Utilizing generative conversational artificial intelligence to create simulated patient encounters: a pilot study for anaesthesia training
Open accessAbstract
Purpose of the study: Generative conversational artificial intelligence (AI) has huge potential to improve medical education. This pilot study evaluated the possibility of using a ‘no-code’ generative AI solution to create 2D and 3D virtual avatars, that trainee doctors can interact with to simulate patient encounters. Methods: The platform ‘Convai’ was used to create a virtual patient avatar, with a custom backstory, to test the feasibility of this technique. The virtual patient model was set up to allow trainee anaesthetists to practice answering questions that patients’ may have about interscalene nerve blocks for open reduction and internal fixation surgery. This tool was provided to anaesthetists to receive their feedback and evaluate the feasibility of this approach. Results: Fifteen anaesthetists were surveyed after using the tool. The tool had a median score [interquartile range (IQR)] of 9 [7–10] in terms of how intuitive and user-friendly it was, and 8 [7–10] in terms of accuracy in simulating patient responses and behaviour. Eighty-seven percent of respondents felt comfortable using the model. Conclusions: By providing trainees with realistic scenarios, this technology allows trainees to practice answering patient questions regardless of actor availability, and indeed from home. Furthermore, the use of a ‘no-code’ platform allows clinicians to create customized training tools tailored to their medical specialties. While overall successful, this pilot study highlighted some of the current drawbacks and limitations of generative conversational AI, including the risk of outputting false information. Additional research and fine-tuning are required before generative conversational AI tools can act as a substitute for actors and peers.
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?
Large language models, such as GPT systems, can generate dynamic, contextually appropriate, and conversationally responsive simulated patients capable of mimicking a wide range of clinical scenarios.
“Large language models (LLMs), such as GPT systems, can generate dynamic, contextually appropriate, and conversationally responsive simulated patients capable of mimicking a wide range of clinical scenarios [4, 5].”
From Utilizing generative artificial intelligence to create simulated patient for history taking in gynecology (2026) · cites this paper as [5]
The Methods describe an interactive simulated patient with a custom clinical backstory, and the interface description says she follows up based on trainees’ responses. The Randomness section reports varied answers across encounters. However, the pilot created one patient for an anaesthesia-training scenario; it does not demonstrate simulated patients across a wide range of clinical scenarios, and the Realism section notes limitations in how closely responses resemble real patient interactions. (LLM, conf=0.86)
Experimental — accuracy not yet measuredConversational GAI-created digital patients provide anesthetists with training for patient interactions, reducing reliance on human actors while enhancing flexibility and consistency.
“In addition, conversational GAI-created digital patients provide anesthetists with valuable training for patient interactions, reducing reliance on human actors while enhancing the flexibility and consistency of the training process [54].”
From Applications, Challenges, and Prospects of Generative Artificial Intelligence Empowering Medical Education: Scoping Review (2025) · cites this paper as [54]
The Abstract says the virtual patient lets anaesthetists practice answering patient questions regardless of actor availability, and the Conclusions describe adaptable scenarios and remote practice. But the Conclusions also warn of potentially reduced repeatability between sessions, so the claimed improvement in training consistency is not supported. (LLM, conf=0.88)
Experimental — accuracy not yet measuredGAI is effective in promoting interactive learning and providing practice in communication skills.
“Studies have shown that GAI is effective in promoting interactive learning and providing practice in communication skills.”
From Applications, Challenges, and Prospects of Generative Artificial Intelligence Empowering Medical Education: Scoping Review (2025) · cites this paper as [54]
The Abstract and Conclusions say the interactive virtual patient lets trainee anaesthetists practice answering patient questions. The Results report favourable usability and simulation ratings from 15 anaesthetists, but do not measure improved learning or communication skills; calling GAI effective in promoting those outcomes overstates this pilot study. (LLM, conf=0.88)
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
ChatGPT is not all you need. A state-of-the-art review of large generative AI models
Gozalo-Brizuela, R., & Garrido-Merchan, E. C. (2023) · arXiv · doi:10.48550/arxiv.2301.04655 · Cited by 245 · see citing works
