DeepSeek-R1 and GPT-4 are comparable in a complex diagnostic challenge: a historical control study
DeepSeek-R1 exhibits diagnostic accuracy comparable to GPT-4 while generating more diverse differential diagnoses. Its open-source nature and innovative reasoning strategies may enhance medical AI applications. Future studies should explore real-world clinical integration and refinement of differential diagnosis prioritization.
Authors
- Xinjie Xu (ORCID: https://orcid.org/0000-0003-0737-0648)
- Kaiyang Lv (ORCID: https://orcid.org/0000-0003-3539-2123)
- L Chan
Institutions
- XinHua Hospital (CN)
- Online Technologies (United States) (US)
Publication Details
- Journal
- International Journal of Surgery
- Published
- 2025-04-03
- DOI
- https://doi.org/10.1097/js9.0000000000002386
- Citations
- 17
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 11.12