Development and Validation of a Large Language Model-Based System for Medical History-Taking Training: Prospective Multicase Study on Evaluation Stability, Human-AI Consistency, and Transparency.

Journal: JMIR medical education
Published Date: Aug 29, 2025

Abstract

BACKGROUND: History-taking is crucial in medical training. However, current methods often lack consistent feedback and standardized evaluation and have limited access to standardized patient (SP) resources. Artificial intelligence (AI)-powered simulated patients offer a promising solution; however, challenges such as human-AI consistency, evaluation stability, and transparency remain underexplored in multicase clinical scenarios.

Authors

  • Yang Liu
    Department of Computer Science, Hong Kong Baptist University, Hong Kong, China.
  • Chujun Shi
    Medical Simulation Center, Shantou University Medical College, No. 22 Xinling Road, Shantou, 515041, China, 86 754-88900459.
  • Liping Wu
    Department of Gastroenterology, The Third People's Hospital of Chengdu, Chengdu 610031, Sichuan Province, China.
  • Xiule Lin
    Medical Simulation Center, Shantou University Medical College, No. 22 Xinling Road, Shantou, 515041, China, 86 754-88900459.
  • Xiaoqin Chen
    Third Hospital of Shanxi Medical University, Shanxi Bethune Hospital, Shanxi Academy of Medical Sciences, Tongji Shanxi Hospital, Taiyuan, 030032, China.
  • Yiying Zhu
    Medical Simulation Center, Shantou University Medical College, No. 22 Xinling Road, Shantou, 515041, China, 86 754-88900459.
  • Haizhu Tan
    Department of Preventive Medicine, Shantou University Medical College, 22 Xinling Rd, Shantou, 515031, China, 86 13318055534.
  • Weishan Zhang
    The College of Computer Science and Communication Engineering, China University of Petroleum (East China), Qingdao 257061, China. zhangws@upc.edu.cn.

Keywords

External Resources

Popular Topics
Recent Journals