetra diam sit amet nisl suscipit adipiscing. Sodales ut eu sem integer vitae. Cursus in hac habitasse platea dictumst quisque sagittis purus. In hendrerit gravida rutrum quisque. Nisl pretium fusce id velit ut tortor. Mauris pellentesque pulvinar pellentesque habitant morbi tristique senectus et netus. A arcu cursus vitae congue mauris rhoncus aenean vel elit. Id aliquet risus feugiat in ante metus. Leo a diam sollicitudin tempor id eu nisl nunc. Pretium viverra suspendisse potenti nullam ac tortor. Egestas diam in arcu cursus euismod quis viverra.

Proin fermentum leo vel orci porta non. Tortor pretium viverra suspendisse potenti nullam ac tortor vitae. Velit aliquet sagittis id consectetur purus ut faucibus. Vel elit scelerisque mauris pellentesque pulvinar pellentesque habitant. Felis eget velit aliquet sagittis id consectetur purus ut faucibus. Tempor nec feugiat nisl pretium fusce id velit ut tortor. Lacinia at quis risus sed vulputate odio. Magnis dis parturient montes nascetur ridiculus mus mauris vitae ultricies. Consequat mauris nunc congue nisi. Adipiscing elit pellentesque habitant morbi tristique senectus et netus et. Praesent elementum facilisis leo vel fringilla. Faucibus nisl tincidunt eget nullam non nisi est sit amet.

Learn More About the Issues in This Case

• Reproductive Freedom

An official website of the United States government

Here’s how you know

Official websites use .gov A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS A lock ( A locked padlock ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

• Heart-Healthy Living
• High Blood Pressure
• Sickle Cell Disease
• Sleep Apnea
• Information & Resources on COVID-19
• The Heart Truth®
• Learn More Breathe Better®
• Blood Diseases and Disorders Education Program
• Publications and Resources
• Blood Disorders and Blood Safety
• Sleep Science and Sleep Disorders
• Lung Diseases
• Health Disparities and Inequities
• Heart and Vascular Diseases
• Precision Medicine Activities
• Obesity, Nutrition, and Physical Activity
• Population and Epidemiology Studies
• Women’s Health
• Research Topics
• Clinical Trials
• All Science A-Z
• Grants and Training Home
• Policies and Guidelines
• Funding Opportunities and Contacts
• Training and Career Development
• Email Alerts
• NHLBI in the Press
• Research Features
• Past Events
• Upcoming Events
• Mission and Strategic Vision
• Divisions, Offices and Centers
• Advisory Committees
• Budget and Legislative Information
• Jobs and Working at the NHLBI
• Contact and FAQs
• NIH Sleep Research Plan
• News and Events
• < Back To All News

Protecting Navajo children with asthma: A case study

Joncita Todechine, a mother of four who lives on the Navajo Nation, knows all too well what can trigger asthma symptoms in her daughter Ashley. But she didn’t always. She recalls a time in 2013, living in Phoenix and attending medical assistant school, when she rushed her then-three-year-old to the Indian Medical Center. 

“She was really sick,” Todechine said. “She was fevering, coughing, and had shortness of breath. We had no idea what was wrong.”

Ashley was admitted to the hospital and stayed for an entire week before the doctors could make a diagnosis of asthma. Now a thriving 13-year-old, Ashley loves gaming, social media, and riding on her hoverboard. These days she lives on the Navajo reservation with her family, who moved there shortly after her mother finished school. For the most part, she keeps her asthma under control by taking medication and doing her best to avoid her asthma triggers. 

But that can be challenging.

On the Navajo Nation, there are many asthma triggers. The semi-arid environment is plagued by drought, so on windy days, the gusts kick up ever-present dust and sand into the air. Shuttered coal-fired powerplants dot the landscape and, though they are closed, residual soot still dirties the air. Uranium and other heavy metals contaminate the landscape, and people breathe diesel fumes from the buses that take children to and from school every day. The many dogs and livestock roaming the reservation carry other allergens.

“And that’s just the outdoor pollution,” said Bruce Bender, Ph.D., professor in the pediatrics department at National Jewish Health in Denver, Colorado. “Seventy percent of households heat with indoor stoves that burn wood or charcoal and can leak a lot of smoke into the air.”

Bender would know. He’s co-project leader of an NHLBI-funded project focused on reducing health disparities in children living on the Navajo Nation, and he’s studied some of the factors that make those disparities worse. He’s also looked at the health data overall and found that while Native adults suffer from higher rates of chronic conditions like cardiovascular diseases and diabetes, it’s asthma that remains one of the most common chronic diseases in children. Some 18% of children on the Navajo reservation have it,  compared to 10.2% of children nationwide.

“Asthma can be incredibly scary for children and their families, especially those who cannot get emergency care easily or quickly,” said Michelle Freemer, M.D., M.P.H., director of the asthma program in NHLBI’s Division of Lung Diseases.

The Navajo Nation extends across more than 27,000 square miles, making it the largest Native land area in the U.S. "For families of children with asthma, the distances and travel conditions on the reservation may add challenges,” said Freemer. “The investigators partnered with the community to find solutions that work where they live, not simply provide asthma care that has been shown to work in other places." 

A local solution

Bender and his colleague, Lynn B. Gerald, Ph.D., M.S.P.H., assistant vice chancellor for population health at the University of Illinois-Chicago, started a large-scale effort to teach educators, children, their families, and local medical providers on the Navajo Nation how to identify an asthma attack and what to do in an emergency. (Gerald had worked previously at the University of Arizona and had gained a wealth of knowledge from the university's Native collaborators.) The program rolled out in three Arizona communities on the reservation: Tuba City, Chinle, and Fort Defiance. Combined, these towns represent 43% of the Navajo Nation population and are home to more than 8,000 children with asthma.  

But before they began, the investigators knew they needed to build relationships with the Navajo people – who refer to themselves as Diné – as the community’s prior experiences with non-Native researchers had left them skeptical. The research team began by ensuring the program was tailored to the needs and wishes of the community itself.

“The Navajo Nation human research review board is very careful and thorough,” Bender said. “They’re protecting their population. We had to earn their trust.”

Once the investigators got approval, they hit the ground running, starting in Tuba City. In the hospitals, the research team provided tools for medical professionals, using self-directed online learning and in-person workshops, to increase their use of practices that have been shown to be important in asthma care.

In the schools, the investigators provided education using the American Lung Association’s Asthma Basics and Open Airways for Schools® training, to teach school staff about asthma, its triggers, and what to do when a child is having an attack and to teach Diné children how to manage their asthma. 

Using a “train-the-trainer” model, school staff, community health workers, respiratory therapists, and pharmacists became students and then instructors. This made it possible for the Diné participants to teach additional staff, ensuring the community can sustain the program after the research funding ends.

Still, there was another urgent need that Bender and Gerald realized had not been addressed. “Less than 15% of children with asthma actually have an inhaler at school when they need it,” Gerald said. In response, the team helped start a program in two of the three communities that provided stock inhalers to schools for children who need them. 

A global threat

After starting the program in Tuba City as planned and spending a year there, the research team moved their focus to Chinle. The goal was to be able to compare how well the program worked in each of the three communities. But a global pandemic had other plans.

“The COVID-19 pandemic hit right in the middle of our time in Chinle,” Bender said. “After that, we weren’t allowed on the reservation for two years.”

While the pandemic changed life for all Americans, it devastated many Native communities. Schools closed and medical clinics focused on emergencies. The research team pivoted: they continued some training virtually and were able to keep learning from families about their needs, especially using the Diné members of the research team who were on the reservation.

Taking stock

Today, despite the challenges of the pandemic, all three communities have completed the original program, and 439 Diné members have been trained to identify asthma and its triggers. Yet the work is far from over. The investigators are analyzing the data they collected. “Particularly important is returning the results to the community,” Gerald said. As soon as they are ready, she said, they will be meeting with the school boards and health boards and joining community meetings to share them.

Freemer said that all the materials the researchers developed through their NHLBI funding are available to the community and have also been shared with those at the Indian Health Service leading the Asthma Control in Tribal Communities program.

“The researchers also took the opportunity to build research capacity,” she said. They developed an agreement with Diné College, the only four-year college on the reservation, to provide training through their Summer Research Experience Program. “In that program, students learned about research and were able to readily reach the families who appreciated the interactions with Diné research team members.”

Todechine said knowing that her child will be cared for if the worst happens has given her peace of mind. “Now the school systems have their own asthma alert systems that the employees and even the bus drivers take part in,” she said. “For me, I feel safer for her to be at school without me.”

  Resources:

Learn more about  Asthma in Our Communities  with specific resources for American Indians.

Related Health Topics

• Case report
• Open access
• Published: 23 April 2024

Genetic exploration of Dravet syndrome: two case report

• Agung Triono 1 ,
• Elisabeth Siti Herini   ORCID: orcid.org/0000-0003-2571-8310 1 &

Journal of Medical Case Reports volume  18 , Article number:  215 ( 2024 ) Cite this article

169 Accesses

1 Altmetric

Metrics details

Dravet syndrome is an infantile-onset developmental and epileptic encephalopathy (DEE) characterized by drug resistance, intractable seizures, and developmental comorbidities. This article focuses on manifestations in two Indonesian children with Javanese ethnicity who experienced Dravet syndrome with an SCN1A gene mutation, presenting genetic analysis findings using next-generation sequencing.

Case presentation

We present a case series involving two Indonesian children with Javanese ethnicity whom had their first febrile seizure at the age of 3 months, triggered after immunization. Both patients had global developmental delay and intractable seizures. We observed distinct genetic findings in both our cases. The first patient revealed heterozygous deletion mutation in three genes ( TTC21B , SCN1A , and SCN9A ). In our second patient, previously unreported mutation was discovered at canonical splice site upstream of exon 24 of the SCN1A gene. Our patient’s outcomes improved after therapeutic evaluation based on mutation findings When comparing clinical manifestations in our first and second patients, we found that the more severe the genetic mutation discovered, the more severe the patient’s clinical manifestations.

These findings emphasize the importance of comprehensive genetic testing beyond SCN1A , providing valuable insights for personalized management and tailored therapeutic interventions in patients with Dravet syndrome. Our study underscores the potential of next-generation sequencing in advancing genotype–phenotype correlations and enhancing diagnostic precision for effective disease management.

