Large Language Models for Automatic Deidentification of Electronic Health Record Notes

International Workshop, IW-DMRN 2024, Kaohsiung, Taiwan, January 15, 2024, Revised Selected Papers
2025
ISBN: 978-981-97-7965-9
Verlag: Springer Nature Singapore

Buch, Englisch, 214 Seiten, Format (B × H): 155 mm x 235 mm, Gewicht: 353 g

Reihe: Communications in Computer and Information Science

This volume constitutes the refereed proceedings of the International Workshop on Deidentification of Electronic Health Record Notes, IW-DMRN 2024, held on January 15, 2024, in Kaohsiung, Taiwan.

The 15 full papers were carefully reviewed and selected from 30 submissions. The conference focuses on medical data analysis, enhancing medication safety, and optimizing medical care efficiency.

Zielgruppe

Research

Autoren/Hrsg.

Jonnagaddala, Jitendra

Chen, Ching-Tai

Dai, Hong-Jie

Fachgebiete

• Mathematik | Informatik EDV | Informatik Informatik

Inhaltsverzeichnis

.- Deidentification And Temporal Normalization of The Electronic Health Record Notes Using Large Language Models: The 2023 SREDH/AI-Cup Competition for Deidentification of Sensitive Health Information.

.- Enhancing Automated De-identification of PathologyText Notes Using Pre-Trained Language Models.

.- A Comparative Study of GPT3.5 Fine Tuning and Rule-Based Approaches for De-identification and Normalization of Sensitive Health Information in Electronic Medical Record Notes.

.- Advancing Sensitive Health Data Recognition and Normalization through Large Language Model Driven Data Augmentation.

.- Privacy Protection and Standardization of Electronic Medical Records Using Large Language Model.

.- Applying Language Models for Recognizing and Normalizing Sensitive Information from Electronic Health Records Text Notes.

.- Enhancing SHI Extraction and Time Normalization in Healthcare Records Using LLMs and Dual- Model Voting.

.- Evaluation of OpenDeID Pipeline in the 2023 SREDH/AI-Cup Competition for Deidentification of Sensitive Health Information.

.- Sensitive Health Information Extraction from EMR Text Notes: A Rule-Based NER Approach Using Linguistic Contextual Analysis.

.- A Hybrid Approach to the Recognition of Sensitive Health Information: LLM and Regular Expressions.

.- Patient Privacy Information Retrieval with Longformer and CRF, Followed by Rule-Based Time Information Normalization: A Dual-Approach Study.

.- A Deep Dive into the Application of Pythia for Enhancing Medical Information De-identification in the AI CUP 2023.

.- Utilizing Large Language Models for Privacy Protection and Advancing Medical Digitization.

.- Comprehensive Evaluation of Pythia Model Efficiency in De-identification and Normalization for Enhanced Medical Data Management.

.- A Two-stage Fine-tuning Procedure to Improve the Performance of Language Models in Sensitive Health Information Recognition and Normalization Tasks.