A comparative study on DeepSeek and ChatGPT for bone and soft tissue tumor clinical practice
DeepSeek outperforms ChatGPT in diagnostic accuracy and specialized clinical reasoning for bone/soft tissue tumors, particularly in pathology and treatment domains. The significant performance gap (p < 0.001) and 24.1% unique correct responses position DeepSeek as a more reliable diagnostic aid, though shared errors (51 questions) necessitate hybrid AI-clinician workflows.
Authors
- Zhangfu Li
- Yongli Jia
- Shengji Yu
- Xiaoyang Li
- Ge Zhao
- Baicheng Yang
- Xinxin Zhang
Institutions
- Hebei North University (CN)
- Chinese Academy of Medical Sciences & Peking Union Medical College (CN)
Publication Details
- Journal
- Frontiers in Oncology
- Published
- 2026-01-09
- DOI
- https://doi.org/10.3389/fonc.2025.1642880
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China
- Cancer Foundation of China