Peer Review reports

Dravet syndrome (DS), previously known as severe myoclonic epilepsy of infancy (SMEI), is an infantile-onset developmental and epileptic encephalopathy (DEE) characterized by drug resistance, intractable seizures, and comorbidities including intellectual disability, behavioral problems, sleep disturbances, gait disturbances, and an increased risk of sudden unexpected death in epilepsy [ 1 , 2 ]. The incidence of DS is approximately 1 in every 15,700 births [ 3 ]. The first symptom of DS is seizures in the first year of life, followed by developmental delay [ 1 ]. This first seizure is either generalized tonic–clonic or focal (occasionally hemiclonic) clonic, and in more than half of the cases, it is a febrile seizure, making it difficult to distinguish from a self-limiting febrile seizure. Infection, hot environment, exhaust, sunlight, or exercise can initiate an attack of DS [ 4 , 5 ]. Approximately 80% of patients with DS carry a pathogenic variant of the sodium channel alpha 1 subunit ( SCN1A ) gene resulting in haploinsufficiency Nav1.1, the alpha-1 subunit of the sodium channel. PCDH19, SCN2A, SCN8A, SCN1B, GABRA1, GABRB3, GABRG2, KCNA2, CHD2, CPLX1, HCN1A, and STXBP1 variants may also be involved in DS or DS-like phenotypes. Accordingly, genetic testing is required to identify other genes that play a role in the DS phenotype and to expand genotype-DS phenotype correlations to enhance the future management of this disease [ 6 ]. In the last decade, next-generation sequencing (NGS) technology has been able to analyze a set of genes (targeted panel sequencing), exome [(whole exome sequencing (WES)], or genome [whole genome sequencing (WGS)] in a single sequencing process, making it possible to diagnose rare diseases such as early childhood epilepsy [ 7 ]. Identification of the genetic basis of DS can provide additional information regarding pathophysiology, prognosis, and individual drug therapy options according to the patient’s condition.

We present a case series involving two children, one aged 11 years and 2 months, and the other aged 1 year and 4 months. Both children were diagnosed with DS, exhibiting symptoms of intractable seizures, global developmental delay, and seizures triggered by postimmunization fever. Despite displaying similar symptoms, the two individuals possess different genetic variants of the SCN1A gene and also possible novel mutation in DS. We also discuss the main clinical characteristics, treatment course, and management of DS at tertiary referral hospitals in Indonesia.

A boy with Javanese ethnicity aged 11 years and 2 months with uncontrollable seizures regularly visits our hospital. The patient had his first seizure at the age of 3 months with a duration of 15 min, and it was triggered after receiving diphtheria–pertussis–tetanus (DPT) immunization, which was accompanied by fever. The patient has about six to seven seizures per day for 1 min in the form of generalized tonic–clonic and absence seizures. He was the first child of nonconsanguineous healthy parents with normal prenatal and birth history. He has a younger sister with normal development. There is no history of family members with febrile seizure. The patient was born at 40 weeks of gestation, with a birth weight of 4000 g, length of 52 cm, and head circumference of 33 cm. The patient is currently experiencing global developmental delay and is still in kindergarten. He had learning difficulties and was unable to speak words at an age-appropriate level. He had delayed motor development and was unable to perform age-appropriate motor activities. Head circumference was 46.5 cm (microcephaly). There were no signs of meningeal irritation nor Babinski response. The motor examination revealed no increased tone in the upper and lower limb. Other systemic examinations revealed no abnormalities. Interictal electroencephalography (EEG) showed diffuse epileptiform irritative abnormality on a normal background (Fig.  1 ). Magnetic resonance imaging (MRI) of the brain showed cerebral atrophy, bilateral frontal subarachnoid enlargement, bilateral occipital lobe and polymicrogyria, and a neuroglial cyst in the right temporal lobe (Fig.  2 ). He was recommended to get genetic testing done since he was suspected of having DS.

Electroencephalography (EEG) shows diffuse epileptiform irritative abnormality on a normal background

Axial brain magnetic resonance imagery shows cerebral atrophy, bilateral frontal subarachnoid enlargement, bilateral occipital lobe polymicrogyria, and a neuroglial cyst in the right temporal lobe

Whole genome sequencing (WGS), whole exome sequencing (WES), and Sanger sequencing were performed at 3Billion (Seoul, Korea). The WGS and WES procedures were conducted according to the protocols of Richards et al . [ 8 ] and Seo et al . [ 9 ], respectively. Both WES and WGS are comprised of four main parts: (1) high-quality sequencing; (2) sequencing data analysis including alignment to the genome reference consortium human 37 (GRCh37)/hg19 for WES, also alignment to the genome reference consortium human 38 (GRCh38) and revised Cambridge reference sequence (rCRS) of the mitochondrial genome for WGS; (3) variant annotation and prioritization by EVIDENCE [a software that was developed in house to prioritize variants based on the American College of Medical Genetics and Genomics (ACMG) guidelines [ 10 ]]; and (4) variant interpretation in the context of the patient’s symptoms and reporting of disease-causing variants. Once EVIDENCE prioritizes the top candidate variants/genes, 3Billion’s highly-trained clinical/medical geneticists manually curate each variant to identify the disease-causing variant for reporting.

In our initial examination, we performed WES on patient 1 and subsequently identified a copy number variant (CNV), prompting us to proceed with WGS. The WGS analysis revealed a heterozygous pathogenic 552.9 Kb deletion variant in 2q24.3. The heterozygous deletion NC_000002.12:g.165811316_166364199delinsTGTACACTA at 2q24.3 spans across three genes ( TTC21B , SCN1A , and SCN9A ). The variant is not observed in the gnomAD SVs v2.1.1 dataset. SCN1A is subject to haploinsufficiency. Other pathogenic variants have been reported in this region. There are multiple similarly affected individuals reported with similar likely pathogenic copy–number–loss overlapping this region [ 11 , 12 ]. Therefore, this variant was classified as pathogenic. Due to region-spanning mutation in SCN1A, which suitable with clinical manifestation, the patient was diagnosed with DS (OMIM 607208: since we were unable to perform a Sanger sequencing study on both of the parents, the pattern of inheritance is still uncertain.

The arents were counseled about their child’s condition and agreed to undergo multipronged therapy. Before the patient was diagnosed with DS, he had received valproic acid (30 mg/kg per day), phenobarbital (2.5 mg/kg per day), and oxcarbazepine (5 mg/kg per day), also physio, occupation, and speech therapy but had not shown significant improvement. He was seizure-free for 3 months after oxcarbazepine was changed to levetiracetam (27 mg/kg per day). However, the patient then had another episodes of less than 5 minutes general tonic–clonic seizure (GTCS)-induced by fever. Interictal EEG was performed to evaluate his condition, and we found that the diffuse epileptiform irritative abnormality persisted.

A 1 year and 4 month-old-girl with Javanese ethnicity was referred to our hospital due experiencing myoclonic seizure followed by 20 minute GTCS at 3 months, after fever following DPT immunization. She then continued to experience generalized tonic–clonic seizures one to two times per day for 10–15 seconds. At 9 months of age, the patient received a second DPT immunization, and on the same day, she had another generalized tonic–clonic seizure that lasted > 30 minutes, resulting in her admission to the pediatric intensive care unit. Before the first seizure, the patient could lift her head, grasp a toy and make eye contact, but after that, she could neither lift her head nor grasp an object. The patient has no previous history of trauma.

She had a normal head circumference increased physiological reflexes in all extremities. Other systemic examinations revealed no abnormalities. Computed tomography (CT) scan examination of the head showed a subdural hygroma in the right and left frontoparietal region, without any other abnormalities (Fig.  3 ). Electroencephalography (EEG) at the beginning of the seizure did not show any abnormalities, but the EEG follow-up 7 months after the onset of the seizure showed an abnormal epileptiform (spike wave) with a normal background (Fig.  4 ). Thus, she was suspected of having DS and was recommended to undergo genetic examination.

Axial brain computed tomography scan shows a subdural hygroma in the right and left frontoparietal region, without any other abnormalities

Electroencephalography shows abnormal irritative epileptiform with a normal background

Whole exome sequencing (WES) showed a likely pathogenic variant identified as a heterozygous mutation of the SCN1A gene with genomic position 2-166859265-T-C (GRCh37), [NM_001165963.4:C.4003-2A > G [NP_001159435.1:p.?]. The variant is located in the canonical splice site upstream of exon 24 of SCN1A gene (NM_001165963.4 transcript). Since this variant is an essential splicing variant, the protein consequence is uncertain and therefore represented as (p.?). In this patient’s genetic mutation, the canonical junction site occurs which is expected to alter the junction and result in loss or disruption of normal protein function. However, using an in silico predictor, spliceAI ( https://spliceailookup.broadinstitute.org/ ), the variant is predicted to result in a loss of 22 base pairs at end of exon 24. This loss is expected to create a frameshift at the Gly1342 position. Sanger sequencing confirmed the patient’s genotype (Fig.  5 A), but the mother’s Sanger analysis was negative (Fig.  5 B). Due to familial issues, Sanger sequencing was not performed on the father, leaving the inheritance pattern unresolved.

A Sanger sequencing result of patient 2 showed a heterozygous mutation of the SCN1A gene with the genomic position 2-166859265-T-C (GRCh37), [NM_001165963.4:C.4003-2A >G [NP_001159435.1:p.?] (red arrow); and B Sanger sequencing result of patient 2’s mother showed normal sequence

The parents were counseled about their child’s condition and agreed to undergo multipronged therapy. Before patient was diagnosed with DS, she received clonazepam (0.01 mg/kg per day), valproic acid (29 mg/kg per day), and phenytoin (5 mg/kg per day), but seizure persisted. When phenytoin was stopped, with valproic acid (30 mg/kg per day) and clonazepam (0.04 mg/kg per day) adjusted, seizures were greatly decreased. Later, patient only experienced one seizure per year. The patient routinely received physio, speech, and occupational therapy.

When comparing the clinical features and outcomes of the two patients (Table  1 ), we found that our first patient, who had three medications, was still having a generalized seizure induced by fever with duration less than 5 minutes after they had been seizure-free for 3 months (at the age 11 years and 8 months. Our second patient, however, only experienced one seizure annually after receiving two medications (at the age 1 year and 10 months). This difference implies that the clinical state of the first patient was worse than that of the second.

Research on the identification of DS genetic mutations using NGS has never been done in Indonesia. In 2010, we conducted a study to identify pathogenic variants of the SCN1A gene using the Sanger sequencing method and successfully reported cases of novel SCN1A mutations in Indonesia in patients with severe myoclonic epilepsy in infancy (SMEI) and borderline SMEI (SMEB). The first boy identified with SMEI experienced a variety of seizures, including his first febrile seizure and general tonic–clonic seizure at 7 months of age, and later suffered from myoclonic seizures, left-sided hemiconvulsions, also focal convulsions without fever, along with delayed speech development. The second patient with SMEB had his first febrile seizures with GTCS after immunization at 3 months old, then later on experienced status epilepticus, GTCS, and atonic convulsions without fever [ 13 ]. We also conducted another research on the spectrum of generalized epilepsy with febrile seizure plus (GEFS+) focusing on clinical manifestations and SCN1A gene mutations. That study analyzed a total of 34 patients who suffered from SMEI (7 patients), SMEB (7 patients), febrile seizure plus (FS+) and absence/myoclonic/atonic/partial seizures (11 patients), and FS+ (9 patients) [ 14 ].

