Comparative analysis of accuracy and completeness in standardized database generation for complex multilingual lung cancer pathological reports: large language model-based assisted diagnosis system vs. DeepSeek, GPT-3.5, and healthcare professionals
The fine-tuned lung cancer LLM outperformed non-chief physicians and general LLMs in accuracy/completeness, significantly reduced medical staff workload (<i>p</i> < 0.001), with future optimization potential despite current limitations.
Authors
- Juan Zhu (ORCID: https://orcid.org/0000-0003-2151-5487)
- Xinghua Cheng (ORCID: https://orcid.org/0000-0001-8232-8146)
- Hsueh‐Ming Hang (ORCID: https://orcid.org/0000-0001-8965-2619)
- Pengchong Li
- Liankai Yang
- Rang Liu (ORCID: https://orcid.org/0000-0001-7151-7224)
- Zhexuan Lin (ORCID: https://orcid.org/0000-0001-9364-5980)
- Shuai Pu
- Zhongjie Wang (ORCID: https://orcid.org/0000-0003-3491-417X)
Institutions
- Bengbu Medical College (CN)
- Shanghai Jiao Tong University (CN)
- Anhui Medical University (CN)
- Shanghai Chest Hospital (CN)
- Cangzhou Central Hospital (CN)
- Liupanshui Normal University (CN)
- Second Affiliated Hospital of Anhui Medical University (CN)
- Southeast University (CN)
Publication Details
- Journal
- Frontiers in Medicine
- Published
- 2025-08-22
- DOI
- https://doi.org/10.3389/fmed.2025.1618858
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Shanghai Municipal Health Commission
- Science and Technology Commission of Shanghai Municipality