Enregistré dans:
Détails bibliographiques
Auteurs principaux: Miranda, Michele, Yan, Xinlan, Mishra, Nishant, Murphy, Rachel, Abu-Hanna, Ameen, Bratières, Sébastien, Calixto, Iacer
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2604.21421
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866918464140083200
author Miranda, Michele
Yan, Xinlan
Mishra, Nishant
Murphy, Rachel
Abu-Hanna, Ameen
Bratières, Sébastien
Calixto, Iacer
author_facet Miranda, Michele
Yan, Xinlan
Mishra, Nishant
Murphy, Rachel
Abu-Hanna, Ameen
Bratières, Sébastien
Calixto, Iacer
contents Protecting patient privacy in clinical narratives is essential for enabling secondary use of healthcare data under regulations such as GDPR and HIPAA. While manual de-identification remains the gold standard, it is costly and slow, motivating the need for automated methods that combine privacy guarantees with high utility. Most automated text de-identification pipelines employed named entity recognition (NER) to identify protected entities for redaction. Although methods based on differential privacy (DP) provide formal privacy guarantees, more recently also large language models (LLMs) are increasingly used for text de-identification in the clinical domain. In this work, we present the first comparative study of DP, NER, and LLMs for Dutch clinical text de-identification. We investigate these methods separately as well as hybrid strategies that apply NER or LLM preprocessing prior to DP, and assess performance in terms of privacy leakage and extrinsic evaluation (entity and relation classification). We show that DP mechanisms alone degrade utility substantially, but combining them with linguistic preprocessing, especially LLM-based redaction, significantly improves the privacy-utility trade-off.
format Preprint
id arxiv_https___arxiv_org_abs_2604_21421
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Differentially Private De-identification of Dutch Clinical Notes: A Comparative Evaluation
Miranda, Michele
Yan, Xinlan
Mishra, Nishant
Murphy, Rachel
Abu-Hanna, Ameen
Bratières, Sébastien
Calixto, Iacer
Cryptography and Security
Artificial Intelligence
Computation and Language
Protecting patient privacy in clinical narratives is essential for enabling secondary use of healthcare data under regulations such as GDPR and HIPAA. While manual de-identification remains the gold standard, it is costly and slow, motivating the need for automated methods that combine privacy guarantees with high utility. Most automated text de-identification pipelines employed named entity recognition (NER) to identify protected entities for redaction. Although methods based on differential privacy (DP) provide formal privacy guarantees, more recently also large language models (LLMs) are increasingly used for text de-identification in the clinical domain. In this work, we present the first comparative study of DP, NER, and LLMs for Dutch clinical text de-identification. We investigate these methods separately as well as hybrid strategies that apply NER or LLM preprocessing prior to DP, and assess performance in terms of privacy leakage and extrinsic evaluation (entity and relation classification). We show that DP mechanisms alone degrade utility substantially, but combining them with linguistic preprocessing, especially LLM-based redaction, significantly improves the privacy-utility trade-off.
title Differentially Private De-identification of Dutch Clinical Notes: A Comparative Evaluation
topic Cryptography and Security
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2604.21421