However, the research that we have done uses the Sanger sequencing genetic examination, which is expensive and takes considerable time. Additionally, it is unable to find any other gene besides SCN1A in patients with DS. A study by Djémié et al . in Belgium reported the discovery of 28 pathogenic variants of the SCN1A gene using the NGS method which were previously missed or undiagnosed using Sanger sequencing [ 7 ]. To link DS cases more effectively, we are attempting to conduct NGS genetic tests, specifically WES and WGS.

Dravet syndrome (DS) was infrequently reported in Indonesia due to its difficulty in diagnosis, misdiagnosis as febrile seizures or other epilepsy syndromes, or lack of follow-up and genetic testing in our country. According to the to the International League Against Epilepsy (ILAE) [ 15 ], the diagnostic criteria for this condition should consist of a number of the following symptoms: (1) a family history of epilepsy or febrile seizures; (2) normal development before seizures onset; (3) seizure before 1 year of age; (4) EEG with generalized spike and polyspike waves; (5) pleomorphic epilepsy (myoclonic, focal, clonic, absence, and generalized seizures); (6) focal abnormalities or early photosensitivity; (7) psychomotor retardation after 24 months; (8) exacerbation of seizures with increased body temperature; and (9) the appearance of subsequent ataxia, pyramidal signs or interictal myoclonus after the beginning of psychomotor slowing. Both of our patients had seizures beginning with increased body temperature and regression of development after seizure onset, which were resistant to the majority of anticonvulsant medications. The seizures began as generalized tonic–clonic seizures, followed by absence seizures. Both of our patients also experienced subsequent ataxia and pyramidal signs. Thus, they were suspected of having DS and were advised to undergo genetic testing.

Infants with DS have normal physical and psychomotor development at the time of their first seizure, which typically occurs between the ages of 5 and 8 months. In our case series, both of our patients experienced their first seizure at the age of 3 months [ 16 , 17 ]. In the first year of life, the most common form of seizure is febrile tonic–clonic. Some patients may experience myoclonic and dyscognitive seizures infrequently. Frequently, protracted seizures result in status epilepticus. In the first year of life, seizures are precipitated by fever/illness, immunization, and cleansing [ 16 ]. As the infant develops, he or she will experience a variety of seizure types, as well as fever and emotional stress, flashes of light, and overexertion being seizure triggers. The child with DS will develop hypotonia, ataxia, incoordination, and pyramidal signs, dysautonomia events, cognitive impairment, and behavioral disturbances such as attention deficit, hyperactivity, or autistic characteristics [ 15 ]. Some of the conditions above are very consistent with what happened to our patients.

The EEG performed during the early phases of the disease is normal. However, as the child grows, generalized spike waves with isolated or brief discharges of fast polyspike waves may be present [ 15 , 18 ]. In the first case, we found diffuse epileptiform irritative abnormality with a normal background, whereas in the second case, initially it was found normal, then a few months later it became abnormal irritative epileptiform with a normal background.

Genetic testing is developing rapidly and playing a significant role in the specific diagnosis and management of epilepsy [ 19 , 20 ]. Several genes with pathogenic mutations produce DS or DS-like phenotypes, which inevitably require different drug therapy approaches. Genes that cause DS can be grouped based on how they work: specifically, three sodium channel-related genes ( SCN2A, SCN8A , and SCN1B ), one potassium channel-related gene ( KCNA2 ), three gamma-aminobutyric acid receptors ( GABAR ) genes ( GABRA2, GABRB3 , and GABRG2 ), a cyclic nucleotide gated cation channel gene ( HCN1 ), and other functional genes including CHD2, CPLX1 , and STXBP1 . Approximately 80% of patients with DS have a pathogenic variant of the SCN1A gene, from which the majority of SCN1A variants are de novo, but 10% of people inherit the SCNA1 mutation from one or both parents [ 6 ]. Both of our patients had a mutation in the SCN1A gene, which is the most common mutation seen in DS.

Furthermore, TTC21B and SCN9A mutations were also found in our first patient. A study conducted by Suls et al . also reported a four generation Bulgarian family with epilepsy, revealing a heterozygous 400 kb deletion on chromosome 2q24 that included the SCN1A and TTC21B genes [ 21 ]. The patients exhibited variable phenotypes, but all experienced generalized tonic–clonic seizures around the first year of life, with some presenting myoclonic or absence seizures. Febrile seizures occurred in three of the four patients during infancy. Notably, one patient had mild mental retardation, another had psychomotor slowing, and a third had mental retardation from early infancy; all showed reduced seizures on medication. The findings in that study parallel the situation observed in our initial patient case. Meanwhile, a study by Singh et al . identified a heterozygous mutation in the SCN9A gene in two patients diagnosed with DS [ 22 ]. One of these patients also exhibited a mutation in the SCN1A gene. The study provided evidence suggesting that the SCN9A gene on chromosome 2q24 could potentially serve as a modifier for DS. Among 109 patients with DS, 8% were found to have an SCN9A mutation. This included six patients with double heterozygosity for SCN9A and SCN1A mutations and three patients with only heterozygous SCN9A mutations, supporting the notion of a multifactorial inheritance pattern [ 22 ]. The previous research confirmed the severity of clinical symptoms in our first patient, whom we identified mutations in the SCN1A, SCN9A , and TTC21B genes.

In the last decade, there has been a very rapid development of neurogenetic science and diagnostic technology. NGS is the latest method of genetic examination that allows for the discovery of causal mutations, including de novo, novel, and familial mutations related to epilepsy syndromes that have variable phenotypic features [ 23 ]. The first generation of DNA sequencing using the Sanger method could only examine one gene at a time and had limitations especially when examining large genomic regions, so the NGS method is more widely used today [ 7 , 23 ]. A study conducted by Kim et al . in Seoul reported an increase in diagnostic yield using WES after targeted panel sequencing with negative results in infantile onset epilepsy by 8%. This result suggests that WES assays increase the opportunity to search for new epilepsy genes and uncover less well-known epileptic phenotypes from known neurological diseases [ 24 ]. The WES examination also allows for the discovery of de novo or inherited mutations if the patient and both parents are examined [ 25 ].

According to the recommendations of the North American consensus panel, clobazam and valproic acid are the first-line therapies for antiepileptic drugs, followed by stiripentol, topiramate and levetiracetam. Patients with a suboptimal response to clobazam and valproic acid have been advised to consider the ketogenic diet as a second-line treatment [ 17 ]. SCN1A is a gene that codes for sodium channel channels, so drugs that work as sodium channel blockers, such as lamotrigine, phenytoin, carbamazepine, oxcarbazepine, lacosamide, and rufinamide, are contraindicated in patients with DS because they can increase the frequency of seizures [ 4 ]. After the failure of first- and second-line therapy, surgical therapies, such as vagus nerve stimulation (VNS), were moderately agreed upon and should be considered [ 17 ]. Besides medication, controlling infections and body temperature variations also showed to decrease the frequency of seizures and severity of the disease [ 18 ]. Initially, the first patient received oxcarbazepine and the second patient got phenytoin, which had been contraindicated to patients with DS. Futhermore, after eliminating medications that were contraindicated, both patients’ outcome improved.

In this study, we discovered unique mutations that have never been documented before, particularly in Indonesia, where NGS analysis of DS genetic variants has never been done. However, the limitation of this study, is that the information comes from two cases only. Further research is needed to explore more cases from Indonesia population.

In summary, our case series utilizing next-generation sequencing (NGS) unveils the intricate genetic landscape of Dravet syndrome (DS) in two Indonesian pediatric cases. By using WGS and WES, we identified distinct mutations in the SCN1A gene, as well as contributions from genes, such as TTC21B and SCN9A . The power of WGS lies in its ability to uncover rare pathogenic variants, including a 552.9 Kb deletion in the 2q24.3 region. These findings emphasize the importance of comprehensive genetic testing beyond SCN1A , providing valuable insights for personalized management and tailored therapeutic interventions in patients with DS. Our study underscores the potential of NGS in advancing genotype–phenotype correlations and enhancing diagnostic precision for effective disease management. Furthermore, we found that the clinical condition of the first patient was worse than that experienced by the second patient. This difference suggests that the more severe the genetic mutation detected, the more severe the clinical manifestations of the patient.

Availability of data and materials

The dataset used and/or analyzed during the current study are available from the corresponding author on reasonable request.

Abbreviations

American College Of Medical Genetics

Copy number variant

Computed tomography

• Dravet syndrome

Developmental and epileptic encephalopathy

Electroencephalography

Febrile seizure plus

Generalized epilepsy with febrile seizure plus

Genome reference consortium human 37

Genome reference consortium human 38

General tonic clonic seizure

International league against epilepsy

Magnetic resonance imaging

• Next-generation sequencing

Revised Cambridge reference sequence

Sodium channel alpha 1 subunit

Severe myoclonic epilepsy of infancy-borderline

Severe myoclonic epilepsy in infancy

Vagus nerve stimulation

Whole-exome sequencing

Whole-genome sequencing

Zuberi SM, Wirrell E, Yozawitz E, Wilmshurst JM, Specchio N, Riney K, et al . ILAE classification and definition of epilepsy syndromes with onset in neonates and infants: position statement by the ILAE Task Force on Nosology and Definitions. Epilepsia. 2022;63(6):1349–97.

Article   PubMed   Google Scholar  

Wirrell EC, Hood V, Knupp KG, Meskis MA, Nabbout R, Scheffer IE, et al . International consensus on diagnosis and management of Dravet syndrome. Epilepsia. 2022;63(7):1761–77.

Article   CAS   PubMed   PubMed Central   Google Scholar  

Isom LL, Knupp KG. Dravet syndrome: novel approaches for the most common genetic epilepsy. Neurotherapeutics. 2021;18(3):1524–34.

Cardenal-Muñoz E, Auvin S, Villanueva V, Cross JH, Zuberi SM, Lagae L, et al . Guidance on Dravet syndrome from infant to adult care: road map for treatment planning in Europe. Epilepsia Open. 2022;7(1):11–26.

Chen C, Fang F, Wang X, Lv J, Wang X, Jin H. Phenotypic and genotypic characteristics of SCN1A associated seizure diseases. Front Mol Neurosci. 2022;28(15): 821012.

Article   Google Scholar  

Ding J, Wang L, Jin Z, Qiang Y, Li W, Wang Y, et al . Do all roads lead to Rome? Genes causing Dravet syndrome and Dravet syndrome-like phenotypes. Front Neurol. 2022;11(13): 832380.

Djémié T, Weckhuysen S, Von Spiczak S, Carvill GL, Jaehn J, Anttonen A, et al . Pitfalls in genetic testing: the story of missed SCN1A mutations. Mol Genet Genomic Med. 2016;4(4):457–64.

