This paper is in the following e-collection/theme issue:

Ethical, Legal, and Social Issues in AI (54) Personal Health Records, Patient-Accessible Electronic Health Records, Patient Portals (626) Applications of AI (156) Generative Language Models Including ChatGPT (457) Electronic Health Records (1149)

Published on in Vol 4 (2025)

Preprints (earlier versions) of this paper are available at https://preprints.jmir.org/preprint/57828, first published .
Harnessing Moderate-Sized Language Models for Reliable Patient Data Deidentification in Emergency Department Records: Algorithm Development, Validation, and Implementation Study

Harnessing Moderate-Sized Language Models for Reliable Patient Data Deidentification in Emergency Department Records: Algorithm Development, Validation, and Implementation Study

Harnessing Moderate-Sized Language Models for Reliable Patient Data Deidentification in Emergency Department Records: Algorithm Development, Validation, and Implementation Study

Authors of this article:

Océane Dorémus1 Author Orcid Image ;   Dylan Russon1 Author Orcid Image ;   Benjamin Contrand1 Author Orcid Image ;   Ariel Guerra-Adames1, 2 Author Orcid Image ;   Marta Avalos-Fernandez2 Author Orcid Image ;   Cédric Gil-Jardiné1, 3 Author Orcid Image ;   Emmanuel Lagarde1 Author Orcid Image
Article Authors Cited by Tweetations Metrics

Océane Dorémus   1 , MSc ;   Dylan Russon   1 , MSc ;   Benjamin Contrand   1 , MSc ;   Ariel Guerra-Adames   1, 2 , BEng, MSc ;   Marta Avalos-Fernandez   2 , HDR, PhD ;   Cédric Gil-Jardiné   1, 3 , MD, PhD ;   Emmanuel Lagarde   1 , HDR, PhD

1 AHeaD Team, University of Bordeaux, INSERM, BPH, U1219, Bordeaux, France

2 SISTM Team, University of Bordeaux, INSERM, INRIA, BPH, U1219, Bordeaux, France

3 Department of Emergency Medicine, Bordeaux University Hospital, Bordeaux, France

Corresponding Author: