Optimizing Data Extraction: Harnessing RAG and LLMs for German Medical Documents
Studies in Health Technology and Informatics · 2024
DOI: 10.3233/shti240567 ↗Kurz gefasst
Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, 2024. Verfasst von Yingding Wang und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pediatrics, Dr. von Hauner Children's Hospital, University Hospital, LMU Munich, Munich, Germany. Hauptthemen laut MEDLINE: Electronic Health Records, Natural Language Processing. Die Arbeit wurde bisher 2-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
In the field of medical data analysis, converting unstructured text documents into a structured format suitable for further use is a significant challenge. This study introduces an automated local deployed data privacy secure pipeline that uses open-source Large Language Models (LLMs) with Retrieval-Augmented Generation (RAG) architecture to convert medical German language documents with sensitive health-related information into a structured format. Testing on a proprietary dataset of 800 unstructured original medical reports demonstrated an accuracy of up to 90% in data extraction of the pipeline compared to data extracted manually by physicians and medical students. This highlights the pipeline’s potential as a valuable tool for efficiently extracting relevant data from unstructured sources.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Pediatrics, Dr. von Hauner Children's Hospital, University Hospital, LMU Munich, Munich, Germany.
- Medical Technology and IT (MIT), University Hospital, LMU Munich, Munich, Germany.
- Department of Radiology, University Hospital, LMU Munich, Munich, Germany.
- Institute for Digital Medicine, University Hospital Augsburg, Augsburg, Germany.
Zitieren
APA
Wang, Y., Leutner, S., Ingrisch, M., Klein, C., Hinske, L. C., & Danhauser, K. (2024). Optimizing Data Extraction: Harnessing RAG and LLMs for German Medical Documents. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti240567
Vancouver
Wang Y, Leutner S, Ingrisch M, Klein C, Hinske LC, Danhauser K. Optimizing Data Extraction: Harnessing RAG and LLMs for German Medical Documents. Studies in Health Technology and Informatics. 2024. doi:10.3233/shti240567
BibTeX
@article{Wang2024,
author = {Wang, Yingding and Leutner, Simon and Ingrisch, Michael and Klein, Christoph and Hinske, Ludwig Christian and Danhauser, Katharina},
title = {Optimizing Data Extraction: Harnessing RAG and LLMs for German Medical Documents},
journal = {Studies in Health Technology and Informatics},
year = {2024},
doi = {10.3233/shti240567}
}
EUVIMED