Article   PubMed   PubMed Central   Google Scholar  

Richards S, Aziz N, Bale S, Bick D, Das S, Gastier-Foster J, et al . Standards and guidelines for the interpretation of sequence variants: a joint consensus recommendation of the American College of Medical Genetics and Genomics and the Association for Molecular Pathology. Genet Med. 2015;17(5):405–24.

Seo GH, Kim T, Choi IH, Park J, Lee J, Kim S, et al . Diagnostic yield and clinical utility of whole exome sequencing using an automated variant prioritization system, EVIDENCE . Clin Genet. 2020;98(6):562–70.

Riggs ER, Andersen EF, Cherry AM, Kantarci S, Kearney H, Patel A, et al . Technical standards for the interpretation and reporting of constitutional copy-number variants: a joint consensus recommendation of the American College of Medical Genetics and Genomics (ACMG) and the Clinical Genome Resource (ClinGen). Genet Med. 2020;22(2):245–57.

Lim BC, Hwang H, Kim H, Chae JH, Choi J, Kim KJ, et al . Epilepsy phenotype associated with a chromosome 2q243 deletion involving SCN1A: migrating partial seizures of infancy or atypical Dravet syndrome? Epilepsy Res. 2015;109:34–9.

Article   CAS   PubMed   Google Scholar  

Fry AE, Rees E, Thompson R, Mantripragada K, Blake P, Jones G, et al . Pathogenic copy number variants and SCN1A mutations in patients with intellectual disability and childhood-onset epilepsy. BMC Med Genet. 2016;17(1):34.

Herini ES, Gunadi, Van Kempen MJA, Yusoff S, Sutaryo, Sunartini, et al. Novel SCN1A mutations in Indonesian patients with severe myoclonic epilepsy in infancy. Pediatr Int. 2010;52(2):234–9.

Herini ES, Gunadi, Harahap ISK, Yusoff S, Morikawa S, Patria SY, et al. Generalized epilepsy with febrile seizures plus (GEFS+) spectrum: clinical manifestations and SCN1A mutations in Indonesian patients. Epilepsy Res. 2010;90(1–2):132–9.

Anwar A, Saleem S, Patel UK, Arumaithurai K, Malik P. Dravet syndrome: an overview. Cureus. 2019. https://www.cureus.com/articles/20900-dravet-syndrome-an-overview . Accessed 20 Nov 2023.

Brunklaus A, Dorris L, Ellis R, Reavey E, Lee E, Forbes G, et al . The clinical utility of an SCN1A genetic diagnosis in infantile-onset epilepsy. Dev Med Child Neurol. 2013;55(2):154–61.

Wirrell EC, Laux L, Donner E, Jette N, Knupp K, Meskis MA, et al . Optimizing the diagnosis and management of Dravet syndrome: recommendations from a North American Consensus Panel. Pediatr Neurol. 2017;68:18-34.e3.

Yadav R, Shah S, Bhandari B, Marasini K, Mandal P, Murarka H, et al . Patient with Dravet syndrome: a case report. Clin Case Rep. 2022;10(5): e05840.

Møller RS, Dahl HA, Helbig I. The contribution of next generation sequencing to epilepsy genetics. Expert Rev Mol Diagn. 2015;15(12):1531–8.

Yozawitz E, Moshé SL. The influence of genetics on epilepsy syndromes in infancy and childhood. Acta Epileptol. 2022;4(1):41.

Suls A, Velizarova R, Yordanova I, Deprez L, Van Dyck T, Wauters J, et al . Four generations of epilepsy caused by an inherited microdeletion of the SCN1A gene. Am Acad Neurol. 2010;75(72):72–6.

CAS   Google Scholar  

Singh NA, Pappas C, Dahle EJ, Claes LRF, Pruess TH, De Jonghe P, et al . A role of SCN9A in human epilepsies, as a cause of febrile seizures and as a potential modifier of Dravet syndrome. PLoS Genet. 2009;5(9): e1000649.

Dunn P, Albury CL, Maksemous N, Benton MC, Sutherland HG, Smith RA, et al . Next generation sequencing methods for diagnosis of epilepsy syndromes. Front Genet. 2018;7(9):20.

Kim SY, Jang SS, Kim H, Hwang H, Choi JE, Chae J, et al . Genetic diagnosis of infantile-onset epilepsy in the clinic: application of whole-exome sequencing following epilepsy gene panel testing. Clin Genet. 2021;99(3):418–24.

Poduri A, Sheidley BR, Shostak S, Ottman R. Genetic testing in the epilepsies—developments and dilemmas. Nat Rev Neurol. 2014;10(5):293–9.

Download references

Acknowledgements

The authors express their gratitude to the patient and their families for their cooperation, as well as to all the staff and nurses who provided care for the patient. We are also thankful for the Faculty of Medicine, Public Health, and Nursing, Universitas Gadjah Mada for funding this research and providing English editing services for assistance in the editing and proofreading process. Additionally, we appreciate the assistance of Kristy Iskandar, Marissa Leviani Hadiyanto and Khansadhia Hasmaradana Mooiindie during the data collection and editing phases.

This study was supported by the Faculty of Medicine, Public Health and Nursing, Universitas Gadjah Mada, (Dana Masyarakat to ESH). The funding body did not influence the study design, data analysis, data interpretation, nor manuscript writing.

Author information

Authors and affiliations.

Department of Child Health, Faculty of Medicine, Public Health and Nursing, Universitas Gadjah Mada, Dr. Sardjito Hospital, Jl. Kesehatan No. 1, Yogyakarta, 55281, Indonesia

Agung Triono & Elisabeth Siti Herini

Pediatric Surgery Division, Department of Surgery/Genetics Working Group/Translational Research Unit, Faculty of Medicine, Public Health and Nursing, Universitas Gadjah Mada, Dr. Sardjito Hospital, Yogyakarta, 55281, Indonesia

You can also search for this author in PubMed   Google Scholar

Contributions

ESH, AG, and G made substantial contributions to the conception and design of the work. AG contributed to data acquisition. ESH, AG, and G performed the data analyses and the interpretation of the data. ESH and AG drafted the text and prepared the figures. ESH, AG, and G revised, read, and approved the final manuscript. All authors approve the present version for publication, and are accountable for all aspects related to the study.

Corresponding author

Correspondence to Elisabeth Siti Herini .

Ethics declarations

Ethics approval and consent to participate.

The Medical and Health Research Ethics Committee of the Faculty of Medicine, Public Health and Nursing, Universitas Gadjah Mada, Yogyakarta, Indonesia approved all recruitment and research protocols. Eligible patients signed an informed consent form (ethical clearance number KE-FK-0455-EC-2023; dated March 2023). Patients older than 12 years old and/or their parents or guardian (for patients < 12 years old) signed a written informed consent form to be included in this study.

Consent for publication

Written informed consent was obtained from the patients’ legal guardians for publication of this case report and any accompanying images.

Competing interests

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.

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.

Triono, A., Herini, E.S. & Gunadi Genetic exploration of Dravet syndrome: two case report. J Med Case Reports 18 , 215 (2024). https://doi.org/10.1186/s13256-024-04514-2

Download citation

Received : 31 January 2024

Accepted : 18 March 2024

Published : 23 April 2024

DOI : https://doi.org/10.1186/s13256-024-04514-2

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

• Case series

Journal of Medical Case Reports

ISSN: 1752-1947

• Submission enquiries: Access here and click Contact Us
• General enquiries: [email protected]

• Skip to main content
• Keyboard shortcuts for audio player

• Your Health
• Treatments & Tests
• Health Inc.
• Public Health

Reproductive rights in America

What's at stake as the supreme court hears idaho case about abortion in emergencies.

Selena Simmons-Duffin

The Supreme Court will hear another case about abortion rights on Wednesday. Protestors gathered outside the court last month when the case before the justices involved abortion pills. Tom Brenner for The Washington Post/Getty Images hide caption

The Supreme Court will hear another case about abortion rights on Wednesday. Protestors gathered outside the court last month when the case before the justices involved abortion pills.

In Idaho, when a pregnant patient has complications, abortion is only legal to prevent the woman's death. But a federal law known as EMTALA requires doctors to provide "stabilizing treatment" to patients in the emergency department.

The Biden administration sees that as a direct conflict, which is why the abortion issue is back – yet again – before the Supreme Court on Wednesday.

The case began just a few weeks after the justices overturned Roe v. Wade in 2022, when the federal Justice Department sued Idaho , arguing that the court should declare that "Idaho's law is invalid" when it comes to emergency abortions because the federal emergency care law preempts the state's abortion ban. So far, a district court agreed with the Biden administration, an appeals court panel agreed with Idaho, and the Supreme Court allowed the strict ban to take effect in January when it agreed to hear the case.

Supreme Court allows Idaho abortion ban to be enacted, first such ruling since Dobbs

The case, known as Moyle v. United States (Mike Moyle is the speaker of the Idaho House), has major implications on everything from what emergency care is available in states with abortion bans to how hospitals operate in Idaho. Here's a summary of what's at stake.

1. Idaho physicians warn patients are being harmed

Under Idaho's abortion law , the medical exception only applies when a doctor judges that "the abortion was necessary to prevent the death of the pregnant woman." (There is also an exception to the Idaho abortion ban in cases of rape or incest, only in the first trimester of the pregnancy, if the person files a police report.)

In a filing with the court , a group of 678 physicians in Idaho described cases in which women facing serious pregnancy complications were either sent home from the hospital or had to be transferred out of state for care. "It's been just a few months now that Idaho's law has been in effect – six patients with medical emergencies have already been transferred out of state for [pregnancy] termination," Dr. Jim Souza, chief physician executive of St. Luke's Health System in Idaho, told reporters on a press call last week.

Those delays and transfers can have consequences. For example, Dr. Emily Corrigan described a patient in court filings whose water broke too early, which put her at risk of infection. After two weeks of being dismissed while trying to get care, the patient went to Corrigan's hospital – by that time, she showed signs of infection and had lost so much blood she needed a transfusion. Corrigan added that without receiving an abortion, the patient could have needed a limb amputation or a hysterectomy – in other words, even if she didn't die, she could have faced life-long consequences to her health.

Attorneys for Idaho defend its abortion law, arguing that "every circumstance described by the administration's declarations involved life-threatening circumstances under which Idaho law would allow an abortion."

Ryan Bangert, senior attorney for the Christian legal powerhouse Alliance Defending Freedom, which is providing pro-bono assistance to the state of Idaho, says that "Idaho law does allow for physicians to make those difficult decisions when it's necessary to perform an abortion to save the life of the mother," without waiting for patients to become sicker and sicker.

Still, Dr. Sara Thomson, an OB-GYN in Boise, says difficult calls in the hospital are not hypothetical or even rare. "In my group, we're seeing this happen about every month or every other month where this state law complicates our care," she says. Four patients have sued the state in a separate case arguing that the narrow medical exception harmed them.

"As far as we know, we haven't had a woman die as a consequence of this law, but that is really on the top of our worry list of things that could happen because we know that if we watch as death is approaching and we don't intervene quickly enough, when we decide finally that we're going to intervene to save her life, it may be too late," she says.

