Enhancing responses from large language models with role-playing prompts: a comparative study on answering frequently asked questions about total knee arthroplasty.

Journal: BMC medical informatics and decision making
Published Date: May 23, 2025

Abstract

BACKGROUND: The application of artificial intelligence (AI) in medical education and patient interaction is rapidly growing. Large language models (LLMs) such as GPT-3.5, GPT-4, Google Gemini, and Claude 3 Opus have shown potential in providing relevant medical information. This study aims to evaluate and compare the performance of these LLMs in answering frequently asked questions (FAQs) about Total Knee Arthroplasty (TKA), with a specific focus on the impact of role-playing prompts.

Authors

  • Yi-Chen Chen
    Department of Psychology, College of Science, National Taiwan University, Taipei 10617, Taiwan.
  • Sheng-Hsun Lee
    Department of Orthopaedic Surgery, Chang Gung Memorial Hospital, Taoyuan, 333, Taiwan.
  • Huan Sheu
    Department of Orthopaedic Surgery, Chang Gung Memorial Hospital, Taoyuan, 333, Taiwan.
  • Sheng-Hsuan Lin
    Institute of Statistics, National Chiao Tung University, Hsinchu, Taiwan.
  • Chih-Chien Hu
    Department of Orthopaedic Surgery, Chang Gung Memorial Hospital, Taoyuan, 333, Taiwan.
  • Shih-Chen Fu
    Institute of Statistics, National Yang Ming Chiao Tung University, Hsinchu, Taiwan.
  • Cheng-Pang Yang
    Department of Orthopedic Surgery, Linkou Chang Gung Memorial Hospital, Taoyuan City, Taiwan.
  • Yu-Chih Lin
    Department of Orthopaedic Surgery, Chang Gung Memorial Hospital (CGMH), Taoyuan, Taiwan.

Keywords

External Resources

Popular Topics
Recent Journals