Lightweight open-source large language models versus cTAKES for information extraction from discharge summaries: tobacco smoking status test case
Lightweight LLMs can be applied for use across diverse clinical information extraction tasks without the need for task-specific fine-tuning.
Authors
- Matthew J. Schuelke (ORCID: https://orcid.org/0000-0001-5755-1725)
- Adam B Wilcox
- David M Dávila-García
Institutions
- Washington University in St. Louis (US)
Publication Details
- Journal
- JAMIA Open
- Published
- 2025-12-30
- DOI
- https://doi.org/10.1093/jamiaopen/ooaf182
- Primary Topic
- Topic Modeling
- Type
- article
- Field-Weighted Citation Impact
- 0.00