Leveraging Large Language Models for Temporal PHI De-identification in Real-World Clinical Notes
Wang, X.; Wang, L.; Wen, A.; Li, R.; Lu, S.; Hu, Y.; Li, X.; Lyu, H.; Liu, H.
Show abstract
De-identifying temporal protected health information (PHI) is challenging because temporal expressions appear in diverse formats and must be transformed while preserving clinically meaningful timelines. This study proposes and evaluates an LLM-based framework for temporal PHI de-identification in real-world clinical notes. Using 1,148 notes from 30 sarcoma patients (28,431 annotated temporal entities), we evaluated multiple modern LLMs for temporal entity extraction and surrogate generation. Proprietary models achieved strong extraction performance, with GPT-4o achieving the best overall results. Most models preserved temporal formatting (>99%), but surrogate generation remained challenging. GPT-5.4 achieved the highest shift correctness (90.2% on a shared-entity subset) and the lowest order violations. Error analysis revealed systematic shift deviations ({+/-}1, {+/-}30/31, {+/-}365 days), highlighting persistent limitations in LLM temporal reasoning. These findings suggest that reliable temporal de-identification will require hybrid or multi-agent approaches beyond standalone LLMs.
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- A Framework to Assess Clinical Safety and Hallucination Rates of LLMs for Medical Text Summarisation 94%
- Zero Shot Health Trajectory Prediction Using Transformer 94%
- Enhancing Privacy-Preserving Deployable Large Language Models for Perioperative Complication Detection: A Targeted Strategy with LoRA Fine-tuning 94%
Similar papers in this journal
Similar papers in this journal
- Evaluation of Patient-Level Retrieval from Electronic Health Record Data for a Cohort Discovery Task 94%
- Design and Implementation of an End-to-End AI-Driven Colonoscopy Recall Workflow at Scale 93%
- A Study of Calibration as a Measurement of Trustworthiness of Large Language Models in Biomedical Research 93%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.