Generation of Case-Based Materials Using Large Language Models in Health Professions Education: Scoping Review
6 affiliations
- 1Clinical Bioinformatics Laboratory, Imagine Institute, Université Paris Cité, INSERM UMR1163, 24 Bd du Montparnasse, 75015, Paris, F-75006, France, 33 668169844
- 2Department of Medical Informatics, Hôpital Européen Georges Pompidou, Hôpital Necker Enfants Malades, AP-HP, Paris, France
- 3Faculté de Santé, DigiHealth UPCité Team, Université Paris Cité, Paris, F-75006, France
- 4Biostatistics and Medical Information Department, Saint-Louis Hospital, Assistance Publique Hôpitaux de Paris, Paris, France
- 5Medical Intensive Care Unit, Cochin Hospital, Assistance Publique-Hôpitaux de Paris, Paris, France
- 6UPPERS, Université Paris Cité, US 007, Paris, F-75006, France
Abstract
Background: Large language models (LLMs) are increasingly used to generate case-based materials for health professions education (HPE). Previous reviews have examined broad applications in HPE or focused on clinical cases, but none have comprehensively synthesized the generation and evaluation of diverse case-based materials.
Objective: This study aims to synthesize current evidence on LLM-generated case-based materials in HPE, focusing on generation approaches, evaluation methods, key findings, and reported challenges.
Methods: This scoping review followed the Joanna Briggs Institute methodology and PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) reporting guidelines. Seven databases (PubMed, Embase, Scopus, Web of Science, CINAHL, ERIC, and IEEE Xplore) were searched on May 10, 2026, for studies published from January 1, 2017. Eligible studies were peer-reviewed original research articles, published in English, reporting the use of generative LLMs to create text-based case-based materials for HPE. Data were synthesized using descriptive statistics and narrative synthesis.
Results: Seventy-two studies were included. Most were published between 2024 and 2026 (67/72, 93%) and focused on medical education (59/72, 82%), with undergraduate students as the most frequently studied population. Case-based multiple-choice questions (MCQs; 28/72, 39%) and clinical cases or vignettes (22/72, 30%) were the most frequently generated materials. Generative Pretrained Transformer-4 (GPT-4) family models were the most commonly used (40/72, 55%), and generation predominantly relied on relatively simple prompting approaches, whereas more advanced strategies, such as few-shot prompting, prompt chaining, or use of external knowledge sources, were rarely adopted. Evaluation primarily relied on expert review, typically involving small panels, while student assessment (25/72, 35%) and psychometric analyses were less common. Overall, LLM-generated materials were frequently judged to be clinically plausible, structurally clear, and reasonably aligned with educational objectives, particularly after refinement. However, consistent limitations included factual inaccuracies, construction flaws, superficial clinical realism, pedagogical misalignment, suboptimal psychometric performance, and bias. No LLM consistently outperformed others, although methodological heterogeneity limits cross-study comparisons.
Conclusions: This review provides a comprehensive synthesis of the literature on LLM-generated case-based materials in HPE. Unlike previous reviews examining broad educational applications or focusing on clinical cases, it integrates evidence across a broad range of case-based materials while synthesizing generation methods, evaluation approaches, reported findings, and challenges. The evidence suggests that LLMs can support the development of case-based materials but still require expert oversight because of recurring concerns regarding clinical accuracy, educational quality, psychometric performance, clinical realism, and bias. By identifying methodological and evidence gaps, this review provides educators, curriculum developers, and researchers with a structured overview of this rapidly evolving field and may inform the development of more robust generation workflows, more standardized evaluation approaches, and the responsible use of LLM-generated case-based materials in HPE.
Related
- Artificial intelligence generated virtual patients in health professions education: a scoping review.
