De-Identification of Free-Text Medical Records Using Large Language Models
Studies in Health Technology and Informatics · 2026
DOI: 10.3233/shti260291 ↗Kurz gefasst
Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, 2026. Verfasst von Richard Noll und 4 weiteren Autor:innen. Beteiligte Einrichtung: Goethe University Frankfurt, University Medicine, Institute of Medical Informatics (IMI), Frankfurt am Main, Germany. Hauptthemen laut MEDLINE: Large Language Models, Electronic Health Records, Confidentiality, Natural Language Processing. 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 large language models (LLMs) for automated de-identification of free-text medical records. Using 150 synthetically generated, personal health information (PHI)-enriched doctor’s letters (23.2 PHIs per letter), we compared the full LLaMA-3.1-8B model (BF16, GPU) with a quantized variant (Q8, CPU) under zero-shot and few-shot prompting. Few-shot prompting improved performance from a macro F1 of 0.989 to 0.996 (recall = 0.994); the quantized Q8 model achieved a macro F1 of 0.992 (recall = 0.987) while enabling fully local, GPU-free inference. Although LLMs perform at a level comparable to human annotation, false negatives remain a concern for highly sensitive PHI, such as names. While human annotators typically require 13.4 seconds per PHI, the LLMs de-identified complete letters within seconds, demonstrating an efficiency and scalability advantage alongside GDPR-compliant, high-precision de-identification.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Goethe University Frankfurt, University Medicine, Institute of Medical Informatics (IMI), Frankfurt am Main, Germany.
Zitieren
APA
Noll, R., Englisch, M., Hofmann, E., Bergmann, N., & Schaaf, J. (2026). De-Identification of Free-Text Medical Records Using Large Language Models. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti260291
Vancouver
Noll R, Englisch M, Hofmann E, Bergmann N, Schaaf J. De-Identification of Free-Text Medical Records Using Large Language Models. Studies in Health Technology and Informatics. 2026. doi:10.3233/shti260291
BibTeX
@article{Noll2026,
author = {Noll, Richard and Englisch, Maximilian and Hofmann, Elias and Bergmann, Nils and Schaaf, Jannik},
title = {De-Identification of Free-Text Medical Records Using Large Language Models},
journal = {Studies in Health Technology and Informatics},
year = {2026},
doi = {10.3233/shti260291}
}
EUVIMED