Enhancing clinical reasoning skills for medical students: a qualitative comparison of LLM-powered social robotic versus computer-based virtual patients within rheumatology

Abstract

Virtual patients (VPs) are increasingly used in medical education to train clinical reasoning (CR) skills. However, optimal VP design for enhancing interactivity and authenticity remains unclear. Novel interactive modalities, such as large language model (LLM)-enhanced social robotic VPs might increase interactivity and authenticity in CR skill practice. To evaluate medical students’ perceptions of CR training using an LLM-enhanced social robotic VP platform compared with a conventional computer-based VP platform. A qualitative study involved 23 third-year medical students from Karolinska Institutet, who completed VP cases on an LLM-enhanced social robotic platform and a computer-based semi-linear platform. In-depth interviews assessed students’ self-perceived acquirement of CR skills using the two platforms. Thematic analysis was employed to identify themes and sub-themes. Three main themes were identified: authenticity, VP application, and strengths and limitations. Students found the social robotic platform more authentic and engaging. It enabled highly interactive communication and expressed emotions, collectively offering a realistic experience. It facilitated active learning, hypothesis generation, and adaptive thinking. Limitations included lack of physical examination options and, occasionally, mechanical dialogue. The LLM-enhanced social robotic VP platform offers a more authentic and interactive learning experience compared to the conventional computer-based platform. Despite some limitations, it shows promise in training CR skills, communication, and adaptive thinking. Social robotic VPs may prove useful and safe learning environments for exposing medical students to diverse, highly interactive patient simulations.