Generative AI Simulated Patients Versus Expert Demonstration Videos for Psychiatric Interview Training in Occupational Therapy Students

The goal of this study is to compare two methods for teaching psychiatric work-history interviewing to third-year occupational therapy students: practice with a generative AI simulated patient and an expert demonstration video. The main questions it aims to answer are: 1. Which teaching method leads to better interview performance in an objective structured clinical examination (OSCE) with a standardized patient? 2. How do the two methods affect students\' interview self-efficacy? 3. How do students evaluate the two methods, and which learning sequence do they prefer? Students enrolled in a required vocational rehabilitation course were randomly assigned to one of two sequences. In the first teaching week, one sequence practiced interviewing a GPT-4o-based simulated patient (a 35-year-old person with schizophrenia), and the other watched and discussed an expert demonstration interview of the same case. Both groups completed a 9-minute standardized-patient OSCE on the same day. In the following week, the two sequences crossed over to the other method. Interview self-efficacy was measured before teaching, after the first method, and after the second method.