Leveraging large language models for the deidentification and temporal normalization of sensitive health information in electronic health records
Authors:
Top Cited Papers
Open Access
- 13 August 2025
- journal article
- Published by Springer Nature in npj Digital Medicine
- Vol. 8 (1) , 517
Abstract
Secondary use of electronic health record notes enhances clinical outcomes and personalized medicine, but risks sensitive health information (SHI) exposure. Inconsistent time formats hinder interpretation, necessitating deidentification and temporal normalization. The SREDH/AI CUP 2023 competition explored large language models (LLMs) for these tasks using 3,244 pathology reports with surrogated SHIs and normalized dates. The competition drew 291 teams; the top teams achieved macro-F1 scores >0.8. Results were presented at the IW-DMRN workshop in 2024. Notably, 77.2% used LLMs, highlighting their growing role in healthcare. This study compares competition results with in-context learning and fine-tuned LLMs. Findings show that fine-tuning, especially with lower-rank adaptation, boosts performance but plateaus or degrades in models over 6 B parameters due to overfitting. Our findings highlight the value of data augmentation, training strategies, and hybrid approaches. Effective LLM-based deidentification requires balancing performance with legal and ethical demands, ensuring privacy and interpretability in regulated healthcare settings.Keywords
Funding Information
- Australian National Health and Medical Research Council (GNT1192469)
- MRFF (MRF2036251)
This publication has 37 references indexed in Scilit:
- BioBERT: a pre-trained biomedical language representation model for biomedical text miningBioinformatics, 2019
- Preserving temporal relations in clinical data while maintaining privacyJournal of the American Medical Informatics Association, 2016
- A context-aware approach for progression tracking of medical concepts in electronic medical recordsJournal of Biomedical Informatics, 2015
- Automated systems for the de-identification of longitudinal clinical narratives: Overview of 2014 i2b2/UTHealth shared task Track 1Journal of Biomedical Informatics, 2015
- Uses of Electronic Health Records for Public Health Surveillance to Advance Public HealthAnnual Review of Public Health, 2015
- Preparing an annotated gold standard corpus to share with extramural investigators for de-identification researchJournal of Biomedical Informatics, 2014
- Electronic health records: new opportunities for clinical researchJournal of Internal Medicine, 2013
- Perspectives of Australian adults about protecting the privacy of their health information in statistical databasesInternational Journal of Medical Informatics, 2012
- Image Data Sharing for Biomedical Research—Meeting HIPAA Requirements for De-identificationJournal of Digital Imaging, 2011
- Evaluating the State-of-the-Art in Automatic De-identificationJournal of the American Medical Informatics Association, 2007