基于LLM生成完整OSCE案例的可行性研究
Extending synthetic medical education: generating OSCE cases with LLMs
研究团队开发了大型语言模型工具以生成完整的结构化临床评估(OSCE)站点,包括考生指令、标准患者脚本及评分方案。三名认证内科专家评估了涵盖8种诊断和3个学习者层级的24个生成案例,结果显示沟通行为评分最高(4.64/5),指南一致性评分最低(4.24/5)。该研究证实单次结构化调用即可生成经模式验证的高质量OSCE站点,并指出指南一致性需加强专家监督。
- Article
- Open access
- Published: 19 October 2026
- Kaiz P. Esmail1,2 na1,
- Arya S. Rao ORCID: orcid.org/0000-0003-3007-48121,2 na1,
- Richard S. Lee1,2,
- Ali Ebada ORCID: orcid.org/0009-0008-6870-00692,3,
- David C. Whitehead1,2,4,
- Caroline Meehan4,
- Andrew Cheung5 &
- …
- Marc D. Succi ORCID: orcid.org/0000-0002-1518-39841,2,4
npj Digital Medicine (2026) Cite this article
We’re sharing this article early to provide faster access to peer-reviewed, accepted research. It is citable and carries a permanent DOI. This version is subject to further edits and will be replaced automatically by the final Version of Record. All legal disclaimers apply.
Abstract
Objective Structured Clinical Examinations (OSCEs) are central to competency-based medical education, yet high-quality case development is resource-intensive. Large language models (LLMs) offer a scalable solution, but comprehensive OSCE case generation, including components such as candidate instructions, standardized patient scripts, and examiner marking schemes, is underexplored. We developed an LLM-based tool to generate complete OSCE stations. Three board-certified internists evaluated 24 generated cases across eight internal medicine diagnoses and three learner levels using a 12-item Likert instrument. Ratings were high across all domains; communication behaviors (4.64/5), EPA alignment (4.62/5), and overall value (4.61/5) performed best; guideline concordance scored lowest (4.24/5) with the greatest rater disagreement. As a feasibility study, these findings establish that whole, schema-validated OSCE stations can be generated from a single structured call at a quality experts rate as acceptable, while also identifying guideline concordance and difficult calibration as the domains most requiring faculty oversight -- providing reproducible infrastructure for, but not yet evidence of, effective EPA-aligned OSCE development.
Acknowledgements
Not applicable.
Funding
A.S.R. is supported in part by award Number T32GM144273 from the National Institute of General Medical Sciences. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institute of General Medical Sciences or the National Institutes of Health. This work was also supported by a Harvard Medical School Dean’s Innovation Award to A.S.R. and M.D.S.
Author information
Author notes
These authors contributed equally: Kaiz P. Esmail, Arya S. Rao.
Authors and Affiliations
Harvard Medical School, Boston, MA, USA
Kaiz P. Esmail, Arya S. Rao, Richard S. Lee, David C. Whitehead & Marc D. Succi
IO Lab, Mass General Brigham, Boston, MA, USA
Kaiz P. Esmail, Arya S. Rao, Richard S. Lee, Ali Ebada, David C. Whitehead & Marc D. Succi
University of Texas Southwestern Medical School, Dallas, TX, USA
Ali Ebada
Massachusetts General Hospital, Boston, MA, USA
David C. Whitehead, Caroline Meehan & Marc D. Succi
McMaster University, Hamilton, ON, Canada
Andrew Cheung
Authors
- Kaiz P. Esmail
- Arya S. Rao
- Richard S. Lee
- Ali Ebada
- David C. Whitehead
- Caroline Meehan
- Andrew Cheung
- Marc D. Succi
Corresponding authors
Correspondence to Arya S. Rao or Marc D. Succi.
Ethics declarations
Competing interests
Author M.D.S. is Editor-in-Chief of 2 Minute Medicine, on the Editorial Board of npj Digital Surgery, and is Guest Editor of the Journal of the American College of Radiology. M.D.S. was not involved in the journal’s review of, or decisions related to, this manuscript. The other authors declare no competing financial or non-financial 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-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, 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 you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. 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-nc-nd/4.0/.
About this article
Cite this article
Esmail, K.P., Rao, A.S., Lee, R.S. et al. Extending synthetic medical education: generating OSCE cases with LLMs. npj Digit. Med. (2026). https://doi.org/10.1038/s41746-026-03421-8
Received: 21 May 2026
Accepted: 05 October 2026
Published: 19 October 2026
DOI: https://doi.org/10.1038/s41746-026-03421-8
来源:Nature 健康护理主题 · nature.com