- Readability of Retina Patient Education Materials Generated With a Large Language Model
- Who Learns from Disruption? Antifragility and Burden Transfer in Health Professions Education
- Artificial intelligence hallucinations in large language models for medical education and healthcare: a scoping review of detection, mitigation, and governance
- Beyond the clicker: rethinking student response systems as pedagogical infrastructure for healthcare professions education
BibTeX
@article{zouakia2026generation,
title = {{Generation of Case-Based Materials Using Large Language Models in Health Professions Education: Scoping Review}},
author = {Zineb Zouakia and Alan Szymczak and Salomé Tordjman and Emmanuel Logak and Thomas Meyre and Matthieu Resche-Rigon and Alain Cariou and Anita Burgun and Rosy Tsopra},
journal = {JMIR Medical Education},
year = {2026},
month = nov,
doi = {10.2196/94795},
url = {https://doi.org/10.2196/94795},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Generation of Case-Based Materials Using Large Language Models in Health Professions Education: Scoping Review
AU - Zineb Zouakia
AU - Alan Szymczak
AU - Salomé Tordjman
AU - Emmanuel Logak
AU - Thomas Meyre
AU - Matthieu Resche-Rigon
AU - Alain Cariou
AU - Anita Burgun
AU - Rosy Tsopra
PY - 2026
DA - 2026/11/03
JO - JMIR Medical Education
DO - 10.2196/94795
UR - https://doi.org/10.2196/94795
AB - Background: Large language models (LLMs) are increasingly used to generate case-based materials for health professions education (HPE). Previous reviews have examined broad applications in HPE or focused on clinical cases, but none have comprehensively synthesized the generation and evaluation of diverse case-based materials. Objective: This study aims to synthesize current evidence on LLM-generated case-based materials in HPE, focusing on generation approaches, evaluation methods, key findings, and reported challenges. Methods: This scoping review followed the Joanna Briggs Institute methodology and PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) reporting guidelines. Seven databases (PubMed, Embase, Scopus, Web of Science, CINAHL, ERIC, and IEEE Xplore) were searched on May 10, 2026, for studies published from January 1, 2017. Eligible studies were peer-reviewed original research articles, published in English, reporting the use of generative LLMs to create text-based case-based materials for HPE. Data were synthesized using descriptive statistics and narrative synthesis. Results: Seventy-two studies were included. Most were published between 2024 and 2026 (67/72, 93%) and focused on medical education (59/72, 82%), with undergraduate students as the most frequently studied population. Case-based multiple-choice questions (MCQs; 28/72, 39%) and clinical cases or vignettes (22/72, 30%) were the most frequently generated materials. Generative Pretrained Transformer-4 (GPT-4) family models were the most commonly used (40/72, 55%), and generation predominantly relied on relatively simple prompting approaches, whereas more advanced strategies, such as few-shot prompting, prompt chaining, or use of external knowledge sources, were rarely adopted. Evaluation primarily relied on expert review, typically involving small panels, while student assessment (25/72, 35%) and psychometric analyses were less common. Overall, LLM-generated materials were frequently judged to be clinically plausible, structurally clear, and reasonably aligned with educational objectives, particularly after refinement. However, consistent limitations included factual inaccuracies, construction flaws, superficial clinical realism, pedagogical misalignment, suboptimal psychometric performance, and bias. No LLM consistently outperformed others, although methodological heterogeneity limits cross-study comparisons. Conclusions: This review provides a comprehensive synthesis of the literature on LLM-generated case-based materials in HPE. Unlike previous reviews examining broad educational applications or focusing on clinical cases, it integrates evidence across a broad range of case-based materials while synthesizing generation methods, evaluation approaches, reported findings, and challenges. The evidence suggests that LLMs can support the development of case-based materials but still require expert oversight because of recurring concerns regarding clinical accuracy, educational quality, psychometric performance, clinical realism, and bias. By identifying methodological and evidence gaps, this review provides educators, curriculum developers, and researchers with a structured overview of this rapidly evolving field and may inform the development of more robust generation workflows, more standardized evaluation approaches, and the responsible use of LLM-generated case-based materials in HPE.
SN - 2369-3762
ER -