Automated Pathologic TN Classification Prediction and Rationale Generation From Lung Cancer Surgical Pathology Reports Using a Large Language Model Fine-Tuned With Chain-of-Thought: Algorithm Development and Validation Study
The generative language model approach presented in this study has the potential to enhance and automate TN classification in complex cancer staging, supporting both clinical practice and oncology data curation. With additional fine-tuning based on cancer-specific guidelines, this approach can be effectively adapted to other cancer types.
Authors
- Sanghwan Kim
- Borham Kim (ORCID: https://orcid.org/0000-0002-6914-5721)
- Jin-Haeng Chung (ORCID: https://orcid.org/0000-0002-6527-3814)
- Keehyuck Lee (ORCID: https://orcid.org/0000-0001-6906-4887)
- Hyeongmin Cho (ORCID: https://orcid.org/0000-0001-5430-8295)
- Leonard Sunwoo (ORCID: https://orcid.org/0000-0003-0374-8658)
- Sooyoung Yoo (ORCID: https://orcid.org/0000-0001-8620-4925)
- Sowon Jang (ORCID: https://orcid.org/0000-0003-3320-1557)
- Seok Kim (ORCID: https://orcid.org/0000-0003-4996-8613)
- Sejin Nam (ORCID: https://orcid.org/0000-0003-4786-2241)
- Donghyoung Lee
Institutions
- Seoul National University (KR)
- Seoul National University Bundang Hospital (KR)
Publication Details
- Journal
- JMIR Medical Informatics
- Published
- 2024-12-20
- DOI
- https://doi.org/10.2196/67056
- Citations
- 11
- Primary Topic
- Lung Cancer Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 4.61
Funders
- Korea Health Industry Development Institute