The Best of All Worlds: A Hybrid Approach to Cohort Identification with Rules, Small and Large Language Models
Studies in Health Technology and Informatics · 2025
DOI: 10.3233/shti250948 ↗Kurz gefasst
Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, 2025. Verfasst von Qiwei Gan und 7 weiteren Autor:innen. Beteiligte Einrichtung: VA Salt Lake City Health Care System, Salt Lake City, UT, USA. Hauptthemen laut MEDLINE: Natural Language Processing, Electronic Health Records, Data Mining. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Balancing operational feasibility with the performance of natural language processing (NLP) systems is a significant challenge. This study presents a hybrid strategy to integrate manually curated rules, small language model (SLM), and large language model (LLM) for cohort identification tasks. This approach demonstrates superior performance in terms of both computational efficiency and NLP validity, as shown here in two separate tasks using large number of clinical notes from the US Department of Veteran Affairs (VA) Healthcare system.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- VA Salt Lake City Health Care System, Salt Lake City, UT, USA.
- Department of Internal Medicine, University of Utah Medical School, Salt Lake.
Zitieren
APA
Gan, Q., Shi, J., Bowles, A., Hanchrow, E., Stanley, J., Hu, M., Duvall, S. L., & Alba, P. R. (2025). The Best of All Worlds: A Hybrid Approach to Cohort Identification with Rules, Small and Large Language Models. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti250948
Vancouver
Gan Q, Shi J, Bowles A, Hanchrow E, Stanley J, Hu M, et al. The Best of All Worlds: A Hybrid Approach to Cohort Identification with Rules, Small and Large Language Models. Studies in Health Technology and Informatics. 2025. doi:10.3233/shti250948
BibTeX
@article{Gan2025,
author = {Gan, Qiwei and Shi, Jianlin and Bowles, Annie and Hanchrow, Elizabeth and Stanley, John and Hu, Mengke and Duvall, Scott L and Alba, Patrick R},
title = {The Best of All Worlds: A Hybrid Approach to Cohort Identification with Rules, Small and Large Language Models},
journal = {Studies in Health Technology and Informatics},
year = {2025},
doi = {10.3233/shti250948}
}
EUVIMED