Related Experiment Video
Updated: Aug 6, 2026
08:36
The Immersive Cleveland Clinic Virtual Reality Shopping Platform for the Assessment of Instrumental Activities of Daily Living
Published on: July 28, 2022
Enhancing objective structured clinical examination performance through an artificial intelligence virtual patient: a
Betty S Chan1,2, Jack Marjot1,2, Timothy Dodds3
1School of Clinical Medicine, University of New South Wales, Kensington, Australia.
Proceedings (Baylor University. Medical Center)
|July 21, 2026
Summary
Artificial intelligence virtual patients (AIVP) show promise in medical education, enhancing student confidence in clinical skills. While not significantly improving all outcomes, AIVP offers a structured learning tool for objective structured clinical examinations (OSCEs).
Area of Science:
- Medical Education Technology
- Artificial Intelligence in Healthcare
- Clinical Skills Assessment
Background:
- The use of AI for simulating patient interactions in clinical exams is an emerging field.
- Objective structured clinical examinations (OSCEs) are crucial for evaluating medical students' clinical competencies.
- There is a need for innovative tools to enhance medical training and provide objective feedback.
Purpose of the Study:
- To evaluate an AI virtual patient (AIVP) system designed for interactive patient simulations.
- To assess the impact of AIVP on medical students' performance in OSCEs.
- To explore student perceptions of AIVP as a learning tool.
Main Methods:
- A prospective mixed-methods pilot study involving final-year medical students.
- Two cohorts: volunteer AIVP group (n=43) and a control group (n=8) using standard educational support.
- Pre- and post-intervention OSCEs were administered, with quantitative data analyzed using Wilcoxon signed-rank test and qualitative data from surveys and focus groups analyzed thematically.
Main Results:
- The AIVP group showed descriptive improvements, but no statistically significant changes in OSCE scores.
- The control group demonstrated significant improvement in overall OSCE outcomes (P=0.03).
- Qualitative feedback indicated AIVP enhanced confidence in history-taking, differential diagnosis, and management planning, serving as a confidence-building tool.
Conclusions:
- AI virtual patients are feasible and well-received, aligning with university OSCE standards.
- AIVP shows potential as a supplementary training tool, particularly for students benefiting from structured support.
- The system's ability to provide tailored feedback and practice for OSCEs highlights its value in medical education.