Evaluation and Bias Analysis of Large Language Models in Generating Synthetic Electronic Health Records: Comparative Study.

Journal: Journal of medical Internet research
PMID: 40354109

Abstract

BACKGROUND: Synthetic electronic health records (EHRs) generated by large language models (LLMs) offer potential for clinical education and model training while addressing privacy concerns. However, performance variations and demographic biases in these models remain underexplored, posing risks to equitable health care.

Authors

  • Ruochen Huang
    School of Biomedical Engineering and Informatics, Nanjing Medical University, Nanjing, China.
  • Honghan Wu
    University College London, London, United Kingdom.
  • Yuhan Yuan
    School of Biomedical Engineering and Informatics, Nanjing Medical University, Nanjing, China.
  • Yifan Xu
    Department of Nutrition and Food Hygiene, School of Public Health, Peking University, 38 Xue Yuan Road, Haidian District, Beijing 100191, China. xuyifan_1992@163.com.
  • Hao Qian
    Department of Respiratory and Critical Care Medicine, Shanghai Pulmonary Hospital, School of Medicine, Tongji University, Shanghai, China.
  • Changwei Zhang
    The Pervasive Communication Center, Purple Mountain Laboratories, Nanjing, China.
  • Xin Wei
    Department of Urology, The Fifth Affiliated Hospital of Guangzhou Medical University, Guangzhou, 510700, China.
  • Shan Lu
    The First Affiliated Hospital of Nanjing Medical University, Nanjing, China.
  • Xin Zhang
    First Department of Infectious Diseases, The First Affiliated Hospital of China Medical University, Shenyang, China.
  • Jingbao Kan
    The First Affiliated Hospital of Nanjing Medical University, Nanjing, China.
  • Cheng Wan
    School of Biomedical Engineering and Informatics, Nanjing Medical University, Nanjing, China.
  • Yun Liu
    Google Health, Palo Alto, CA USA.

Keywords

External Resources

Popular Topics
Recent Journals