Mapping Applications and Outcomes of Large-Language-Model-Generated Cases in Health Professions Education: A Scoping Review.

Abdullah Bedir Kaya; Emre Emekli; Yavuz Selim Kiyak

doi:10.6018/edumed.691691

Autores/as

Abdullah Bedir Kaya Hitit University https://orcid.org/0000-0003-0124-2127
Emre Emekli Faculty of Medicine, Eskişehir Osmangazi University, Eskişehir, Turkiye https://orcid.org/0000-0001-5989-1897
Yavuz Selim Kiyak Faculty of Medicine, Gazi University, Ankara 06500, Turkiye https://orcid.org/0000-0002-5026-3234

DOI: https://doi.org/10.6018/edumed.691691

Palabras clave: IA, LLM, Casos clínicos

Resumen

Objetivo: Los modelos de lenguaje grande (LLM) han permeado rápidamente la educación de las profesiones de la salud y se utilizan cada vez más para generar casos clínicos y viñetas, pero sus características, métodos de evaluación e impacto educativo siguen sin estar claros. Para mapear cómo se utilizan los LLM para generar casos en la educación de las profesiones de la salud y para resumir las características de los casos informados, los enfoques de evaluación, el sesgo y los resultados educativos. Métodos: Realizamos una revisión de alcance siguiendo el marco de Arksey y O'Malley e informamos utilizando PRISMA-ScR. Se realizaron búsquedas en PubMed, Web of Science y Scopus el 27 de agosto de 2025. De 2023 registros, se evaluaron 72 textos completos y 23 estudios cumplieron los criterios de inclusión. Los datos se graficaron con un formulario de extracción estructurado. Resultados: En los 23 estudios, se utilizaron 33 LLM distintos, los modelos basados en GPT más comúnmente (54,5%). Los casos se basaron principalmente en texto (69%), con formatos adicionales basados en imágenes (20,7%) y audio (10,3%) en 23 dominios clínicos y educativos. Se informaron indicaciones en el 65,2% de los estudios y el 60,9% incluyó una evaluación de calidad formal, que abarcó desde ejemplos de alta calidad hasta claramente problemáticos. Siete estudios (30,4%) identificaron sesgos o patrones discriminatorios. La participación de los estudiantes ocurrió en el 39,1% de los estudios, pero no se informaron resultados educativos de nivel superior, como cambios de comportamiento o rendimiento a largo plazo. Conclusiones: Los casos generados por LLM parecen factibles y versátiles en la educación de las profesiones de la salud, pero están respaldados por evidencia temprana y metodológicamente heterogénea. Las investigaciones futuras deben estandarizar la evaluación de calidad, evaluar rigurosamente los resultados de aprendizaje y comportamiento, y auditar sistemáticamente el sesgo en el contenido generado.

Descargas

Los datos de descargas todavía no están disponibles.

Metrics

Vistas/Descargas

Resumen
114
pdf
55
Annex 1
7

Citas

Krystal Hu. ChatGPT sets record for fastest-growing user base - analyst note. Reuters 2023. https://www.reuters.com/technology/chatgpt-sets-record-fastest-growing-user-base-analyst-note-2023-02-01/

3. Zhang Y, Xie X, Xu Q. ChatGPT in medical education: Bibliometric and visual analysis. JMIR Med Educ. 2025, 11, e72356–e72356. https://doi.org/10.2196/72356.

4. Tsekhmister Y. Effectiveness of case-based learning in medical and pharmacy education: A meta-analysis. Electron J Gen Med. 2023, 20(5), em515. https://doi.org/10.29333/ejgm/13315.

6. Thistlethwaite JE, Davies D, Ekeocha S, Kidd JM, MacDougall C, Matthews P, et al. The effectiveness of case-based learning in health professional education. A BEME systematic review: BEME Guide No. 23. Medical Teacher 2012, 34, e421–e444. https://doi.org/10.3109/0142159X.2012.680939.

