Conference paper · 2026 · Open access
Differentially Private De-identification of Dutch Clinical Notes: A Comparative Evaluation
Language Resources and Evaluation Conference (LREC), 113–124 · Published 1 May 2026 · DOI 10.63317/2xrg7fmndfhy
In brief
“Differentially Private De-identification of Dutch Clinical Notes: A Comparative Evaluation” is a 2026 conference paper by Michele Miranda and 6 co-authors, published in Language Resources and Evaluation Conference (LREC). OpenAlex counts 0 citations as of 19 November 2026. It is open access under a CC BY-NC licence: the full text is free to read at Language Resources and Evaluation Conference (LREC).
- Citations
- 0
- References
- 27
- Authors
- 7
Abstract
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.Historically, 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.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Miranda, M., Yan, X., Mishra, N., Murphy, R. M., Abu–Hanna, A., Bratières, S., & Calixto, I. (2026). Differentially Private De-identification of Dutch Clinical Notes: A Comparative Evaluation. Language Resources and Evaluation Conference (LREC), 113–124. https://doi.org/10.63317/2xrg7fmndfhy
MLA 9
Miranda, Michele, et al. “Differentially Private De-identification of Dutch Clinical Notes: A Comparative Evaluation.” Language Resources and Evaluation Conference (LREC), 2026, pp. 113–124. https://doi.org/10.63317/2xrg7fmndfhy.
Chicago
Miranda, Michele, Xinlan Yan, Nishant Mishra, Rachel M. Murphy, Ameen Abu–Hanna, Sébastien Bratières, and Iacer Calixto. 2026. “Differentially Private De-identification of Dutch Clinical Notes: A Comparative Evaluation.” Language Resources and Evaluation Conference (LREC): 113–124. https://doi.org/10.63317/2xrg7fmndfhy.
Harvard
Miranda, M. et al. (2026) ‘Differentially Private De-identification of Dutch Clinical Notes: A Comparative Evaluation’, Language Resources and Evaluation Conference (LREC), pp. 113–124. doi:10.63317/2xrg7fmndfhy.
IEEE
M. Miranda et al., “Differentially Private De-identification of Dutch Clinical Notes: A Comparative Evaluation,” Language Resources and Evaluation Conference (LREC), pp. 113–124, 2026, doi: 10.63317/2xrg7fmndfhy.
BibTeX
@inproceedings{miranda2026differentially,
title = {{Differentially Private De-identification of Dutch Clinical Notes: A Comparative Evaluation}},
author = {Miranda, Michele and Yan, Xinlan and Mishra, Nishant and Murphy, Rachel M. and Abu–Hanna, Ameen and Bratières, Sébastien and Calixto, Iacer},
booktitle = {Language Resources and Evaluation Conference (LREC)},
year = {2026},
pages = {113--124},
doi = {10.63317/2xrg7fmndfhy},
url = {https://doi.org/10.63317/2xrg7fmndfhy}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- differential privacy
- named entity recognition
- large language models
- privacy-utility trade-off
- privacy leakage
- entity classification
- relation classification
- patient privacy
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Miranda, M., Yan, X., Mishra, N., Murphy, R. M., Abu–Hanna, A., Bratières, S., & Calixto, I. (2026). Differentially Private De-identification of Dutch Clinical Notes: A Comparative Evaluation. Language Resources and Evaluation Conference (LREC), 113–124. https://doi.org/10.63317/2xrg7fmndfhy
How many times has this paper been cited?
0 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at Language Resources and Evaluation Conference (LREC): sign in and open the PDF from this page.
Who wrote this paper?
Michele Miranda, Xinlan Yan, Nishant Mishra, Rachel M. Murphy, Ameen Abu–Hanna, Sébastien Bratières, Iacer Calixto.
What is the DOI of this paper?
10.63317/2xrg7fmndfhy, permanently at https://doi.org/10.63317/2xrg7fmndfhy. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.