Zero-Shot Clinical Data Extraction from Pathology Reports Using Llama 3.1
Studies in Health Technology and Informatics · 2025
DOI: 10.3233/shti251230 ↗Kurz gefasst
Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, 2025. Verfasst von Sunghyeon Park und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medical Informatics, College of Medicine, The Catholic University of Korea. Hauptthemen laut MEDLINE: Data Mining, Electronic Health Records, Natural Language Processing, Information Storage and Retrieval. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
This study evaluates the performance of the Llama 3.1 model with 70 billion parameters (70b) in extracting clinically significant information from free-text pathology reports under zero-shot learning conditions. The model achieved a remarkable accuracy of 98%, directly generating structured outputs in JSON format without requiring annotated examples. These findings demonstrate the potential of Llama 3.1 in automating data extraction from complex medical documents, streamlining clinical workflows, and enhancing the precision of information retrieval in healthcare settings.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Medical Informatics, College of Medicine, The Catholic University of Korea.
- Department of Biomedicine and Health Sciences, The Catholic University of Korea.
Zitieren
APA
Park, S., Choi, W., & Choi, I. (2025). Zero-Shot Clinical Data Extraction from Pathology Reports Using Llama 3.1. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti251230
Vancouver
Park S, Choi W, Choi I. Zero-Shot Clinical Data Extraction from Pathology Reports Using Llama 3.1. Studies in Health Technology and Informatics. 2025. doi:10.3233/shti251230
BibTeX
@article{Park2025,
author = {Park, Sunghyeon and Choi, Wona and Choi, InYoung},
title = {Zero-Shot Clinical Data Extraction from Pathology Reports Using Llama 3.1},
journal = {Studies in Health Technology and Informatics},
year = {2025},
doi = {10.3233/shti251230}
}
EUVIMED