Applying ChatGPT to plan and create a realistic collection of virtual patients for clinical reasoning training
Open accessAbstract
BACKGROUND: Virtual patients (VPs) are useful tools in training of medical students’ clinical reasoning abilities. However, creating high-quality and peer-reviewed VPs is time-consuming and resource-intensive. Therefore, the aim of this study was to investigate whether generative artificial intelligence (AI) could facilitate the planning and creation of a diverse collection of VPs suitable for training medical students in clinical reasoning. METHODS: We used ChatGPT to generate a blueprint for 200 diverse VPs that adequately represent the population in Europe. We selected five VPs from the blueprint to be created by humans and ChatGPT. We assessed the generated blueprint for representativeness and internal consistency, and we reviewed the VPs in a multi-step, partly blinded process for didactical quality and content accuracy. Finally, we received 44 VP evaluations from medical students. RESULTS: The generated blueprint did not meet our expectations in terms of quality or representativeness and showed repetitive patterns and an unusually high number of atypical VP outlines. The ChatGPT- and human-generated VPs were comparable in terms of didactic quality and medical accuracy. Neither contained any medically incorrect information and reviewers and students could not discern significant differences. However, the five human-created VPs demonstrated a greater variety in storytelling, differential diagnosis, and patient-doctor interaction. The ChatGPT-generated VPs also included AI-generated patient images; however, we could not generate realistic clinical images. CONCLUSIONS: While we do not consider ChatGPT in its current version capable of generating a realistic blueprint for a VP collection, we believe that the process of prompting, combined with iterative discussions and refinements after each step, is promising and warrants further exploration. Similarly, although ChatGPT-generated VPs can serve as a good starting point, the variety of VP scenarios in a large collection may be limited without interactions between authors and reviewers to further refine it.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Early educational research suggests that AI-generated virtual patients may improve learners' engagement, provide unlimited practice opportunities, and support consistent exposure to rare or sensitive clinical presentations.
“Early educational research suggests that AI-generated virtual patients may improve learners’ engagement [8, 9], provide unlimited practice opportunities [10–12], and support consistent exposure to rare or sensitive clinical presentations.”
From Utilizing generative artificial intelligence to create simulated patient for history taking in gynecology (2026) · cites this paper as [9]
The Background describes virtual patients as a safe way to practise clinical reasoning, and Results > Evaluation reports students’ ratings of AI-generated cases as learning experiences. The paper does not establish unlimited practice opportunities. Discussion > Creation of VPs also cautions that AI-generated collections may lack variety, so it does not support the claimed consistent exposure to rare or sensitive presentations. No page numbers were available in our copy. (LLM, conf=0.85)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Dave, T., Athaluri, S. A., & Singh, S. (2023) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2023.1169595 · Cited by 1,204 · see citing works
Eysenbach, G. (2023) · JMIR Medical Education · doi:10.2196/46885 · Cited by 840 · see citing works
A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT
White, J., Fu, Q., Hays, S., Sandborn, M., Olea, C., Gilbert, H., Elnashar, A., Spencer-Smith, J., & Schmidt, D. C. (2023) · arXiv · doi:10.48550/arxiv.2302.11382 · Cited by 838 · see citing works
Kononowicz, A. A., Woodham, L. A., Edelbring, S., Stathakarou, N., Davies, D., Saxena, N., Tudor Car, L., Carlstedt-Duke, J., Car, J., & Zary, N. (2019) · Journal of Medical Internet Research · doi:10.2196/14676 · Cited by 600 · see citing works
Self-citationA scoping review of artificial intelligence in medical education: BEME Guide No. 84
Gordon, M., Daniel, M., Ajiboye, A., Uraiby, H., Xu, N. Y., Bartlett, R., Hanson, J., Haas, M., Spadafore, M., Grafton-Clarke, C., et al. (2024) · Medical Teacher · doi:10.1080/0142159x.2024.2314198 · Cited by 543 · cited 1× · see citing works
“To review and refine ChatGPT-generated VPs, they still need training and experience in creating and reviewing VPs, which could be lost by relying on Chat-GPT [64].”
