iScience (May 2024)
The application of large language models in medicine: A scoping review
- Xiangbin Meng,
- Xiangyu Yan,
- Kuo Zhang,
- Da Liu,
- Xiaojuan Cui,
- Yaodong Yang,
- Muhan Zhang,
- Chunxia Cao,
- Jingjia Wang,
- Xuliang Wang,
- Jun Gao,
- Yuan-Geng-Shuo Wang,
- Jia-ming Ji,
- Zifeng Qiu,
- Muzi Li,
- Cheng Qian,
- Tianze Guo,
- Shuangquan Ma,
- Zeying Wang,
- Zexuan Guo,
- Youlan Lei,
- Chunli Shao,
- Wenyao Wang,
- Haojun Fan,
- Yi-Da Tang
Affiliations
- Xiangbin Meng
- Department of Cardiology and Institute of Vascular Medicine, Peking University Third Hospital, Beijing, China; State Key Laboratory of Vascular Homeostasis and Remodeling, Peking University, Beijing, China
- Xiangyu Yan
- Institute of Disaster and Emergency Medicine, Tianjin University, Tianjin, China
- Kuo Zhang
- Department of Cardiology, State Key Laboratory of Cardiovascular Disease, Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences, and Peking Union Medical College, Beijing, China
- Da Liu
- Department of Cardiology, the First Hospital of Hebei Medical University, Graduate School of Hebei Medical University, Shi-jia-zhuang, Hebei, China
- Xiaojuan Cui
- School of Software & Microelectronics, Peking University, Beijing, China
- Yaodong Yang
- Institute for Artificial Intelligence, Peking University, Beijing, China
- Muhan Zhang
- Institute for Artificial Intelligence, Peking University, Beijing, China
- Chunxia Cao
- Institute of Disaster and Emergency Medicine, Tianjin University, Tianjin, China
- Jingjia Wang
- Department of Cardiology and Institute of Vascular Medicine, Peking University Third Hospital, Beijing, China
- Xuliang Wang
- Department of Cardiology and Institute of Vascular Medicine, Peking University Third Hospital, Beijing, China
- Jun Gao
- Department of Cardiology and Institute of Vascular Medicine, Peking University Third Hospital, Beijing, China
- Yuan-Geng-Shuo Wang
- Department of Cardiology and Institute of Vascular Medicine, Peking University Third Hospital, Beijing, China
- Jia-ming Ji
- Institute for Artificial Intelligence, Peking University, Beijing, China
- Zifeng Qiu
- Peking University Health Science Center, Peking University First Hospital, Beijing, China
- Muzi Li
- Peking University Health Science Center, Peking University People’s Hospital, Beijing, China
- Cheng Qian
- Department of Cardiology and Institute of Vascular Medicine, Peking University Third Hospital, Beijing, China
- Tianze Guo
- Peking University Health Science Center, Beijing, China
- Shuangquan Ma
- School of Biological Science and Medical Engineering, Beijing Advanced Innovation Centre for Biomedical Engineering, Beihang University, Key Laboratory for Biomechanics and Mechanobiology of Ministry of Education, Beijing, China
- Zeying Wang
- Department of Prosthodontics, Peking University School and Hospital of Stomatology, National Engineering Laboratory for Digital and Material Technology of Stomatology, National Clinical Research Center for Oral Diseases, Beijing Key Laboratory of Digital Stomatology, Beijing, China
- Zexuan Guo
- Peking University Health Science Center, Beijing, China
- Youlan Lei
- Peking University Health Science Center, Beijing, China
- Chunli Shao
- Department of Cardiology and Institute of Vascular Medicine, Peking University Third Hospital, Beijing, China
- Wenyao Wang
- Department of Cardiology and Institute of Vascular Medicine, Peking University Third Hospital, Beijing, China
- Haojun Fan
- Institute of Disaster and Emergency Medicine, Tianjin University, Tianjin, China; Corresponding author
- Yi-Da Tang
- Department of Cardiology and Institute of Vascular Medicine, Peking University Third Hospital, Beijing, China; State Key Laboratory of Vascular Homeostasis and Remodeling, Peking University, Beijing, China; Corresponding author
- Journal volume & issue
-
Vol. 27,
no. 5
p. 109713
Abstract
Summary: This study systematically reviewed the application of large language models (LLMs) in medicine, analyzing 550 selected studies from a vast literature search. LLMs like ChatGPT transformed healthcare by enhancing diagnostics, medical writing, education, and project management. They assisted in drafting medical documents, creating training simulations, and streamlining research processes. Despite their growing utility in assisted diagnosis and improving doctor-patient communication, challenges persisted, including limitations in contextual understanding and the risk of over-reliance. The surge in LLM-related research indicated a focus on medical writing, diagnostics, and patient communication, but highlighted the need for careful integration, considering validation, ethical concerns, and the balance with traditional medical practice. Future research directions suggested a focus on multimodal LLMs, deeper algorithmic understanding, and ensuring responsible, effective use in healthcare.
