AI patients, real practice: exploring the use of AI-simulated patients to support primary healthcare training for combat medical technicians.

Authors

Hugo Cohen, Ben Smith, Natasha Day, Chris Jacobs, Douglas Reid

Published in

Education for primary care : an official publication of the Association of Course Organisers, National Association of GP Tutors, World Organisation of Family Doctors. Pages 1-7. Aug 21, 2026. Epub Aug 21, 2026.

Abstract

Combat Medical Technicians (CMTs) are central to military primary care but have limited opportunity for clinical exposure. Simulated patients offer a controlled method to maintain clinical currency. Advances in conversational artificial intelligence (AI) enable realistic and interactive simulated consultations. We present our evaluation of the feasibility, acceptability and educational impact of AI-simulated patients for CMT training.
Five military primary care simulated patients were developed and hosted on the SimFlow.ai platform and delivered during a development course. Participants completed pre- and post-simulation surveys assessing confidence across 12 clinical domains alongside perceptions of realism, usability and educational value. Quantitative analysis used Wilcoxon signed-rank tests and Spearman rank correlations.
Twenty CMTs completed both simulations and surveys. Statistically significant improvements were observed in 10 of 12 clinical domains, including core consultation skills such as comprehensive history taking, identifying key symptoms, adapting questioning and formulating a management plan, and differential diagnoses (all p < 0.002). Evaluation of the simulations demonstrated positive perceptions of medical accuracy, patient narratives and overall educational value. Technical performance received mixed feedback, with response lags identified as the primary barrier. No associations were found between outcomes and CMT demographics which suggests equitable benefit across the cohort.
AI-simulated patients are feasible to implement and are associated with meaningful improvements in consultation confidence among CMTs. Despite technical constraints, AI-simulated patients represent a scalable, standardised adjunct to support clinical currency across the CMT workforce. Further research should evaluate objective competence outcomes and explore broader uses of this technology.

PMID:
42627168
Bibliographic data and abstract were imported from PubMed on 21 Aug 2026.

Read full publication at:
Please sign in to see all details.

Stats

1-terrible, 9-excellent. How would you rate this publication? Sign in in to submit your rating.

Post a comment

You need to be signed in to post comments. You can sign in here.

Comments

There are no comments yet.