Extraction and classification of structured data from unstructured hepatobiliary pathology reports using large language models: a feasibility study compared with rules-based natural language processing
LLMs have significant potential to simplify the extraction of research elements from pathology reporting, and therefore, accelerate the pace of cancer research.
Authors
- Ruben Geevarghese (ORCID: https://orcid.org/0000-0002-8461-0011)
- Brett Marinelli (ORCID: https://orcid.org/0000-0003-3220-1360)
- John Cadley (ORCID: https://orcid.org/0000-0002-3739-4838)
- Pulkit Jain (ORCID: https://orcid.org/0000-0001-5708-9761)
- Avijit Chatterjee (ORCID: https://orcid.org/0000-0002-0492-4839)
- Nathaniel Swinburne (ORCID: https://orcid.org/0000-0001-5831-7287)
- Carlie Sigel (ORCID: https://orcid.org/0000-0001-6276-3968)
- Alex Hollingsworth
- Khawaja Hasan Bilal
- Subrata Chatterjee
Institutions
- Memorial Sloan Kettering Cancer Center (US)
Publication Details
- Journal
- Journal of Clinical Pathology
- Published
- 2024-09-20
- DOI
- https://doi.org/10.1136/jcp-2024-209669
- Citations
- 8
- Primary Topic
- Topic Modeling
- Type
- article
- Field-Weighted Citation Impact
- 2.78