Zack, T., Lehman, E., Suzgun, M., Rodriguez, J. A., Celi, L. A., Gichoya, J., Jurafsky, D., Szolovits, P., Bates, D. W., Abdulnour, R.-E. E., et al. (2024) · The Lancet Digital Health · doi:10.1016/s2589-7500(23)00225-x · Cited by 510 · see citing works
(2018) · Europe PMC (PubMed Central) · Cited by 409 · see citing works
Using ChatGPT to write patient clinic letters
Ali, S. R., Dobbs, T. D., Hutchings, H. A., & Whitaker, I. S. (2023) · The Lancet Digital Health · doi:10.1016/s2589-7500(23)00048-1 · Cited by 375 · see citing works
Kim, S., Phillips, W. R., Pinsky, L. E., Brock, D., Phillips, K. A., & Keary, J. (2006) · Medical Education · doi:10.1111/j.1365-2929.2006.02544.x · Cited by 358 · see citing works
A systematic review of large language models and their implications in medical education
Lucas, H. C., Upperman, J. S., & Robinson, J. R. (2024) · Medical Education · doi:10.1111/medu.15402 · Cited by 287 · see citing works
Virtual Patient Simulation at U.S. and Canadian Medical Schools
Huang, G. C., Reynolds, R., & Candler, C. S. (2007) · Academic Medicine · doi:10.1097/acm.0b013e31803e8a0a · Cited by 235 · see citing works
Kosmyna, N., Hauptmann, E., Yuan, Y. T., Situ, J., Liao, X.-H., Beresnitzky, A. V., Braunstein, I., & Maes, P. (2025) · arXiv · doi:10.48550/arxiv.2506.08872 · Cited by 220 · cited 1× · see citing works
“This sense of ownership and responsibility for a VP did not emerge with the ChatGPT-generated VPs - a phenomenon that has also been described for essay writing in a recent study by Kosmyna et al. [60].”
Choudhury, A., & Chaudhry, Z. (2024) · Journal of Medical Internet Research · doi:10.2196/56764 · Cited by 159 · see citing works
Kıyak, Y. S., & Emekli, E. (2024) · Postgraduate Medical Journal · doi:10.1093/postmj/qgae065 · Cited by 139 · see citing works
COGNITION, CONFIDENCE, AND CLINICAL SKILLS
Chang, R. W., Bordage, G., & Connell, K. J. (1998) · Academic Medicine · doi:10.1097/00001888-199810000-00062 · Cited by 113 · see citing works
Design principles for virtual patients: a focus group study among students
Huwendiek, S., Reichert, F., Bosse, H. M., de Leng, B. A., van der Vleuten, C. P. M., Haag, M., Hoffmann, G. F., & Tönshoff, B. (2009) · Medical Education · doi:10.1111/j.1365-2923.2009.03369.x · Cited by 108 · see citing works
Harnessing the potential of large language models in medical education: promise and pitfalls
Benítez, T. M., Xu, Y., Boudreau, J. D., Kow, A. W. C., Bello, F., Van Phuoc, L., Wang, X., Sun, X., Leung, G. K.-K., Lan, Y., et al. (2024) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocad252 · Cited by 100 · see citing works
Çiçek, F. E., Ülker, M., Özer, M., & Kıyak, Y. S. (2024) · Postgraduate Medical Journal · doi:10.1093/postmj/qgae170 · Cited by 82 · see citing works
Virtual patient simulation: what do students make of it? A focus group study
Botezatu, M., Hult, H., & Fors, U. (2010) · BMC Medical Education · doi:10.1186/1472-6920-10-91 · Cited by 81 · see citing works
Creating virtual patients using large language models: scalable, global, and low cost
Cook, D. A. (2025) · Medical Teacher · doi:10.1080/0142159x.2024.2376879 · Cited by 73 · see citing works
The Utility of Virtual Patient Simulations for Clinical Reasoning Education
Watari, T., Tokuda, Y., Owada, M., & Onigata, K. (2020) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph17155325 · Cited by 65 · see citing works
A Clinical Reasoning Tool for Virtual Patients: Design-Based Research Study
Hege, I., Kononowicz, A. A., & Adler, M. (2017) · JMIR Medical Education · doi:10.2196/mededu.8100 · Cited by 58 · see citing works
Self-citationUsing artificial intelligence to create diverse and inclusive medical case vignettes for education