Flagged first, then by citations
Research works printed but not linked: 9
- Turbitt LR, Mariano ER, El-Boghdadly K. Future directions in regional anaesthesia: not just for the cognoscenti. Anaesthe- sia 2020;75:293-7. Epub 2019 Jul 3. https://doi.org/10.1111/ anae.14768 . · DOI
- Bunt H, Petukhova V. Semantic and pragmatic precision in conversational AI systems. Front Artif Intelligence 2023;6:896729. https://doi.org/10.3389/frai.2023.896729 . · DOI
- Deng J, Zubair A, Park Y-J. Postgrad Med J 2023;9:1298-99. https:// doi.org/10.1093/postmj/qgad069 . · DOI
- Mello MM, Guha N. ChatGPT and physicians' malpractice risk. JAMA Health Forum 2023;4(5):e231938. https://doi.org/10.1001/ jamahealthforum.2023.1938 . · DOI · Paper page
- Yeo YH, Samaan JS, Ng WH. et al. Assessing the performance of ChatGPT in answering questions regarding cirrhosis and hepa- tocellular carcinoma. Clin Mol Hepatol 2023;29(3):721-32. https:// doi.org/10.3350/cmh.2023.0089 . · DOI
- Franceschelli G, Musolesi M. Copyright in generative deep learn- ing. Data Policy 2022;4:e17. https://doi.org/10.1017/dap.2022.10 . · DOI
- Abd-alrazaq A, AlSaad R, Alhuwail D. et al. Large language models in medical education: opportunities, challenges, and future directions. JMIR Med Educ 2023;9:e48291. https://doi. org/10.2196/48291 . · DOI · Paper page
- Pereira DSM, Falcão F, Nunes A. et al. Designing and build- ing OSCEBot ® for virtual OSCE -performance evaluation. Med Educ Online 2023;28:2228550. https://doi.org/10.1080/10872981. 2023.2228550. · DOI
- Suárez A, Adanero A, Díaz-Flores GV. et al. Using a virtual patient via an artificial intelligence Chatbot to develop dental students' diagnostic skills. Int J Environ Res Public Health 2022;19(14):8735. https://doi.org/10.3390/ijerph19148735. · DOI
Cited by
Sorted by citations
A Comprehensive Review on Generative AI for Education
Mittal, U., Sai, S., Chamola, V., & Sangwan, D. (2024) · IEEE Access · doi:10.1109/access.2024.3468368 · Cited by 383 · see citing works
Weisman, D., Sugarman, A., Huang, Y. M., Gelberg, L., Ganz, P. A., & Comulada, W. S. (2025) · JMIR Formative Research · doi:10.2196/65670 · Cited by 37 · see citing works
Lin, Y., Luo, Z., Ye, Z., Zhong, N., Zhao, L., Zhang, L., Li, X., Chen, Z., & Chen, Y. (2025) · JMIR Medical Education · doi:10.2196/71125 · Cited by 31 · see citing works
“This limitation makes it challenging for students to fully appreciate the importance of empathy and its application in doctor-patient interactions, which affects their development of communication and empathy skills development [38,54,76,77,101,107,147,152].”
The role of generative artificial intelligence in psychiatric education– a scoping review
Lee, Q. Y., Chen, M., Ong, C. W., & Ho, C. S. H. (2025) · BMC Medical Education · doi:10.1186/s12909-025-07026-9 · Cited by 23 · see citing works
Jones, B., Desu, A., & Honig, C. D. F. (2026) · European Journal of Dental Education · doi:10.1111/eje.13135 · Cited by 21 · see citing works
Generative artificial intelligence in healthcare simulation-based education: A scoping review
Neo, N. W. S., Gunawan, J., Levett-Jones, T., Khoo, E. T., Chua, W. L., & Liaw, S. Y. (2025) · Clinical Simulation in Nursing · doi:10.1016/j.ecns.2025.101819 · Cited by 15 · see citing works
Shen, M., Shen, Y., & Shi, Z. (2025) · Nurse Education in Practice · doi:10.1016/j.nepr.2025.104612 · Cited by 8 · 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
“Large language models (LLMs), such as GPT systems, can generate dynamic, contextually appropriate, and conversationally responsive simulated patients capable of mimicking a wide range of clinical scenarios [4, 5].”
- Authors
- Sardesai, N., Russo, P., Martin, J., & Sardesai, A.
- Affiliations
- University of Cambridge (GB)
- Cambridge University Hospitals NHS Foundation Trust (GB)
- Simulation Centre, Cambridge University Hospitals NHS Foundation Trust , Hills Road, Cambridge, CB2 0QQ , United Kingdom
- Corresponding author
- Sardesai, Neil
- Venue
- Postgraduate Medical Journal
- Publisher
- Oxford University Press (OUP)
- Published
- 2024-01-17
- Volume
- 100
- Issue
- 1182
- Pages
- 237-241
- ISSN
- 0032-5473 (ISSN-L)
- 1469-0756
- OpenAlex
- W4391029755
- Cited by
- 67
- References
- 1
- Citations by year
- 2026: 30 · 2025: 33 · 2024: 4
- FWCI
- 2.68
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Postgraduate Medical Journal (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Apollo (University of Cambridge) (submittedVersion, cc-by)
- Apollo (cc-by)
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Health Sciences › Medicine › Physiology › Simulation-Based Education in Healthcare
- Health Sciences › Medicine › Public Health, Environmental and Occupational Health › Innovations in Medical Education
- Keywords
- simulated patient encounters, anesthesiology education, interscalene nerve block, trainee anaesthetists, medical education
- MeSH terms
- Anesthesia, Anesthesiology, Artificial Intelligence, Communication, Humans, Pilot Projects
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