2. Hospitals are closing units and struggling to recruit doctors

Labor and delivery departments are expensive for hospitals to operate. Idaho already had a shortage of providers, including OB-GYNS. Hospital administrators now say the Idaho abortion law has led to an exodus of maternal care providers from the state, which has a population of 2 million people.

Three rural hospitals in Idaho have closed their labor-and-delivery units since the abortion law took effect. "We are seeing the expansion of what's called obstetrical deserts here in Idaho," said Brian Whitlock, president and CEO of the Idaho Hospital Association.

Since Idaho's abortion law took effect, nearly one in four OB-GYNs have left the state or retired, according to a report from the Idaho Physician Well-Being Action Collaborative. The report finds the loss of doctors who specialize in high-risk pregnancies is even more extreme – five of nine full time maternal-fetal medicine specialists have left Idaho.

Administrators say they aren't able to recruit new providers to fill those positions. "Since [the abortion law's] enactment, St. Luke's has had markedly fewer applicants for open physician positions, particularly in obstetrics. And several out-of-state candidates have withdrawn their applications upon learning of the challenges of practicing in Idaho, citing [the law's] enactment and fear of criminal penalties," reads an amicus brief from St. Luke's health system in support of the federal government.

"Prior to the abortion decision, we already ranked 50th in number of physicians per capita – we were already a strained state," says Thomson, the doctor in Boise. She's experienced the loss of OB-GYN colleagues first hand. "I had a partner retire right as the laws were changing and her position has remained open – unfilled now for almost two years – so my own personal group has been short-staffed," she says.

ADF's Bangert says he's skeptical of the assertion that the abortion law is responsible for this exodus of doctors from Idaho. "I would be very surprised if Idaho's abortion law is the sole or singular cause of any physician shortage," he says. "I'm very suspicious of any claims of causality."

3. Justices could weigh in on fetal "personhood"

The state of Idaho's brief argues that EMTALA actually requires hospitals "to protect and care for an 'unborn child,'" an argument echoed in friend-of-the-court briefs from the U.S. Conference of Catholic Bishops and a group of states from Indiana to Wyoming that also have restrictive abortion laws. They argue that abortion can't be seen as a stabilizing treatment if one patient dies as a result.

Thomson is also Catholic, and she says the idea that, in an emergency, she is treating two patients – the fetus and the mother – doesn't account for clinical reality. "Of course, as obstetricians we have a passion for caring for both the mother and the baby, but there are clinical situations where the mom's health or life is in jeopardy, and no matter what we do, the baby is going to be lost," she says.

The Idaho abortion law uses the term "unborn child" as opposed to the words "embryo" or "fetus" – language that implies the fetus has the same rights as other people.

Shots - Health News

The science of ivf: what to know about alabama's 'extrauterine children' ruling.

Mary Ziegler , a legal historian at University of California - Davis, who is writing a book on fetal personhood, describes it as the "North Star" of the anti-abortion rights movement. She says this case will be the first time the Supreme Court justices will be considering a statute that uses that language.

"I think we may get clues about the future of bigger conflicts about fetal personhood," she explains, depending on how the justices respond to this idea. "Not just in the context of this statute or emergency medical scenarios, but in the context of the Constitution."

ADF has dismissed the idea that this case is an attempt to expand fetal rights. "This case is, at root, a question about whether or not the federal government can affect a hostile takeover of the practice of medicine in all 50 states by misinterpreting a long-standing federal statute to contain a hidden nationwide abortion mandate," Bangert says.

4. The election looms large

Ziegler suspects the justices will allow Idaho's abortion law to remain as is. "The Supreme Court has let Idaho's law go into effect, which suggests that the court is not convinced by the Biden administration's arguments, at least at this point," she notes.

Trump backed a federal abortion ban as president. Now, he says he wouldn't sign one

Whatever the decision, it will put abortion squarely back in the national spotlight a few months before the November election. "It's a reminder on the political side of things, that Biden and Trump don't really control the terms of the debate on this very important issue," Zielger observes. "They're going to be things put on everybody's radar by other actors, including the Supreme Court."

The justices will hear arguments in the case on Wednesday morning. A decision is expected by late June or early July.

Correction April 23, 2024

An earlier version of this story did not mention the rape and incest exception to Idaho's abortion ban. A person who reports rape or incest to police can end a pregnancy in Idaho in the first trimester.

• Abortion rights
• Supreme Court

This paper is in the following e-collection/theme issue:

Published on 24.4.2024 in Vol 26 (2024)

The Costs of Anonymization: Case Study Using Clinical Data

Authors of this article:

Lisa Pilgram   1, 2 , MD ;   Thierry Meurers   3 , MSc ;   Bradley Malin   4 , PhD ;   Elke Schaeffner   5 , MSc, MD ;   Kai-Uwe Eckardt   2, 6 , MD ;   Fabian Prasser   3 , PhD ;   GCKD Investigators   7

1 Junior Digital Clinician Scientist Program, Biomedical Innovation Academy, Berlin Institute of Health at Charité—Universitätsmedizin Berlin, Berlin, Germany

2 Department of Nephrology and Medical Intensive Care, Charité—Universitätsmedizin Berlin, Berlin, Germany

3 Medical Informatics Group, Berlin Institute of Health at Charité—Universitätsmedizin Berlin, Berlin, Germany

4 Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, TN, United States

5 Institute of Public Health, Charité—Universitätsmedizin Berlin, Berlin, Germany

6 Department of Nephrology and Hypertension, Universitätsklinikum Erlangen, Friedrich-Alexander University Erlangen-Nürnberg, Erlangen, Germany

7 See Acknowledgments, Erlangen, Germany

Corresponding Author:

• Lisa Pilgram , MD
• Junior Digital Clinician Scientist Program
• Biomedical Innovation Academy
• Berlin Institute of Health at Charité—Universitätsmedizin Berlin
• Charitéplatz 1
• Berlin , 10117
• Phone: 49 30 450543049
• Fax: 49 30 450 7 553 9
• Email: [email protected]

An official website of the United States government

The .gov means it’s official. Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

The site is secure. The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

• Publications
• Account settings

Preview improvements coming to the PMC website in October 2024. Learn More or Try it out now .

• Advanced Search
• Journal List
• BMC Med Res Methodol

The case study approach

Sarah crowe.

1 Division of Primary Care, The University of Nottingham, Nottingham, UK

Kathrin Cresswell

2 Centre for Population Health Sciences, The University of Edinburgh, Edinburgh, UK

Ann Robertson

3 School of Health in Social Science, The University of Edinburgh, Edinburgh, UK

Anthony Avery

Aziz sheikh.

The case study approach allows in-depth, multi-faceted explorations of complex issues in their real-life settings. The value of the case study approach is well recognised in the fields of business, law and policy, but somewhat less so in health services research. Based on our experiences of conducting several health-related case studies, we reflect on the different types of case study design, the specific research questions this approach can help answer, the data sources that tend to be used, and the particular advantages and disadvantages of employing this methodological approach. The paper concludes with key pointers to aid those designing and appraising proposals for conducting case study research, and a checklist to help readers assess the quality of case study reports.

Introduction

The case study approach is particularly useful to employ when there is a need to obtain an in-depth appreciation of an issue, event or phenomenon of interest, in its natural real-life context. Our aim in writing this piece is to provide insights into when to consider employing this approach and an overview of key methodological considerations in relation to the design, planning, analysis, interpretation and reporting of case studies.

The illustrative 'grand round', 'case report' and 'case series' have a long tradition in clinical practice and research. Presenting detailed critiques, typically of one or more patients, aims to provide insights into aspects of the clinical case and, in doing so, illustrate broader lessons that may be learnt. In research, the conceptually-related case study approach can be used, for example, to describe in detail a patient's episode of care, explore professional attitudes to and experiences of a new policy initiative or service development or more generally to 'investigate contemporary phenomena within its real-life context' [ 1 ]. Based on our experiences of conducting a range of case studies, we reflect on when to consider using this approach, discuss the key steps involved and illustrate, with examples, some of the practical challenges of attaining an in-depth understanding of a 'case' as an integrated whole. In keeping with previously published work, we acknowledge the importance of theory to underpin the design, selection, conduct and interpretation of case studies[ 2 ]. In so doing, we make passing reference to the different epistemological approaches used in case study research by key theoreticians and methodologists in this field of enquiry.

This paper is structured around the following main questions: What is a case study? What are case studies used for? How are case studies conducted? What are the potential pitfalls and how can these be avoided? We draw in particular on four of our own recently published examples of case studies (see Tables ​ Tables1, 1 , ​ ,2, 2 , ​ ,3 3 and ​ and4) 4 ) and those of others to illustrate our discussion[ 3 - 7 ].

Example of a case study investigating the reasons for differences in recruitment rates of minority ethnic people in asthma research[ 3 ]

Example of a case study investigating the process of planning and implementing a service in Primary Care Organisations[ 4 ]

Example of a case study investigating the introduction of the electronic health records[ 5 ]

Example of a case study investigating the formal and informal ways students learn about patient safety[ 6 ]

What is a case study?

A case study is a research approach that is used to generate an in-depth, multi-faceted understanding of a complex issue in its real-life context. It is an established research design that is used extensively in a wide variety of disciplines, particularly in the social sciences. A case study can be defined in a variety of ways (Table ​ (Table5), 5 ), the central tenet being the need to explore an event or phenomenon in depth and in its natural context. It is for this reason sometimes referred to as a "naturalistic" design; this is in contrast to an "experimental" design (such as a randomised controlled trial) in which the investigator seeks to exert control over and manipulate the variable(s) of interest.

Definitions of a case study

Stake's work has been particularly influential in defining the case study approach to scientific enquiry. He has helpfully characterised three main types of case study: intrinsic , instrumental and collective [ 8 ]. An intrinsic case study is typically undertaken to learn about a unique phenomenon. The researcher should define the uniqueness of the phenomenon, which distinguishes it from all others. In contrast, the instrumental case study uses a particular case (some of which may be better than others) to gain a broader appreciation of an issue or phenomenon. The collective case study involves studying multiple cases simultaneously or sequentially in an attempt to generate a still broader appreciation of a particular issue.

These are however not necessarily mutually exclusive categories. In the first of our examples (Table ​ (Table1), 1 ), we undertook an intrinsic case study to investigate the issue of recruitment of minority ethnic people into the specific context of asthma research studies, but it developed into a instrumental case study through seeking to understand the issue of recruitment of these marginalised populations more generally, generating a number of the findings that are potentially transferable to other disease contexts[ 3 ]. In contrast, the other three examples (see Tables ​ Tables2, 2 , ​ ,3 3 and ​ and4) 4 ) employed collective case study designs to study the introduction of workforce reconfiguration in primary care, the implementation of electronic health records into hospitals, and to understand the ways in which healthcare students learn about patient safety considerations[ 4 - 6 ]. Although our study focusing on the introduction of General Practitioners with Specialist Interests (Table ​ (Table2) 2 ) was explicitly collective in design (four contrasting primary care organisations were studied), is was also instrumental in that this particular professional group was studied as an exemplar of the more general phenomenon of workforce redesign[ 4 ].

