ZHENG Qingyong 1,2,3 , WU Jingling 4 , LI Molan 5 , XU Jianguo 1,2,3 , LIU Ming 1,2,3 , ZHOU Yongjia 1,2,3 , CUI Yating 1,2,3 , LI Ruixue 6 , GAO Ya 7,8 , GE Long 2,9,10,11 , ZHANG Junhua 12,13 , TIAN Jinhui 1,2,3
  • 1. Evidence-Based Medicine Center, School of Basic Medical Sciences, Lanzhou University, Lanzhou 730000, P. R. China;
  • 2. Key Laboratory of Evidence-Based Medicine of Gansu Province, Lanzhou 730000, P. R. China;
  • 3. Research Unit of Evidence-Based Evaluation and Guidelines, Chinese Academy of Medical Sciences, Lanzhou 730000, P. R. China;
  • 4. Department of Ultrasound, 96604 Military Hospital of China People's Liberation Army, Lanzhou 730000, P. R. China;
  • 5. The First School of Clinical Medicine, Lanzhou University, Lanzhou 730000, P. R. China;
  • 6. School of Public Health, Cheeloo College of Medicine, Shandong University, Jinan 250012, P. R. China;
  • 7. National Institute of Health and Medical Data Science, Jinan 250003, P. R. China;
  • 8. Department of Health Policy and Management, School of Public Health, Lanzhou 730000, P. R. China;
  • 9. Laboratory of Cross-Innovation for Evidence-based Social Sciences, Lanzhou 730000, P. R. China;
  • 10. Research Centre for Health Management and Health Development, Lanzhou University, Lanzhou 730000, P. R. China;
  • 11. Evidence-Based Medicine Center, Tianjin University of Traditional Chinese Medicine, Tianjin 301617, P. R. China;
  • 12. Key Laboratory of Evidence-Based Evaluation of Traditional Chinese Medicine, National Medical Products Administration, Tianjin 301617, P. R. China;
  • 13. ;
ZHANG Junhua, Email: zjhtcm@163.com; TIAN Jinhui, Email: tjh996@163.com
Export PDF Favorites Scan Get Citation

The burgeoning application of large language models (LLM) in healthcare demonstrates immense potential, yet simultaneously poses new challenges to the standardization of research reporting. To enhance the transparency and reliability of medical LLM research, an international expert group published the TRIPOD-LLM reporting guideline in Nature Medicine in January 2024. As an extension of the TRIPOD+AI guideline, TRIPOD-LLM provides detailed reporting items specifically tailored to the unique characteristics of LLMs, including general foundational models (e.g., GPT-4) and domain-specific fine-tuned models (e.g., Med-PaLM 2). It addresses critical aspects such as prompt engineering, inference parameters, generative evaluation, and fairness considerations. Notably, the guideline introduces an innovative modular design and a "living guideline" mechanism. This paper provides a systematic, item-by-item interpretation and example-based analysis of the TRIPOD-LLM guideline. It is intended to serve as a clear and practical handbook for researchers in this field, as well as for journal reviewers and editors responsible for assessing the quality of such studies, thereby fostering the high-quality development of medical LLM research in China.

Copyright © the editorial department of Chinese Journal of Evidence-Based Medicine of West China Medical Publisher. All rights reserved