Real-world feasibility of generative large language models for clinical decision support in benign prostatic hyperplasia
Studies have shown that in the domain of clinical knowledge related to BPH, ChatGPT o1 and DeepSeek R1 perform at levels approaching those of attending physicians. Both models demonstrate substantial potential in supporting clinical decision-making, with DeepSeek R1 performing particularly well. Despite existing limitations, the application of AI in healthcare holds considerable promise and is highly anticipated.
Authors
- Qingfu Deng (ORCID: https://orcid.org/0009-0008-4836-9495)
- Yuqi Li (ORCID: https://orcid.org/0009-0004-4373-9048)
- Chunyang Meng
- Xiong Li (ORCID: https://orcid.org/0000-0001-9614-7194)
- Zhiyu Liu (ORCID: https://orcid.org/0000-0002-1678-5960)
- Xu Li (ORCID: https://orcid.org/0000-0002-7378-6054)
- Lei Peng (ORCID: https://orcid.org/0000-0002-4332-4166)
- Tao Zhou (ORCID: https://orcid.org/0000-0002-3733-7286)
- Yang Zeng (ORCID: https://orcid.org/0009-0000-4133-4080)
- Rui Liang (ORCID: https://orcid.org/0009-0005-2718-2128)
Institutions
- Affiliated Hospital of Southwest Medical University (CN)
- Sichuan Mianyang 404 Hospital (CN)
- Affiliated Hospital of North Sichuan Medical College (CN)
- Southern Medical University Shenzhen Hospital (CN)
Publication Details
- Journal
- International Journal of Surgery
- Published
- 2025-11-12
- DOI
- https://doi.org/10.1097/js9.0000000000004022
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 0.00