A Two-Stage Generative Framework for Sensitive Health Information Extraction and Temporal Normalization in Medical Records
- 26 June 2026
- book chapter
- Published by Springer Nature
- p. 59-67
Abstract
No abstract availableKeywords
This publication has 6 references indexed in Scilit:
- Benchmarking Recording-Level Clinical Speech De-identification for Privacy-Preserving Clinical AudiomedRxiv, 2026
- Survey and analysis of hallucinations in large language models: attribution to prompting strategies or model behaviorFrontiers in Artificial Intelligence, 2025
- Leveraging large language models for the deidentification and temporal normalization of sensitive health information in electronic health recordsnpj Digital Medicine, 2025
- Privacy preserving strategies for electronic health records in the era of large language modelsnpj Digital Medicine, 2025
- The OpenDeID corpus for patient de-identificationScientific Reports, 2021
- 2010 i2b2/VA challenge on concepts, assertions, and relations in clinical textJournal of the American Medical Informatics Association, 2011