Enhancing Medical Interview Skills through AI Simulated Patient Interactions: Non-Randomized Controlled Trial (Preprint)

BACKGROUND Medical interviewing is a critical skill in clinical practice, yet opportunities for practical training are limited in Japanese medical schools, necessitating urgent measures. Given advancements in AI technology, its application in the medical field is expanding. However, reports on its application in medical interviews in medical education are scarce. OBJECTIVE This study aimed to investigate whether medical students' interview skills could be improved by engaging with AI-simulated patients using large language models (LLMs), including the provision of feedback. METHODS A simulation program using LLMs was provided to 35 fourth-year medical students in Japan in 2023. As a control group, 110 fourth-year medical students from 2022 who did not participate in the intervention were selected. The primary outcome was the score on the pre-Clinical Clerkship Objective Structured Clinical Examination (pre-CC OSCE), a national standardized clinical skills examination, in medical interviewing. Secondary outcomes included surveys such as Simulation-Based Training Quality Assurance Tool (SBT-QA10). RESULTS The AI intervention group showed significantly higher scores on medical interviews than the control group (AI group vs. control group: median 28.0 vs. 27.0, p = 0.01). There was a trend of inverse correlation between the SBT-QA10 and pre-CC OSCE scores (regression coefficient -2.0 to -2.1). No significant safety concerns were observed. CONCLUSIONS Education through medical interviews using AI-simulated patients has demonstrated safety and a certain level of educational effectiveness, suggesting promising prospects for multifaceted applications in the field of medical education.