7. Arksey H, O’Malley L. Scoping studies: towards a methodological framework. International Journal of Social Research Methodology 2005, 8, 19–32. https://doi.org/10.1080/1364557032000119616.

8. Maggio LA, Samuel A, Stellrecht E. Systematic reviews in medical education. Journal of Graduate Medical Education 2022, 14, 171–175. https://doi.org/10.4300/JGME-D-22-00113.1.

9. Thomas A, Lubarsky S, Varpio L, Durning SJ, Young ME. Scoping reviews in health professions education: challenges, considerations and lessons learned about epistemology and methodology. Adv in Health Sci Educ. 2020, 25, 989–1002. https://doi.org/10.1007/s10459-019-09932-2.

10. Akutay S, Yüceler Kaçmaz H, Kahraman H. The effect of artificial intelligence supported case analysis on nursing students’ case management performance and satisfaction: A randomized controlled trial. Nurse Education in Practice 2024, 80, 104142. https://doi.org/10.1016/j.nepr.2024.104142.

11. Andrew K, Montalbano MJ. Through a Glass Darkly: Perceptions of Ethnoracial Identity in Artificial Intelligence Generated Medical Vignettes and Images. Medical Science Educator 2025, 35, 1473–1488. https://doi.org/10.1007/s40670-025-02332-9.

12. Arain SA, Akhund SA, Barakzai MA, Meo SA. Transforming medical education: Leveraging large language models to enhance PBL-a proof-of-concept study. Advances in Physiology Education 2025, 49, 398–404. https://doi.org/10.1152/advan.00209.2024.

13. Artemiou E, Hooper S, Dascanio L, Schmidt M, Gilbert G. Introducing AI-generated cases (AI-cases) & standardized clients (AI-SCs) in communication training for veterinary students: Perceptions and adoption challenges. Front Vet Sci. 2025, 11, 1504598. https://doi.org/10.3389/fvets.2024.1504598.

15. Aygün İ, Kaya M. Use of large language models for medical synthetic data generation in mental illness. IET Conf Proc. 2024, 652–656. https://doi.org/10.1049/icp.2024.1033.

16. Bakkum MJ, Hartjes MG, Piet JD, Donker EM, Likic R, Sanz E, et al. Using artificial intelligence to create diverse and inclusive medical case vignettes for education. British Journal Of Clinical Pharmacology 2024, 90, 640–648. https://doi.org/10.1111/bcp.15977.

17. Benoit JRA. ChatGPT for clinical vignette generation, revision, and evaluation. MedRxiv 2023. https://doi.org/10.1101/2023.02.04.23285478.

18. Coşkun Ö, Kıyak YS, Budakoğlu Iİ. ChatGPT to generate clinical vignettes for teaching and multiple-choice questions for assessment: A randomized controlled experiment. Medical Teacher 2025, 47, 268–274. https://doi.org/10.1080/0142159X.2024.2327477.

19. Ghaffari F, Langarizadeh M, Nabovati E, Sabery M. Effectiveness of ChatGPT for clinical scenario generation: A qualitative study. Archives Of Academic Emergency Medicine 2025, 13, e49. https://doi.org/10.22037/aaemj.v13i1.2690.

20. Higashitsuji A, Otsuka T, Watanabe K. Impact of ChatGPT on case creation efficiency and learning quality in case-based learning for undergraduate nursing students. Teaching and Learning in Nursing 2025, 20, e159–166. https://doi.org/10.1016/j.teln.2024.10.002.

21. Mondal H, Marndi G, Behera J, Mondal S. ChatGPT for teachers: Practical examples for utilizing artificial intelligence for educational purposes. Indian Journal of Vascular and Endovascular Surgery 2023, 10, 200–205. https://doi.org/10.4103/ijves.ijves_37_23.