What are case studies used for?

According to Yin, case studies can be used to explain, describe or explore events or phenomena in the everyday contexts in which they occur[ 1 ]. These can, for example, help to understand and explain causal links and pathways resulting from a new policy initiative or service development (see Tables ​ Tables2 2 and ​ and3, 3 , for example)[ 1 ]. In contrast to experimental designs, which seek to test a specific hypothesis through deliberately manipulating the environment (like, for example, in a randomised controlled trial giving a new drug to randomly selected individuals and then comparing outcomes with controls),[ 9 ] the case study approach lends itself well to capturing information on more explanatory ' how ', 'what' and ' why ' questions, such as ' how is the intervention being implemented and received on the ground?'. The case study approach can offer additional insights into what gaps exist in its delivery or why one implementation strategy might be chosen over another. This in turn can help develop or refine theory, as shown in our study of the teaching of patient safety in undergraduate curricula (Table ​ (Table4 4 )[ 6 , 10 ]. Key questions to consider when selecting the most appropriate study design are whether it is desirable or indeed possible to undertake a formal experimental investigation in which individuals and/or organisations are allocated to an intervention or control arm? Or whether the wish is to obtain a more naturalistic understanding of an issue? The former is ideally studied using a controlled experimental design, whereas the latter is more appropriately studied using a case study design.

Case studies may be approached in different ways depending on the epistemological standpoint of the researcher, that is, whether they take a critical (questioning one's own and others' assumptions), interpretivist (trying to understand individual and shared social meanings) or positivist approach (orientating towards the criteria of natural sciences, such as focusing on generalisability considerations) (Table ​ (Table6). 6 ). Whilst such a schema can be conceptually helpful, it may be appropriate to draw on more than one approach in any case study, particularly in the context of conducting health services research. Doolin has, for example, noted that in the context of undertaking interpretative case studies, researchers can usefully draw on a critical, reflective perspective which seeks to take into account the wider social and political environment that has shaped the case[ 11 ].

Example of epistemological approaches that may be used in case study research

How are case studies conducted?

Here, we focus on the main stages of research activity when planning and undertaking a case study; the crucial stages are: defining the case; selecting the case(s); collecting and analysing the data; interpreting data; and reporting the findings.

Defining the case

Carefully formulated research question(s), informed by the existing literature and a prior appreciation of the theoretical issues and setting(s), are all important in appropriately and succinctly defining the case[ 8 , 12 ]. Crucially, each case should have a pre-defined boundary which clarifies the nature and time period covered by the case study (i.e. its scope, beginning and end), the relevant social group, organisation or geographical area of interest to the investigator, the types of evidence to be collected, and the priorities for data collection and analysis (see Table ​ Table7 7 )[ 1 ]. A theory driven approach to defining the case may help generate knowledge that is potentially transferable to a range of clinical contexts and behaviours; using theory is also likely to result in a more informed appreciation of, for example, how and why interventions have succeeded or failed[ 13 ].

Example of a checklist for rating a case study proposal[ 8 ]

For example, in our evaluation of the introduction of electronic health records in English hospitals (Table ​ (Table3), 3 ), we defined our cases as the NHS Trusts that were receiving the new technology[ 5 ]. Our focus was on how the technology was being implemented. However, if the primary research interest had been on the social and organisational dimensions of implementation, we might have defined our case differently as a grouping of healthcare professionals (e.g. doctors and/or nurses). The precise beginning and end of the case may however prove difficult to define. Pursuing this same example, when does the process of implementation and adoption of an electronic health record system really begin or end? Such judgements will inevitably be influenced by a range of factors, including the research question, theory of interest, the scope and richness of the gathered data and the resources available to the research team.

Selecting the case(s)

The decision on how to select the case(s) to study is a very important one that merits some reflection. In an intrinsic case study, the case is selected on its own merits[ 8 ]. The case is selected not because it is representative of other cases, but because of its uniqueness, which is of genuine interest to the researchers. This was, for example, the case in our study of the recruitment of minority ethnic participants into asthma research (Table ​ (Table1) 1 ) as our earlier work had demonstrated the marginalisation of minority ethnic people with asthma, despite evidence of disproportionate asthma morbidity[ 14 , 15 ]. In another example of an intrinsic case study, Hellstrom et al.[ 16 ] studied an elderly married couple living with dementia to explore how dementia had impacted on their understanding of home, their everyday life and their relationships.

For an instrumental case study, selecting a "typical" case can work well[ 8 ]. In contrast to the intrinsic case study, the particular case which is chosen is of less importance than selecting a case that allows the researcher to investigate an issue or phenomenon. For example, in order to gain an understanding of doctors' responses to health policy initiatives, Som undertook an instrumental case study interviewing clinicians who had a range of responsibilities for clinical governance in one NHS acute hospital trust[ 17 ]. Sampling a "deviant" or "atypical" case may however prove even more informative, potentially enabling the researcher to identify causal processes, generate hypotheses and develop theory.

In collective or multiple case studies, a number of cases are carefully selected. This offers the advantage of allowing comparisons to be made across several cases and/or replication. Choosing a "typical" case may enable the findings to be generalised to theory (i.e. analytical generalisation) or to test theory by replicating the findings in a second or even a third case (i.e. replication logic)[ 1 ]. Yin suggests two or three literal replications (i.e. predicting similar results) if the theory is straightforward and five or more if the theory is more subtle. However, critics might argue that selecting 'cases' in this way is insufficiently reflexive and ill-suited to the complexities of contemporary healthcare organisations.

The selected case study site(s) should allow the research team access to the group of individuals, the organisation, the processes or whatever else constitutes the chosen unit of analysis for the study. Access is therefore a central consideration; the researcher needs to come to know the case study site(s) well and to work cooperatively with them. Selected cases need to be not only interesting but also hospitable to the inquiry [ 8 ] if they are to be informative and answer the research question(s). Case study sites may also be pre-selected for the researcher, with decisions being influenced by key stakeholders. For example, our selection of case study sites in the evaluation of the implementation and adoption of electronic health record systems (see Table ​ Table3) 3 ) was heavily influenced by NHS Connecting for Health, the government agency that was responsible for overseeing the National Programme for Information Technology (NPfIT)[ 5 ]. This prominent stakeholder had already selected the NHS sites (through a competitive bidding process) to be early adopters of the electronic health record systems and had negotiated contracts that detailed the deployment timelines.

It is also important to consider in advance the likely burden and risks associated with participation for those who (or the site(s) which) comprise the case study. Of particular importance is the obligation for the researcher to think through the ethical implications of the study (e.g. the risk of inadvertently breaching anonymity or confidentiality) and to ensure that potential participants/participating sites are provided with sufficient information to make an informed choice about joining the study. The outcome of providing this information might be that the emotive burden associated with participation, or the organisational disruption associated with supporting the fieldwork, is considered so high that the individuals or sites decide against participation.

In our example of evaluating implementations of electronic health record systems, given the restricted number of early adopter sites available to us, we sought purposively to select a diverse range of implementation cases among those that were available[ 5 ]. We chose a mixture of teaching, non-teaching and Foundation Trust hospitals, and examples of each of the three electronic health record systems procured centrally by the NPfIT. At one recruited site, it quickly became apparent that access was problematic because of competing demands on that organisation. Recognising the importance of full access and co-operative working for generating rich data, the research team decided not to pursue work at that site and instead to focus on other recruited sites.

Collecting the data

In order to develop a thorough understanding of the case, the case study approach usually involves the collection of multiple sources of evidence, using a range of quantitative (e.g. questionnaires, audits and analysis of routinely collected healthcare data) and more commonly qualitative techniques (e.g. interviews, focus groups and observations). The use of multiple sources of data (data triangulation) has been advocated as a way of increasing the internal validity of a study (i.e. the extent to which the method is appropriate to answer the research question)[ 8 , 18 - 21 ]. An underlying assumption is that data collected in different ways should lead to similar conclusions, and approaching the same issue from different angles can help develop a holistic picture of the phenomenon (Table ​ (Table2 2 )[ 4 ].

Brazier and colleagues used a mixed-methods case study approach to investigate the impact of a cancer care programme[ 22 ]. Here, quantitative measures were collected with questionnaires before, and five months after, the start of the intervention which did not yield any statistically significant results. Qualitative interviews with patients however helped provide an insight into potentially beneficial process-related aspects of the programme, such as greater, perceived patient involvement in care. The authors reported how this case study approach provided a number of contextual factors likely to influence the effectiveness of the intervention and which were not likely to have been obtained from quantitative methods alone.

In collective or multiple case studies, data collection needs to be flexible enough to allow a detailed description of each individual case to be developed (e.g. the nature of different cancer care programmes), before considering the emerging similarities and differences in cross-case comparisons (e.g. to explore why one programme is more effective than another). It is important that data sources from different cases are, where possible, broadly comparable for this purpose even though they may vary in nature and depth.

Analysing, interpreting and reporting case studies

Making sense and offering a coherent interpretation of the typically disparate sources of data (whether qualitative alone or together with quantitative) is far from straightforward. Repeated reviewing and sorting of the voluminous and detail-rich data are integral to the process of analysis. In collective case studies, it is helpful to analyse data relating to the individual component cases first, before making comparisons across cases. Attention needs to be paid to variations within each case and, where relevant, the relationship between different causes, effects and outcomes[ 23 ]. Data will need to be organised and coded to allow the key issues, both derived from the literature and emerging from the dataset, to be easily retrieved at a later stage. An initial coding frame can help capture these issues and can be applied systematically to the whole dataset with the aid of a qualitative data analysis software package.

The Framework approach is a practical approach, comprising of five stages (familiarisation; identifying a thematic framework; indexing; charting; mapping and interpretation) , to managing and analysing large datasets particularly if time is limited, as was the case in our study of recruitment of South Asians into asthma research (Table ​ (Table1 1 )[ 3 , 24 ]. Theoretical frameworks may also play an important role in integrating different sources of data and examining emerging themes. For example, we drew on a socio-technical framework to help explain the connections between different elements - technology; people; and the organisational settings within which they worked - in our study of the introduction of electronic health record systems (Table ​ (Table3 3 )[ 5 ]. Our study of patient safety in undergraduate curricula drew on an evaluation-based approach to design and analysis, which emphasised the importance of the academic, organisational and practice contexts through which students learn (Table ​ (Table4 4 )[ 6 ].

Case study findings can have implications both for theory development and theory testing. They may establish, strengthen or weaken historical explanations of a case and, in certain circumstances, allow theoretical (as opposed to statistical) generalisation beyond the particular cases studied[ 12 ]. These theoretical lenses should not, however, constitute a strait-jacket and the cases should not be "forced to fit" the particular theoretical framework that is being employed.

