Delirium Identification from Nursing Reports Using Large Language Models
Studies in Health Technology and Informatics · 2025
DOI: 10.3233/shti250492 ↗Kurz gefasst
Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, 2025. Verfasst von Lisa Graf und 2 weiteren Autor:innen. Beteiligte Einrichtung: Neurorobotics Lab, Department of Computer Science - University of Freiburg, Germany. Hauptthemen laut MEDLINE: Delirium, Natural Language Processing, Nursing Records, Nursing Diagnosis. Die Arbeit wurde bisher 3-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Themen: Delir
Abstract (Originalsprache)
This study investigates large language models for delirium detection from nursing reports, comparing keyword matching, prompting, and finetuning. Using a manually labelled dataset from the University Hospital Freiburg, Germany, we tested Llama3 and Phi3 models. Both prompting and finetuning were effective, with finetuning Phi3 (3.8B) achieving the highest accuracy (90.24%) and AUROC (96.07%), significantly outperforming other methods.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Neurorobotics Lab, Department of Computer Science - University of Freiburg, Germany.
- Department of Neurology, Medical Center - University of Freiburg, Germany.
- Center of Implementing Nursing Care Innovations Freiburg, Medical Center - University of Freiburg, Germany.
- Centre for Geriatric Medicine and Gerontology (ZGGF), Medical Center - University of Freiburg, Germany.
- Department of Nursing Science, University of Turku, Finland.
Zitieren
APA
Graf, L., Ritzi, A., & Schoeler, L. M. (2025). Delirium Identification from Nursing Reports Using Large Language Models. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti250492
Vancouver
Graf L, Ritzi A, Schoeler LM. Delirium Identification from Nursing Reports Using Large Language Models. Studies in Health Technology and Informatics. 2025. doi:10.3233/shti250492
BibTeX
@article{Graf2025,
author = {Graf, Lisa and Ritzi, Alexander and Schoeler, Lili M},
title = {Delirium Identification from Nursing Reports Using Large Language Models},
journal = {Studies in Health Technology and Informatics},
year = {2025},
doi = {10.3233/shti250492}
}
EUVIMED