22. Jackson ML. From cases to confidence: Developing diagnostic reasoning skills through collaborative learning in graduate nursing education. Nurs Educ Perspect. 2025, 46, 319–321. https://doi.org/10.1097/01.NEP.0000000000001438.

24. Lam G, Shammoon Y, Coulson A, Lalloo F, Maini A, Amin A, et al. Utility of large language models for creating clinical assessment items. Medical Teacher 2025, 47, 878–882. https://doi.org/10.1080/0142159X.2024.2382860.

25. Liu C, Zheng J, Liu Y, Wang X, Zhang Y, Fu Q, et al. Potential to perpetuate social biases in health care by Chinese large language models: A model evaluation study. Int J Equity Health 2025, 24, 206. https://doi.org/10.1186/s12939-025-02581-5

26. Lopez M, Goh P-S. Catering for the Needs of Diverse Patient Populations: Using ChatGPT to Design Case-Based Learning Scenarios. Med Sci Educ. 2024, 34, 319–325. https://doi.org/10.1007/s40670-024-01975-4.

27. Rao AS, Kim J, Mu A, Young CC, Kalmowitz E, Senter-Zapata M, et al. Synthetic medical education in dermatology leveraging generative artificial intelligence. Npj Digit Med. 2025, 8, 247. https://doi.org/10.1038/s41746-025-01650-x.

28. Ruiz Sarrias O, Martínez Del Prado MP, Sala Gonzalez MÁ, Azcuna Sagarduy J, Casado Cuesta P, Figaredo Berjano C, et al. Leveraging large language models for precision monitoring of chemotherapy-induced toxicities: A pilot study with expert comparisons and future directions. Cancers 2024, 16, 2830. https://doi.org/10.3390/cancers16162830.

29. Silvestri-Elmore A, Burton C. How can nursing faculty create case studies using AI and educational technology? Nurse Educator 2025, 50, 35–39. https://doi.org/10.1097/NNE.0000000000001734.

30. Sridharan K, Sequeira RP. Evaluation of artificial intelligence‐generated drug therapy communication skill competencies in medical education. Br J Clin Pharmacol. 2025, 91, 2168–2175. https://doi.org/10.1111/bcp.16144.

31. Xie W, Yuan Z, Si Y, Huang Z, Li Y, Wu F, et al. Enhancing medical students’ diagnostic accuracy of infectious keratitis with AI-generated images. BMC Medical Education 2025, 25, 1027. https://doi.org/10.1186/s12909-025-07592-y.

32. Yanagita Y, Yokokawa D, Uchida S, Li Y, Uehara T, Ikusaka M. Can AI-Generated clinical vignettes in japanese be used medically and linguistically? J Gen Intern Med. 2024, 39, 3282–3289. https://doi.org/10.1007/s11606-024-09031-y.

33. Zack T, Lehman E, Suzgun M, Rodriguez JA, Celi LA, Gichoya J, et al. Assessing the potential of GPT-4 to perpetuate racial and gender biases in health care: a model evaluation study. The Lancet Digital Health 2024, 6, e12–22. https://doi.org/10.1016/S2589-7500(23)00225-X.

34. Zhong D, Chow SKK. Investigating the potential of generative AI clinical case‐based simulations on radiography education: A pilot study. Journal of Imaging Informatics in Medicine 2025, 1–13. https://doi.org/10.1007/s10278-025-01601-8.

35. Lees N. The Brandt Line after forty years: The more North–South relations change, the more they stay the same? Rev Int Stud. 2021, 47(1), 85–106. https://doi.org/10.1017/S026021052000039X.

36. Mayer R. Multimedia Learning. 3rd ed. Cambridge University Press; 2020. https://doi.org/10.1017/9781316941355.

37. Feigerlova E, Hani H, Hothersall-Davies E. A systematic review of the impact of artificial intelligence on educational outcomes in health professions education. BMC Med Educ. 2025, 25, 129. https://doi.org/10.1186/s12909-025-06719-5.