Impact of LLM Scale and Quantization on Information Extraction from Clinical Text
Studies in Health Technology and Informatics · 21.05.2026
DOI: 10.3233/shti260295 ↗Kurz gefasst
Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, erschienen am 21.05.2026. Verfasst von Alban Bornet und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology and Medical Informatics, University of Geneva, Switzerland. Hauptthemen laut MEDLINE: Large Language Models, Electronic Health Records, Natural Language Processing, Data Mining. Die Arbeit wurde bisher 1-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Large Language Models (LLMs) show strong potential for extracting structured information from unstructured clinical narratives. However, their adoption in healthcare is constrained by privacy requirements that necessitate local deployment, often under limited computational resources. This study systematically investigates the trade-offs between model size and numerical precision (quantization) in locally deployed, open-source LLMs applied to a clinical information extraction task. Using seven reasoning models from the Qwen3 and DeepSeek-R1 families (0.6B–70B parameters) and six quantization levels (2, 3, 4, 5, 6, and 8 bits), we evaluated performance on the classification of the modified Rankin Scale (mRS) score from 105 neurosurgery patient notes. A linear mixed-effects analysis revealed significant effects for log-scaled model size (β=-0.84, p
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Radiology and Medical Informatics, University of Geneva, Switzerland.
- Department of Neurosurgery, University Hospitals of Geneva, Switzerland.
Zitieren
APA
Bornet, A., Sandralegar, A., Yazdani, A., Bijlenga, P., & Teodoro, D. (2026). Impact of LLM Scale and Quantization on Information Extraction from Clinical Text. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti260295
Vancouver
Bornet A, Sandralegar A, Yazdani A, Bijlenga P, Teodoro D. Impact of LLM Scale and Quantization on Information Extraction from Clinical Text. Studies in Health Technology and Informatics. 2026. doi:10.3233/shti260295
BibTeX
@article{Bornet2026,
author = {Bornet, Alban and Sandralegar, Abiram and Yazdani, Anthony and Bijlenga, Philippe and Teodoro, Douglas},
title = {Impact of LLM Scale and Quantization on Information Extraction from Clinical Text},
journal = {Studies in Health Technology and Informatics},
year = {2026},
doi = {10.3233/shti260295}
}
EUVIMED