Bakkum, M. J., Hartjes, M. G., Piët, J. D., Donker, E. M., Likic, R., Sanz, E., de Ponti, F., Verdonk, P., Richir, M. C., van Agtmael, M. A., et al. (2024) · British Journal of Clinical Pharmacology · doi:10.1111/bcp.15977 · Cited by 56 · see citing works
Plackett, R., Kassianos, A. P., Kambouri, M. A., Kay, N., Mylan, S., Hopwood, J., Schartau, P., Gray, S., Timmis, J., Bennett, S., et al. (2020) · BMC Medical Education · doi:10.1186/s12909-020-02168-4 · Cited by 48 · see citing works
Emerging Roles of Virtual Patients in the Age of AI
Combs, C. D., & Combs, P. F. (2019) · The AMA Journal of Ethic · doi:10.1001/amajethics.2019.153 · Cited by 46 · see citing works
Generative AI in Undergraduate Medical Education: A Rapid Review
Hale, J., Alexander, S., Wright, S. T., & Gilliland, K. (2024) · Journal of Medical Education and Curricular Development · doi:10.1177/23821205241266697 · Cited by 46 · see citing works
Hege, I., Kononowicz, A. A., Berman, N. B., Lenzer, B., & Kiesewetter, J. (2018) · PubMed Central · doi:10.3205/zma001159 · Cited by 42 · see citing works
Self-citationAI in medical education: uses of AI in construction type A MCQs
Rezigalla, A. A. (2024) · BMC Medical Education · doi:10.1186/s12909-024-05250-3 · Cited by 36 · see citing works
Huwendiek, S., de Leng, B. A., Kononowicz, A. A., Kunzmann, R., Muijtjens, A. M. M., van der Vleuten, C. P. M., Hoffmann, G. F., Tönshoff, B., & Dolmans, D. H. J. M. (2014) · Medical Teacher · doi:10.3109/0142159x.2014.970622 · Cited by 34 · see citing works
Self-citationChatGPT-Based Learning: Generative Artificial Intelligence in Medical Education
Stretton, B., Kovoor, J., Arnold, M., & Bacchi, S. (2023) · Medical Science Educator · doi:10.1007/s40670-023-01934-5 · Cited by 34 · see citing works
Deliberate Practice at the Virtual Bedside to Improve Clinical Reasoning
Abdulnour, R.-E. E., Parsons, A. S., Muller, D., Drazen, J. M., Rubin, E. J., & Rencic, J. J. (2022) · New England Journal of Medicine · doi:10.1056/nejme2204540 · Cited by 32 · see citing works
Context factors in clinical decision-making: a scoping review
Schuler, K., Jung, I.-C., Zerlik, M., Hahn, W., Sedlmayr, M., & Sedlmayr, B. (2025) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-025-02965-1 · Cited by 31 · see citing works
A collaborative model for developing and maintaining virtual patients for medical education
Berman, N. B., Fall, L. H., Chessman, A. W., Dell, M. R., Lang, V. J., Leong, S. L., Nixon, L. J., & Smith, S. (2011) · Medical Teacher · doi:10.3109/0142159x.2011.540268 · Cited by 27 · see citing works
Feasibility and Educational Value of Clinical Cases Generated Using Large Language Models
Berbenyuk, A., Powell, L., & Zary, N. (2024) · Studies in health technology and informatics · doi:10.3233/shti240705 · Cited by 17 · see citing works
Utility of large language models for creating clinical assessment items
Lam, G., Shammoon, Y., Coulson, A., Lalloo, F., Maini, A., Amin, A., Brown, C., & Sam, A. H. (2024) · Medical Teacher · doi:10.1080/0142159x.2024.2382860 · Cited by 15 · see citing works
Zary, N., Hege, I., Heid, J., Woodham, L. A., Donkers, J. H. H. L. M., & Kononowicz, A. A. (2009) · Studies in health technology and informatics · doi:10.3233/978-1-60750-044-5-826 · Cited by 15 · see citing works
Self-citationEducational Utility of Clinical Vignettes Generated in Japanese by ChatGPT-4: Mixed Methods Study
Takahashi, H., Shikino, K., Kondo, T., Komori, A., Yamada, Y., Saita, M., & Naito, T. (2024) · JMIR Medical Education · doi:10.2196/59133 · Cited by 14 · see citing works
How Can Nursing Faculty Create Case Studies Using AI and Educational Technology?