When reporting findings, it is important to provide the reader with enough contextual information to understand the processes that were followed and how the conclusions were reached. In a collective case study, researchers may choose to present the findings from individual cases separately before amalgamating across cases. Care must be taken to ensure the anonymity of both case sites and individual participants (if agreed in advance) by allocating appropriate codes or withholding descriptors. In the example given in Table ​ Table3, 3 , we decided against providing detailed information on the NHS sites and individual participants in order to avoid the risk of inadvertent disclosure of identities[ 5 , 25 ].

What are the potential pitfalls and how can these be avoided?

The case study approach is, as with all research, not without its limitations. When investigating the formal and informal ways undergraduate students learn about patient safety (Table ​ (Table4), 4 ), for example, we rapidly accumulated a large quantity of data. The volume of data, together with the time restrictions in place, impacted on the depth of analysis that was possible within the available resources. This highlights a more general point of the importance of avoiding the temptation to collect as much data as possible; adequate time also needs to be set aside for data analysis and interpretation of what are often highly complex datasets.

Case study research has sometimes been criticised for lacking scientific rigour and providing little basis for generalisation (i.e. producing findings that may be transferable to other settings)[ 1 ]. There are several ways to address these concerns, including: the use of theoretical sampling (i.e. drawing on a particular conceptual framework); respondent validation (i.e. participants checking emerging findings and the researcher's interpretation, and providing an opinion as to whether they feel these are accurate); and transparency throughout the research process (see Table ​ Table8 8 )[ 8 , 18 - 21 , 23 , 26 ]. Transparency can be achieved by describing in detail the steps involved in case selection, data collection, the reasons for the particular methods chosen, and the researcher's background and level of involvement (i.e. being explicit about how the researcher has influenced data collection and interpretation). Seeking potential, alternative explanations, and being explicit about how interpretations and conclusions were reached, help readers to judge the trustworthiness of the case study report. Stake provides a critique checklist for a case study report (Table ​ (Table9 9 )[ 8 ].

Potential pitfalls and mitigating actions when undertaking case study research

Stake's checklist for assessing the quality of a case study report[ 8 ]

Conclusions

The case study approach allows, amongst other things, critical events, interventions, policy developments and programme-based service reforms to be studied in detail in a real-life context. It should therefore be considered when an experimental design is either inappropriate to answer the research questions posed or impossible to undertake. Considering the frequency with which implementations of innovations are now taking place in healthcare settings and how well the case study approach lends itself to in-depth, complex health service research, we believe this approach should be more widely considered by researchers. Though inherently challenging, the research case study can, if carefully conceptualised and thoughtfully undertaken and reported, yield powerful insights into many important aspects of health and healthcare delivery.

Competing interests

The authors declare that they have no competing interests.

Authors' contributions

AS conceived this article. SC, KC and AR wrote this paper with GH, AA and AS all commenting on various drafts. SC and AS are guarantors.

Pre-publication history

The pre-publication history for this paper can be accessed here:

http://www.biomedcentral.com/1471-2288/11/100/prepub

Acknowledgements

We are grateful to the participants and colleagues who contributed to the individual case studies that we have drawn on. This work received no direct funding, but it has been informed by projects funded by Asthma UK, the NHS Service Delivery Organisation, NHS Connecting for Health Evaluation Programme, and Patient Safety Research Portfolio. We would also like to thank the expert reviewers for their insightful and constructive feedback. Our thanks are also due to Dr. Allison Worth who commented on an earlier draft of this manuscript.

• Yin RK. Case study research, design and method. 4. London: Sage Publications Ltd.; 2009. [ Google Scholar ]
• Keen J, Packwood T. Qualitative research; case study evaluation. BMJ. 1995; 311 :444–446. [ PMC free article ] [ PubMed ] [ Google Scholar ]
• Sheikh A, Halani L, Bhopal R, Netuveli G, Partridge M, Car J. et al. Facilitating the Recruitment of Minority Ethnic People into Research: Qualitative Case Study of South Asians and Asthma. PLoS Med. 2009; 6 (10):1–11. [ PMC free article ] [ PubMed ] [ Google Scholar ]
• Pinnock H, Huby G, Powell A, Kielmann T, Price D, Williams S, The process of planning, development and implementation of a General Practitioner with a Special Interest service in Primary Care Organisations in England and Wales: a comparative prospective case study. Report for the National Co-ordinating Centre for NHS Service Delivery and Organisation R&D (NCCSDO) 2008. http://www.sdo.nihr.ac.uk/files/project/99-final-report.pdf
• Robertson A, Cresswell K, Takian A, Petrakaki D, Crowe S, Cornford T. et al. Prospective evaluation of the implementation and adoption of NHS Connecting for Health's national electronic health record in secondary care in England: interim findings. BMJ. 2010; 41 :c4564. [ PMC free article ] [ PubMed ] [ Google Scholar ]
• Pearson P, Steven A, Howe A, Sheikh A, Ashcroft D, Smith P. the Patient Safety Education Study Group. Learning about patient safety: organisational context and culture in the education of healthcare professionals. J Health Serv Res Policy. 2010; 15 :4–10. doi: 10.1258/jhsrp.2009.009052. [ PubMed ] [ CrossRef ] [ Google Scholar ]
• van Harten WH, Casparie TF, Fisscher OA. The evaluation of the introduction of a quality management system: a process-oriented case study in a large rehabilitation hospital. Health Policy. 2002; 60 (1):17–37. doi: 10.1016/S0168-8510(01)00187-7. [ PubMed ] [ CrossRef ] [ Google Scholar ]
• Stake RE. The art of case study research. London: Sage Publications Ltd.; 1995. [ Google Scholar ]
• Sheikh A, Smeeth L, Ashcroft R. Randomised controlled trials in primary care: scope and application. Br J Gen Pract. 2002; 52 (482):746–51. [ PMC free article ] [ PubMed ] [ Google Scholar ]
• King G, Keohane R, Verba S. Designing Social Inquiry. Princeton: Princeton University Press; 1996. [ Google Scholar ]
• Doolin B. Information technology as disciplinary technology: being critical in interpretative research on information systems. Journal of Information Technology. 1998; 13 :301–311. doi: 10.1057/jit.1998.8. [ CrossRef ] [ Google Scholar ]
• George AL, Bennett A. Case studies and theory development in the social sciences. Cambridge, MA: MIT Press; 2005. [ Google Scholar ]
• Eccles M. the Improved Clinical Effectiveness through Behavioural Research Group (ICEBeRG) Designing theoretically-informed implementation interventions. Implementation Science. 2006; 1 :1–8. doi: 10.1186/1748-5908-1-1. [ PMC free article ] [ PubMed ] [ CrossRef ] [ Google Scholar ]
• Netuveli G, Hurwitz B, Levy M, Fletcher M, Barnes G, Durham SR, Sheikh A. Ethnic variations in UK asthma frequency, morbidity, and health-service use: a systematic review and meta-analysis. Lancet. 2005; 365 (9456):312–7. [ PubMed ] [ Google Scholar ]
• Sheikh A, Panesar SS, Lasserson T, Netuveli G. Recruitment of ethnic minorities to asthma studies. Thorax. 2004; 59 (7):634. [ PMC free article ] [ PubMed ] [ Google Scholar ]
• Hellström I, Nolan M, Lundh U. 'We do things together': A case study of 'couplehood' in dementia. Dementia. 2005; 4 :7–22. doi: 10.1177/1471301205049188. [ CrossRef ] [ Google Scholar ]
• Som CV. Nothing seems to have changed, nothing seems to be changing and perhaps nothing will change in the NHS: doctors' response to clinical governance. International Journal of Public Sector Management. 2005; 18 :463–477. doi: 10.1108/09513550510608903. [ CrossRef ] [ Google Scholar ]
• Lincoln Y, Guba E. Naturalistic inquiry. Newbury Park: Sage Publications; 1985. [ Google Scholar ]
• Barbour RS. Checklists for improving rigour in qualitative research: a case of the tail wagging the dog? BMJ. 2001; 322 :1115–1117. doi: 10.1136/bmj.322.7294.1115. [ PMC free article ] [ PubMed ] [ CrossRef ] [ Google Scholar ]
• Mays N, Pope C. Qualitative research in health care: Assessing quality in qualitative research. BMJ. 2000; 320 :50–52. doi: 10.1136/bmj.320.7226.50. [ PMC free article ] [ PubMed ] [ CrossRef ] [ Google Scholar ]
• Mason J. Qualitative researching. London: Sage; 2002. [ Google Scholar ]
• Brazier A, Cooke K, Moravan V. Using Mixed Methods for Evaluating an Integrative Approach to Cancer Care: A Case Study. Integr Cancer Ther. 2008; 7 :5–17. doi: 10.1177/1534735407313395. [ PubMed ] [ CrossRef ] [ Google Scholar ]
• Miles MB, Huberman M. Qualitative data analysis: an expanded sourcebook. 2. CA: Sage Publications Inc.; 1994. [ Google Scholar ]
• Pope C, Ziebland S, Mays N. Analysing qualitative data. Qualitative research in health care. BMJ. 2000; 320 :114–116. doi: 10.1136/bmj.320.7227.114. [ PMC free article ] [ PubMed ] [ CrossRef ] [ Google Scholar ]
• Cresswell KM, Worth A, Sheikh A. Actor-Network Theory and its role in understanding the implementation of information technology developments in healthcare. BMC Med Inform Decis Mak. 2010; 10 (1):67. doi: 10.1186/1472-6947-10-67. [ PMC free article ] [ PubMed ] [ CrossRef ] [ Google Scholar ]
• Malterud K. Qualitative research: standards, challenges, and guidelines. Lancet. 2001; 358 :483–488. doi: 10.1016/S0140-6736(01)05627-6. [ PubMed ] [ CrossRef ] [ Google Scholar ]
• Yin R. Case study research: design and methods. 2. Thousand Oaks, CA: Sage Publishing; 1994. [ Google Scholar ]
• Yin R. Enhancing the quality of case studies in health services research. Health Serv Res. 1999; 34 :1209–1224. [ PMC free article ] [ PubMed ] [ Google Scholar ]
• Green J, Thorogood N. Qualitative methods for health research. 2. Los Angeles: Sage; 2009. [ Google Scholar ]
• Howcroft D, Trauth E. Handbook of Critical Information Systems Research, Theory and Application. Cheltenham, UK: Northampton, MA, USA: Edward Elgar; 2005. [ Google Scholar ]
• Blakie N. Approaches to Social Enquiry. Cambridge: Polity Press; 1993. [ Google Scholar ]
• Doolin B. Power and resistance in the implementation of a medical management information system. Info Systems J. 2004; 14 :343–362. doi: 10.1111/j.1365-2575.2004.00176.x. [ CrossRef ] [ Google Scholar ]
• Bloomfield BP, Best A. Management consultants: systems development, power and the translation of problems. Sociological Review. 1992; 40 :533–560. [ Google Scholar ]
• Shanks G, Parr A. Proceedings of the European Conference on Information Systems. Naples; 2003. Positivist, single case study research in information systems: A critical analysis. [ Google Scholar ]

• International

Supreme Court hears case about emergency abortion care

By CNN's Tierney Sneed, John Fritze, Hannah Rabinowitz, Jen Christensen and Holmes Lybrand

Key takeaways from today's Supreme Court oral arguments over emergency abortions

From CNN's Tierney Sneed and John Fritze

The Supreme Court heard oral arguments Wednesday on whether Idaho’s abortion ban can be enforced in medical emergencies, putting a spotlight on what has been one of the most politically explosive flashpoints in the aftermath of Roe v. Wade’s demise. 

