Large Language Models for Electronic Health Record De-Identification in English and German
Information · 06.02.2025 · 16 (2) · 112
DOI: 10.3390/info16020112 ↗Kurz gefasst
Fachartikel in der Zeitschrift Information, online erschienen am 06.02.2025. Verfasst von Samuel Sousa und 3 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 102 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Austrian Ministry of Transport, Innovation and Technology (BMVIT), BMK and BMAW.
Abstract (Originalsprache)
Electronic health record (EHR) de-identification is crucial for publishing or sharing medical data without violating the patient’s privacy. Protected health information (PHI) is abundant in EHRs, and privacy regulations worldwide mandate de-identification before downstream tasks are performed. The ever-growing data generation in healthcare and the advent of generative artificial intelligence have increased the demand for de-identified EHRs and highlighted privacy issues with large language models (LLMs), especially data transmission to cloud-based LLMs. In this study, we benchmark ten LLMs for de-identifying EHRs in English and German. We then compare de-identification performance for in-context learning and full model fine-tuning and analyze the limitations of LLMs for this task. Our experimental evaluation shows that LLMs effectively de-identify EHRs in both languages. Moreover, in-context learning with a one-shot setting boosts de-identification performance without the costly full fine-tuning of the LLMs.
Förderung
- Austrian Ministry of Transport, Innovation and Technology (BMVIT)
- BMK and BMAW
Zitieren
APA
Sousa, S., Jantscher, M., Kröll, M., & Kern, R. (2025). Large Language Models for Electronic Health Record De-Identification in English and German. Information, 16(2), 112. https://doi.org/10.3390/info16020112
Vancouver
Sousa S, Jantscher M, Kröll M, Kern R. Large Language Models for Electronic Health Record De-Identification in English and German. Information. 2025;16(2):112. doi:10.3390/info16020112
BibTeX
@article{Sousa2025,
author = {Sousa, Samuel and Jantscher, Michael and Kröll, Mark and Kern, Roman},
title = {Large Language Models for Electronic Health Record De-Identification in English and German},
journal = {Information},
year = {2025},
volume = {16},
number = {2},
pages = {112},
doi = {10.3390/info16020112}
}
EUVIMED