Privacy preserving strategies for electronic health records in the era of large language models

Стратегии обеспечения конфиденциальности электронных медицинских записей в эпоху больших языковых моделей
Jitendra Jonnagaddala, Zoie Shui-Yee Wong
2025-01-16

electronic health recordslarge language modelsprivacy preservationsecondary data usesensitive health information
The secondary use of electronic health records (EHRs) involves the utilization of EHR data for various purposes other than their original intent in clinical operations, such as clinical research, health systems and services research, patient registries, quality improvement, disease surveillance, and other areas beyond direct patient care 1 . This secondary use of electronic health records (EHRs) has significantly accelerated in the past decade with advances in artificial intelligence (AI), especially in large language models (LLMs) 2 . EHRs are increasingly used with LLMs for primary uses, such as clinical documentation, generation and summarization, as well as for secondary uses, such as information extraction, retrieval, identification of eligible patients for research, medical education, and outcome reporting. Safeguarding both the structured and unstructured sensitive health information (SHI) of patients from EHRs is essential, particularly when LLMs are used for secondary uses 3 , 4 . Most countries across the world have stipulated regulatory privacy acts, guidelines and frameworks to achieve this goal.
1
LLMs are increasingly applied to EHRs for clinical documentation, text generation, summarization, information extraction, retrieval, research cohort identification, medical education, and outcome reporting.
2
Protecting both structured and unstructured sensitive health information is essential when EHRs are used with LLMs, especially for secondary purposes.
3
Regulatory privacy acts, guidelines, and frameworks have been established in many countries to safeguard patient information during EHR reuse.
4
Secondary use of electronic health records has expanded substantially with advances in artificial intelligence, particularly large language models.

electronic health records (EHRs) containing structured and unstructured sensitive health information, used with large language models (LLMs)

privacy-preserving strategies and regulatory safeguards for the secondary use of EHR data with LLMs

Publication Details
Publication Date
2025-01-16
Journal
Publisher
ISSN
Cited by
90
Access Type
Author Information
Authors
Jitendra Jonnagaddala
Zoie Shui-Yee Wong
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%