Here are key takeaways from today's high-stakes hearing :

US solicitor general tailors her appeal to an abortion-hostile court as "narrow" circumstances of medical emergencies: US Solicitor General Elizabeth Prelogar said that there was a real conflict between Idaho’s law and the federal law, known as the Emergency Medical Treatment and Labor Act (EMTALA), but she painted it as a narrow one. She stressed that, in this case, the administration is not trying to interfere with Idaho’s overall ability to criminalize abortions outside of certain medical emergencies.

Idaho and its defenders argue that the Biden administration is trying to circumvent the Supreme Court’s 2022 ruling that let states prohibit abortion, and to rebut that argument, Prelogar described Idaho has an outlier among states that have banned the procedure.

Prelogar’s argument was met with deep skepticism from several of the court’s conservative justices, but others – including Chief Justice John Roberts and Amy Coney Barrett– asked probing questions of both sides. The court’s liberal wing, meanwhile, all signaled they would coalesce around the Biden administration.

Idaho attorney struggles with questions from female justices about serious pregnancy complications: Idaho’s attorney Joshua Turner was subjected to a brutal and extended line of questioning from the female justices of the court exploring how the state’s abortion ban plays out in medical emergencies – particularly in dire situations where a woman’s health is at risk but her life is not yet in danger.

Justice Sonia Sotomayor asked Turner point blank: “What you are saying is that there is no federal law on the book that prohibits any state from saying, even if a woman will die, you can’t perform an abortion?”

Justice Elena Kagan offered a hypothetical in which a woman was about to lose her reproductive organs due to a pregnancy complication. As Turner danced around the “difficult” and “tough” situation her question as posing, she pushed harder: “That would be a good response if federal law did not take a position on what you characterize as a ‘tough question.’”

Keep reading takeaways from the arguments.

Supreme Court justices appear divided on abortion case, with Roberts and Barrett emerging as key votes 

From CNN's Tierney Sneed

In a Supreme Court  hearing on the Biden administration’s challenge to aspects of Idaho’s strict abortion ban , US Solicitor General  Elizabeth Prelogar  sought to appeal to conservative justices who just two years ago ruled that states should have the ability to prohibit the procedure.

The dispute, stemming from the Justice Department’s marquee response to the high court’s reversal of Roe v. Wade in 2022, turns on whether federal mandates for hospital emergency room care override abortion bans that do not exempt situations where a woman’s health is in danger but her life is not yet threatened.

To prevail, the Biden administration will need the votes of two members of the court’s conservative bloc, and with Justice Brett Kavanaugh signaling sympathies toward Idaho, the case will likely come down to the votes of Chief Justice John Roberts and Amy Coney Barrett. The two justices had tough questions for both sides of the case.

The court’s far-right wing, perhaps in an attempt to keep those two justices on their side, framed the case as a federal overreach into state power. The court’s liberals, meanwhile, focused on the grisly details of medical emergencies faced by pregnant woman that were not covered by the limited life-of-the-woman exemption in Idaho’s ban.

Having access to safe abortion is critical for a safe health care system, doctor from rural Idaho says

From CNN's Maureen Chowdhury

Dr. Caitlin Gustafson, a family medicine physician from rural Idaho, said having access to safe abortions should be a standard of care in order to have a safe health care system.

Speaking to CNN right outside of the Supreme Court, Gustafson said that she has seen Idaho's health care system "fall apart" since the abortion ban went into effect.

"We have lost a multitude of providers, particularly my OB-GYN colleagues who cannot continue to have themselves in the position of trying to make these decisions in emergencies, where a patient's heath and life threatened," she said, noting that if they make the wrong decision at the wrong moment, they may go to jail or lose their license.

Gustafson said that believes the Supreme Court's decision, based on today's arguments regarding whether Idaho's abortion ban can be enforced in medical emergencies , puts safe emergency health care across the board is at risk.

"This isn't just about abortion, this is about a protection of — a life saving protection we've had in place that keeps any person, including our pregnant patients who come to the emergency room safe," she said.

The federal law is what doctors across the country has "grown up under and it's what keeps everyone safe" she said. Gustafson also noted that she's seen a distinct change in the health care system in Idaho since doctors in the state lost this protection and says it is "untenable."

US solicitor general compares Idaho abortion law to hypothetical ban on epinephrine

From CNN's Holmes Lybrand

US Solicitor General Elizabeth Prelogar argued today that Idaho’s abortion law is akin to a ban on epinephrine, which treats severe allergic reactions.

Prelogar noted federal law mandates that if a person has an emergency medical condition and goes to an emergency room, “they have to stabilize you."

“Congress did not provide a reticulated list of all possible emergency medical conditions and all possible treatments,” she said. “But it was very clear that Congress set a baseline national standard of care to ensure that no matter where you live in this country you can’t be declined service.”

Of Idaho’s abortion law, Prelogar said: “It would be no different if the state had come out and decided to ban epinephrine."

“I don’t see any way to try to draw lines around to exclude pregnancy complications,” she added.

Supreme Court arguments on historic abortion case have concluded

From CNN's John Fritze

Supreme Court arguments in the historic abortion case have concluded. 

Now the justices will begin drafting an opinion – or several. That process usually takes a few months. In this case, the court is expected to hand down its ruling by the end of June.

US solicitor general and Alito go head-to-head

From CNN's Hannah Rabinowitz

In a tense exchange over how federal protections extend to a fetus, US Solicitor General Elizabeth Prelogar argued that women “deserve” medical treatment whenever it is needed.

Prelogar and Conservative Justice Samuel Alito went head-to-head as part of a line of questioning from the justice over whether, in enacting the federal law EMTALA, lawmakers were aiming to give protections to an “unborn child" — a term that is included in multiple provisions of the law.

Prelogar said the law states there is a duty for doctors to act when a pregnant person is “suffering some kind of emergency and her own health isn’t at risk, but the fetus might die,” like in the case of a prolapse of the umbilical cord into the cervix.

“But to suggest that in doing so," Prelogar said, "Congress suggested that the woman herself isn’t an individual, that she doesn’t deserve stabilization — I think that that is an erroneous reading of this."

Alito snapped back: “Nobody’s suggesting that a woman is not an individual and she doesn’t deserve stabilization.”

US solicitor general cites 1800s SCOTUS decision in abortion arguments

US Solicitor General Elizabeth Prelogar argued that the federal government has an interest to “protect its sovereign interest,” noting that “Idaho has directly interfered with the ability of hospitals to accept” federal funds through its abortion law.

Prelogar said several cases address the issue of proprietary interest, citing a case from the late 1800s in which the US Supreme Court unanimously upheld the federal government’s injunction to stop a labor strike related to US railroads.

Prelogar cited the Supreme Court’s ruling in the case, known as In re Debs, during arguments against Idaho’s abortion law.

Justice Neil Gorsuch reacted: “Debs? You really want to rely on Debs, general? I mean that wasn’t exactly our brightest moment."

“I do think though that it reflects the history and tradition of this nation in recognizing that it’s entirely appropriate for the United States to seek to protect its interests in this manner,” Prelogar said.

Alito brings up the "unborn child" debate

Conservative Justice Samuel Alito asked US Solicitor General Elizabeth Prelogar to explain why the federal law in question, the Emergency Medical Treatment and Labor Act (EMTALA), uses the term “unborn child.”

“It’s not an odd phrase when you look at what Congress was doing,” at the time Prelogar said. The law was amended to add the term in 1989.

“There were well publicized cases where women were experiencing conditions their own health and life were not in danger, but the fetus was engraved distress and hospitals weren’t treating them," Prelogar said.

The term is referenced multiple times in law, including in the definition of a medical emergency scenario where the health of an unborn child is in serious jeopardy, where restricting the transfer of a patient in labor would put the safety of the unborn child at risk. 

The Charlotte Lozier Institute, an anti-abortion think tank, said in a friend-of-the-court brief that that EMTALA “expressly protects the lives of unborn children” and that it requires hospitals to “to follow the two-patient paradigm to protect both the mother and her unborn child.”   

“The United States’ attempt to diminish the ‘unborn child’s’ life as secondary—one that must be protected only if her mother’s health is not threatened but loses all value if her mother’s health is in jeopardy—is atextual,” the brief said. “Congress expected hospitals and physicians to preserve both lives wherever possible.”  

After Idaho’s abortion ban, more patients have been transferred out of state for emergency abortion care

From CNN Health's Meg Tirrell, Carma Hassan and Jamie Gumbrecht

If a pregnant woman in Idaho comes to an emergency room facing a grave threat to health but isn’t facing death, doctors have to delay her care until she deteriorates “or they’re airlifting her out of the state so she can get the emergency care that she needs,” US Solicitor General Elizabeth Prelogar said in her argument.

“One hospital system in Idaho says that right now, it's having to transfer pregnant women in medical crisis out of the state about once every other week,” she said.

There has been an uptick in the number of patients transferred for life-saving abortions after Idaho  banned the procedure , according to Dr. Jim Souza, the chief physician executive for Boise-based St. Luke’s Health System.

St. Luke's, Idaho's largest hospital system, wrote in a  friend-of-the-court brief  that the legal uncertainty created by the state's abortion ban means patients with emergency pregnancy complications are more likely to be transferred out of state for care unless they're at "imminent risk of death."

Souza said that in 2023, during an injunction on enforcement of the law as it pertained to the Emergency Medical Treatment and Labor Act (EMTALA), only one patient in the emergency department was recommended to be transferred out of the state.

“In the short period of time, it’s been just a few months now that Idaho’s law has been in effect, six patients with medical emergencies have already been transferred out of state for termination,” Souza said in a call with reporters last week. “If we annualize that, we can anticipate up to 20 patients needing out-of-state care this year alone.”

Dr. Julie Lyons, a family medicine physician with St. Luke’s Health System, told CNN in February that she counsels patients on their first prenatal visit to "buy life-flight insurance," in case they face a "rare situation that a complication does happen."

Some doctors have also left Idaho as a result of the law, Souza said, creating a “destabilizing effect” on the hospital system.

Please enable JavaScript for a better experience.