
Qian Li, Yongxin Li, Chao Ye, K. Zhang, Jing Bai, Xinbo Liu, Zhantao Li, Xuanyu Meng, Xianjun Min, Jin Guo · Frontiers in Artificial Intelligence 2026 · 2026
DOI: 10.3389/frai.2026.1772518
Frontiers in Artificial IntelligenceJournal85 h-indexCounts differ because each database indexes a different set of publications. We treat OpenAlex as the canonical count; Google Scholar is not shown (no API, and crawling it violates its ToS).
Background Specialized thoracic-surgery questions require the integration of multi-factor clinical relationships within text, yet general-purpose large language models (LLMs) may underperform on such exam-style benchmarks. Methods We constructed a DK-LLM agent by embedding curated medical textbook knowledge into a LangChain-based framework to support domain-specific reasoning. The model was tested on a 56-item thoracic-surgery examination question set in a restricted text-only setting without internet browsing or external tools and was compared with generic LLM baselines, three thoracic surgeons, and three non-expert engineers. Examination score and error patterns were assessed. Results The knowledge-augmented DK-LLM configuration showed an 11.8-point examination-score advantage over the version without the local knowledge base. Commercial LLM-based agents outperformed the open-source baselines and non-expert participants on this question set, whereas experienced thoracic surgeons achieved the highest scores overall; in the ablation analysis, removing the local knowledge base reduced the examination score by 11.8 percentage points. Conclusion Embedding domain-specific knowledge into LLMs may improve performance on specialized exam-style thoracic-surgery questions on this text-only benchmark. However, the present 56-item evaluation does not establish clinical equivalence, diagnostic accuracy in practice, multimodal competence, or readiness for real-world clinical decision support.
No comments yet — start the discussion below.