A comparison of the performance of Chinese large language models and ChatGPT throughout the entire clinical workflow
The large language model Doubao from China demonstrates performance similar to ChatGPT across full clinical workflows. LLMs outperform human emergency fellow physicians and exhibit rapid development, offering significant practical application potential in healthcare.
Authors
- Zhuo Zhang (ORCID: https://orcid.org/0000-0002-4449-5733)
- Yang Wang (ORCID: https://orcid.org/0000-0003-1029-9280)
- Ning Liu (ORCID: https://orcid.org/0000-0002-3408-8632)
- Pengpeng Chen (ORCID: https://orcid.org/0000-0003-2501-8381)
- Yang He
- Yucai Hong (ORCID: https://orcid.org/0009-0004-3780-6670)
- Lingling Lai
Institutions
- Shaoxing University (CN)
- Sir Run Run Shaw Hospital (CN)
Publication Details
- Journal
- Scientific Reports
- Published
- 2025-10-17
- DOI
- https://doi.org/10.1038/s41598-025-20210-7
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Natural Science Foundation of Zhejiang Province