Differentiating ChatGPT-Generated and Human-Written Medical Texts: Quantitative Study.

Journal: JMIR medical education
Published Date:

Abstract

BACKGROUND: Large language models, such as ChatGPT, are capable of generating grammatically perfect and human-like text content, and a large number of ChatGPT-generated texts have appeared on the internet. However, medical texts, such as clinical notes and diagnoses, require rigorous validation, and erroneous medical content generated by ChatGPT could potentially lead to disinformation that poses significant harm to health care and the general public.

Authors

  • Wenxiong Liao
    School of Computer Science and Engineering, South China University of Technology, Guangzhou, China.
  • Zhengliang Liu
    School of Computing, University of Georgia, Athens, GA, United States.
  • Haixing Dai
    School of Computing, University of Georgia, Athens, GA, United States.
  • Shaochen Xu
    School of Computing, University of Georgia, Athens, GA, United States.
  • Zihao Wu
    School of Computing, University of Georgia, Athens, GA, United States.
  • Yiyang Zhang
    CEMS, NCMIS, HCMS, MDIS, RCSDS, Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing, 100190, China.
  • Xiaoke Huang
    School of Computer Science and Engineering, South China University of Technology, Guangzhou, China.
  • Dajiang Zhu
    Department of Computer Science and Engineering, The University of Texas at Arlington, Arlington, TX, United States.
  • Hongmin Cai
    School of Computer Science& Engineering, South China University of Technology, Guangdong, China. hmcai@scut.edu.cn.
  • Quanzheng Li
    Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, United States.
  • Tianming Liu
    School of Computing, University of Georgia, Athens, GA, United States.
  • Xiang Li
    Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, United States.