# An Easy-to-use and Robust Approach for the Differentially Private De-Identification of Clinical Textual Documents

arXiv: https://arxiv.org/abs/2211.01147 · HTML: https://mlsanity.com/paper/2211.01147/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 46 references that are in the map.
- First posted on arXiv 2 Nov 2022.

## Builds on (most cited first, 15 of 15)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [BioBERT: a pre-trained biomedical language representation model for biomedical text mining](https://mlsanity.com/paper/1901.08746/) (2019)
- [ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission](https://mlsanity.com/paper/1904.05342/) (2019)
- [Amplification by Shuffling: From Local to Central Differential Privacy via Anonymity](https://mlsanity.com/paper/1811.12469/) (2018)
- [FlauBERT: Unsupervised Language Model Pre-training for French](https://mlsanity.com/paper/1912.05372/) (2019)
- [Privacy- and Utility-Preserving Textual Analysis via Calibrated Multivariate Perturbations](https://mlsanity.com/paper/1910.08902/) (2019)
- [De-identification of Patient Notes with Recurrent Neural Networks](https://mlsanity.com/paper/1606.03475/) (2016)
- [Protecting Locations with Differential Privacy under Temporal Correlations](https://mlsanity.com/paper/1410.5919/) (2014)
- [Optimal Geo-Indistinguishable Mechanisms for Location Privacy](https://mlsanity.com/paper/1402.5029/) (2014)
- [Improving the utility of locally differentially private protocols for longitudinal and multidimensional frequency estimates](https://mlsanity.com/paper/2111.04636/) (2021)
- [Optimal Differentially Private Mechanisms for Randomised Response](https://mlsanity.com/paper/1612.05568/) (2016)
- [Deep Learning Transformer Architecture for Named Entity Recognition on Low Resourced Languages: State of the art results](https://mlsanity.com/paper/2111.00830/) (2021)
- [De-Identification of French Unstructured Clinical Notes for Machine Learning Tasks](https://mlsanity.com/paper/2209.09631/) (2022)
- [Metric-based local differential privacy for statistical applications](https://mlsanity.com/paper/1805.01456/) (2018)

## Built on by (most cited first, 1 of 1)

- [Differentially Private De-identification of Dutch Clinical Notes: A Comparative Evaluation](https://mlsanity.com/paper/2604.21421/) (2026)

## Abstract (arXiv)

Unstructured textual data is at the heart of healthcare systems. For obvious privacy reasons, these documents are not accessible to researchers as long as they contain personally identifiable information. One way to share this data while respecting the legislative framework (notably GDPR or HIPAA) is, within the medical structures, to de-identify it, i.e. to detect the personal information of a person through a Named Entity Recognition (NER) system and then replacing it to make it very difficult to associate the document with the person. The challenge is having reliable NER and substitution tools without compromising confidentiality and consistency in the document. Most of the conducted research focuses on English medical documents with coarse substitutions by not benefiting from advances in privacy. This paper shows how an efficient and differentially private de-identification approach can be achieved by strengthening the less robust de-identification method and by adapting state-of-the-art differentially private mechanisms for substitution purposes. The result is an approach for de-identifying clinical documents in French language, but also generalizable to other languages and whose robustness is mathematically proven.