Cancer Diagnosis Categorization in Electronic Health Records Using Large Language Models and BioBERT: Model Performance Evaluation Study
Although current performance levels appear sufficient for administrative and research use, reliable clinical applications will require standardized documentation practices alongside robust human oversight for high-stakes decision-making.
Authors
- Rezaur Rashid (ORCID: https://orcid.org/0000-0003-1343-5364)
- Janet A. Zink (ORCID: https://orcid.org/0000-0002-0261-4917)
- Arash Shaban‐Nejad (ORCID: https://orcid.org/0000-0003-2047-4759)
- Lokesh K. Chinthala (ORCID: https://orcid.org/0000-0002-1258-8353)
- Fekede Asefa Kumsa (ORCID: https://orcid.org/0000-0002-6700-4810)
- Soheil Hashtarkhani (ORCID: https://orcid.org/0000-0001-7750-6294)
- Christopher Brett (ORCID: https://orcid.org/0000-0003-2958-599X)
- Robert Lowell Davis (ORCID: https://orcid.org/0000-0001-8807-0019)
- David L. Schwartz (ORCID: https://orcid.org/0000-0002-7235-5586)
Institutions
- University of Tennessee Health Science Center (US)
- University of Tennessee at Knoxville (US)
Publication Details
- Journal
- JMIR Cancer
- Published
- 2025-10-02
- DOI
- https://doi.org/10.2196/72005
- Citations
- 2
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 4.96