Silvestri-Elmore, A., & Burton, C. W. (2024) · Nurse Educator · doi:10.1097/nne.0000000000001734 · Cited by 14 · see citing works
Mayer, A., Domingues, V. D. S., Hege, I., Kononowicz, A. A., Moles, M. L., Martínez‐Jarreta, B., Rodríguez-Molina, D., Sousa‐Pinto, B., Sudacka, M., & Morin, L. (2022) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph19106175 · Cited by 13 · see citing works
Self-citationFrom Noise to Music: Reframing the Role of Context in Clinical Reasoning
Penner, J. C., Schuwirth, L., & Durning, S. J. (2024) · Journal of General Internal Medicine · doi:10.1007/s11606-024-08612-1 · Cited by 13 · see citing works
Using ChatGPT in the Development of Clinical Reasoning Cases: A Qualitative Study
Wong, K. G., Fayngersh, A., Traba, C. M., Cennimo, D. J., Kothari, N., & Chen, S. (2024) · Cureus · doi:10.7759/cureus.61438 · Cited by 8 · see citing works
Twelve tips: Using generative AI to create and optimize content for virtual patient simulations
Moser, M., Posel, N. H., Ganescu, O., & FLEISZER, D. M. (2025) · Medical Teacher · doi:10.1080/0142159x.2025.2501252 · Cited by 6 · see citing works
Szydlak, R., Kıyak, Y. S., Hege, I., et al. (2025) · Studies in health technology and informatics · doi:10.3233/shti250538
Self-citation
Flagged first, then by citations
Research works printed but not linked: 2
- [11]iCoViP project and review documents. https://www.icovip.eu. Accessed 15 June 2025.
- [61]Benítez TM, Xu Y, Boudreau JD, Kow AWC, Bello F, Van Phuoc L, Wang X, Sun X, Leung GK, Lan Y, Wang Y, Cheng D, Tham YC, Wong TY, Chung KC. Harnessing the potential of large language models in medical education: promise and pitfalls. J Am Med Inf Assoc. 2024;31(3):776–83. PMC10873781 38269644 · DOI · Paper page
Cited by
Sorted by citations
Alon, L., Shoval, D. H., & Levkovich, I. (2026) · npj Digital Medicine · doi:10.1038/s41746-026-02608-3 · Cited by 9 · see citing works
Gao, L., Zhang, L., Zhang, Y., Wu, M., Xu, J., & Lu, D. (2026) · BMC Medical Education · doi:10.1186/s12909-026-09219-2 · Cited by 2 · see citing works
“Besides, unlike human role-playing, where fatigue or variability may occur, the AI system offers repeated, high-fidelity practice opportunities [9, 11, 12], allowing students to master the check-list elements of history taking through deliberate practice [14].”
