Deep Learning Framework for Advanced De-Identification of Protected Health Information

Ahmad Aloqaily (), Emad E. Abdallah, Rahaf Al-Zyoud, Esraa Abu Elsoud, Malak Al-Hassan and Alaa E. Abdallah
Additional contact information
Ahmad Aloqaily: Department of Information Technology, Faculty of Prince Al-Hussein Bin Abdullah II for Information Technology, The Hashemite University, P.O. Box 330127, Zarqa 13133, Jordan
Emad E. Abdallah: Department of Information Technology, Faculty of Prince Al-Hussein Bin Abdullah II for Information Technology, The Hashemite University, P.O. Box 330127, Zarqa 13133, Jordan
Rahaf Al-Zyoud: Department of Information Technology, Faculty of Prince Al-Hussein Bin Abdullah II for Information Technology, The Hashemite University, P.O. Box 330127, Zarqa 13133, Jordan
Esraa Abu Elsoud: Department of Computer Science, Faculty of Information Technology, Zarqa University, P.O. Box 330127, Zarqa 13133, Jordan
Malak Al-Hassan: King Abdullah II School of Information Technology, The University of Jordan, Amman 11942, Jordan
Alaa E. Abdallah: Department of Computer Science, Faculty of Prince Al-Hussein Bin Abdullah II for Information Technology, The Hashemite University, P.O. Box 330127, Zarqa 13133, Jordan

Future Internet, 2025, vol. 17, issue 1, 1-24

Abstract: Electronic health records (EHRs) are widely used in healthcare institutions worldwide, containing vast amounts of unstructured textual data. However, the sensitive nature of Protected Health Information (PHI) embedded within these records presents significant privacy challenges, necessitating robust de-identification techniques. This paper introduces a novel approach, leveraging a Bi-LSTM-CRF model to achieve accurate and reliable PHI de-identification, using the i2b2 dataset sourced from Harvard University. Unlike prior studies that often unify Bi-LSTM and CRF layers, our approach focuses on the individual design, optimization, and hyperparameter tuning of both the Bi-LSTM and CRF components, allowing for precise model performance improvements. This rigorous approach to architectural design and hyperparameter tuning, often underexplored in the existing literature, significantly enhances the model’s capacity for accurate PHI tag detection while preserving the essential clinical context. Comprehensive evaluations are conducted across 23 PHI categories, as defined by HIPAA, ensuring thorough security across critical domains. The optimized model achieves exceptional performance metrics, with a precision of 99%, recall of 98%, and F1-score of 98%, underscoring its effectiveness in balancing recall and precision. By enabling the de-identification of medical records, this research strengthens patient confidentiality, promotes compliance with privacy regulations, and facilitates safe data sharing for research and analysis.

Keywords: protected health information; electronic health record; deep learning; de-identification; Bi-LSTM-CRF (search for similar items in EconPapers)
JEL-codes: O3 (search for similar items in EconPapers)
Date: 2025
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1999-5903/17/1/47/pdf (application/pdf)
https://www.mdpi.com/1999-5903/17/1/47/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jftint:v:17:y:2025:i:1:p:47-:d:1571002

Access Statistics for this article

Future Internet is currently edited by Ms. Grace You

More articles in Future Internet from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().