Scaling Responsible Medical Text Retrieval Across Silos: Evaluating Small Language Models with Retrieval-Augmented Generation
Studies in Health Technology and Informatics · 2026
DOI: 10.3233/shti260043 ↗Kurz gefasst
Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, 2026. Verfasst von Rahul Shetty und 1 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Health Policy, Management and Evaluation, Dalla Lana School of Public Health, University of Toronto, Toronto, ON, Canada. Hauptthemen laut MEDLINE: Electronic Health Records, Natural Language Processing, Information Storage and Retrieval, Diabetes Mellitus. Die Arbeit wurde bisher 1-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
This study evaluates small language models with FAISS and Dynamic Top-k for diabetes-focused medical text retrieval, with all-mpnet-base-v2 performing best and FAISS (FAISS Facebook AI Similarity Search) maintaining sub-2 ms latency even at tenfold scale. Dynamic Top-k improved precision and nDCG (Normalized Discounted Cumulative Gain), showing that lightweight SLM–RAG (Small Language Model-Retrieval Augmented Generation) pipelines can approach larger-model accuracy while remaining highly scalable for cloud-based EMR (Electronic Medical Record) environments.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Institute of Health Policy, Management and Evaluation, Dalla Lana School of Public Health, University of Toronto, Toronto, ON, Canada.
Zitieren
APA
Shetty, R., & Keshavjee, K. (2026). Scaling Responsible Medical Text Retrieval Across Silos: Evaluating Small Language Models with Retrieval-Augmented Generation. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti260043
Vancouver
Shetty R, Keshavjee K. Scaling Responsible Medical Text Retrieval Across Silos: Evaluating Small Language Models with Retrieval-Augmented Generation. Studies in Health Technology and Informatics. 2026. doi:10.3233/shti260043
BibTeX
@article{Shetty2026,
author = {Shetty, Rahul and Keshavjee, Karim},
title = {Scaling Responsible Medical Text Retrieval Across Silos: Evaluating Small Language Models with Retrieval-Augmented Generation},
journal = {Studies in Health Technology and Informatics},
year = {2026},
doi = {10.3233/shti260043}
}
EUVIMED