A clinician-based comparative study of large language models in answering medical questions: the case of asthma
GPT and other large language models can answer medical questions with a certain degree of completeness and accuracy. However, clinical physicians should critically assess internet information, distinguishing between true and false data, and should not blindly accept the outputs of these models. With advancements in key technologies, LLMs may one day become a safe option for doctors seeking information.
Authors
- Mei Zeng (ORCID: https://orcid.org/0000-0002-3491-5298)
- Bin Dong (ORCID: https://orcid.org/0000-0002-8123-4401)
- Hansong Wang
- Jilei Lin (ORCID: https://orcid.org/0000-0003-1920-9317)
- Haibo Yang (ORCID: https://orcid.org/0000-0003-3038-6453)
- Shuai Yuan (ORCID: https://orcid.org/0000-0001-5055-5627)
- Jiande Chen (ORCID: https://orcid.org/0000-0001-7884-3460)
- Tingyue Huang
- Fen Jiang (ORCID: https://orcid.org/0000-0002-3143-9265)
- Dan Xie (ORCID: https://orcid.org/0000-0003-3173-3920)
- Jiajun Yuan (ORCID: https://orcid.org/0000-0002-9576-7890)
- Shang‐Jung Wu (ORCID: https://orcid.org/0000-0002-6111-9094)
- Mingyu Tang (ORCID: https://orcid.org/0000-0003-0034-5124)
- Yong Yin (ORCID: https://orcid.org/0000-0001-9718-6988)
- Chuxiong Zhou (ORCID: https://orcid.org/0000-0001-8839-980X)
Institutions
- Shanghai Jiao Tong University (CN)
- Shanghai Children's Medical Center (CN)
Publication Details
- Journal
- Frontiers in Pediatrics
- Published
- 2025-04-25
- DOI
- https://doi.org/10.3389/fped.2025.1461026
- Citations
- 2
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 1.31