Information extraction from clinical notes: are we ready to switch to large language models?
Instruction-tuned LLaMA models show promise for clinical NER and RE tasks. However, the tradeoff between improved performance and increased computational cost must be carefully evaluated. We release our Kiwi package (https://kiwi.clinicalnlp.org/) to facilitate the application of both LLaMA and BERT models in clinical IE applications.
Authors
- Vincent Zhang (ORCID: https://orcid.org/0009-0002-3931-7374)
- Xueqing Peng
- Yujia Zhou (ORCID: https://orcid.org/0000-0002-3716-7854)
- Yan Hu (ORCID: https://orcid.org/0000-0001-8723-9900)
- Cathy Shyr
- Kirk E Roberts
- Xiaoqian Jiang
- Vipina K Keloth
- Qingyu Chen
- Hua Xu
- Xu Zuo
- Jimin Huang
- Ruey-Ling Weng
Institutions
- Yale University (US)
- Vanderbilt University Medical Center (US)
- The University of Texas Health Science Center at Houston (US)
Publication Details
- Journal
- Journal of the American Medical Informatics Association
- Published
- 2025-11-21
- DOI
- https://doi.org/10.1093/jamia/ocaf213
- Citations
- 2
- Primary Topic
- Topic Modeling
- Type
- article
- Field-Weighted Citation Impact
- 4.96