Thind, B. S., Javidi, D., & Schwartz, L. M. (2026) · Frontiers in Digital Health · doi:10.3389/fdgth.2026.1830254 · Cited by 2 · see citing works
Çiftçi, M. U., Koluman, A., Çiftçi, E. A., Çakmur, B. B., & Ziroğlu, N. (2026) · The Knee · doi:10.1016/j.knee.2026.104579 · Cited by 2 · see citing works
Lautier, M., Béal, F., Domergue, A. R., Jung, S., Clauss, F., & Strub, M. (2026) · BMC Medical Education · doi:10.1186/s12909-025-08502-y
Mlika, M., Zorgati, M. M., Ismail, I. B., Cheikhrouhou, S., Hofman, P., & Labbène, I. (2026) · Journal of Medical Education and Curricular Development · doi:10.1177/23821205261463619
Artificial intelligence generated virtual patients in health professions education: a scoping review
Fang, E., Boon, Y., Ho, J. Y., Tey, N., & Low, M. (2026) · BMC Medical Education · doi:10.1186/s12909-026-10028-w · Cited by 1 · see citing works
Wang, P., Li, H., Tu, D., Qu, H., Chang, M., Zhang, Q., Gan, X., Li, B., Wang, Y., & Xu, W. (2026) · BMC Medical Education · doi:10.1186/s12909-026-09650-5
AI-enhanced case-based learning for clinical reasoning in pathophysiology: A sequential cohort studyPreprint
Hu¹, Z., Xiong¹, L., Guo², K., Yuan², C., & Huang, Y. (2026) · Research Square · doi:10.21203/rs.3.rs-10187129/v1
Generative artificial intelligence and the transformation of medical education: a scoping review
Zhao, J., Yang, K., Gao, H., & Jiang, G. (2026) · Frontiers in Education · doi:10.3389/feduc.2026.1907589 · Cited by 1 · see citing works
- Authors
- Fąferek, J., Kononowicz, A. A., Bogutska, N., Da Silva Domingues, V., Davydova, N., Frankowska, A., Iguacel, I., Mayer, A., Morin, L., Pavlyukovich, N., Popova, I., Shchudrova, T., Sudacka, M., Szydlak, R., & Hege, I.
- Affiliations
- Jagiellonian University (PL)
- Bukovinian State Medical University (UA)
- Universidad de Zaragoza (ES)
- University of Augsburg (DE)
- Bicêtre Hospital (FR)
- Medizinische Hochschule Brandenburg Theodor Fontane (DE)
- Corresponding author
- Hege, Inga
- ORCID
- Venue
- BMC Medical Education
- Published
- 2025-10-02
- Volume
- 25
- Issue
- 1
- Pages
- 1277-1277
- ISSN
- 1472-6920 (ISSN-L)
- PMC
- PMC12490129
- OpenAlex
- W4414744900
- Cited by
- 10
- References
- 40
- Citations by year
- 2026: 10
- FWCI
- 2.39
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- BMC Medical Education (publishedVersion, cc-by-nc-nd)
- Europe PMC (PubMed Central) (publishedVersion, cc-by-nc-nd)
- PubMed (publishedVersion)
- PubMed Central (publishedVersion, cc-by-nc-nd)
- Homo Politicus (Academy of Humanities and Economics in Lodz) (submittedVersion, cc-by-nc-nd)
- Zaguan (University of Zaragoza Repository) (submittedVersion, cc-by-nc-nd)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Uniwersytet Jagielloński Collegium Medicum
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Health Sciences › Medicine › Family Practice › Clinical Reasoning and Diagnostic Skills
- Health Sciences › Medicine › Public Health, Environmental and Occupational Health › Innovations in Medical Education
- Keywords
- virtual patients, ChatGPT, generative AI, clinical reasoning training, medical students, representativeness, differential diagnosis, patient-doctor interaction, human-AI collaboration
- MeSH terms
- Clinical Reasoning, Generative Artificial Intelligence, Artificial Intelligence, Clinical Competence, Education, Medical, Undergraduate, Europe, Humans, Patient Simulation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
