Can large language models replace standardised patients?

Saved in:
Bibliographic Details
Title: Can large language models replace standardised patients?
Authors: Han, Weipeng, Lyu, Xiaohong, Yang, Ji‐Jiang, Yan, Mengsha, Zhang, Yuelun, Wang, Tingyan, Pan, Hui, Chen, Shi, Zhu, Jiming, Huang, Xiaoming
Source: Medical Education. May2025, Vol. 59 Issue 5, p552-553. 2p.
Subjects: Medical education, Artificial intelligence, Natural language processing, Experience, Students, Simulated patients, Video recording
Abstract: The article discusses a study which evaluated the viability and effectiveness of large language models (LLM) as substitutes for standardised patients in medical education. The study tested open-source and closed-source LLMs and assessed the experiences of medical students. Lessons learned include less effectiveness of SPs than LLMs in students' psychological experiences, ability of LLMs to conduct simulated consultations, and higher examination difficulty and role-play assessment of SPs.
Database: Psychology and Behavioral Sciences Collection
Full text is not displayed to guests.
Description
Abstract:The article discusses a study which evaluated the viability and effectiveness of large language models (LLM) as substitutes for standardised patients in medical education. The study tested open-source and closed-source LLMs and assessed the experiences of medical students. Lessons learned include less effectiveness of SPs than LLMs in students' psychological experiences, ability of LLMs to conduct simulated consultations, and higher examination difficulty and role-play assessment of SPs.
ISSN:03080110
DOI:10.1111/medu.15641