# Development and validation of a natural language processing algorithm to pseudonymize documents in the context of a clinical data warehouse

arXiv: https://arxiv.org/abs/2303.13451 · HTML: https://mlsanity.com/paper/2303.13451/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 37 references that are in the map.
- First posted on arXiv 23 Mar 2023.

## Builds on (most cited first, 12 of 12)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks](https://mlsanity.com/paper/1802.08232/) (2018)
- [CamemBERT: a Tasty French Language Model](https://mlsanity.com/paper/1911.03894/) (2019)
- [Carbontracker: Tracking and Predicting the Carbon Footprint of Training Deep Learning Models](https://mlsanity.com/paper/2007.03051/) (2020)
- [Does BERT Pretrained on Clinical Notes Reveal Sensitive Data?](https://mlsanity.com/paper/2104.07762/) (2021)
- [De-identification of Patient Notes with Recurrent Neural Networks](https://mlsanity.com/paper/1606.03475/) (2016)
- [Single-/Multi-Source Cross-Lingual NER via Teacher-Student Learning on Unlabeled Data in Target Language](https://mlsanity.com/paper/2004.12440/) (2020)
- [FedNER: Privacy-preserving Medical Named Entity Recognition with Federated Learning](https://mlsanity.com/paper/2003.09288/) (2020)
- [Mitigating Temporal-Drift: A Simple Approach to Keep NER Models Crisp](https://mlsanity.com/paper/2104.09742/) (2021)
- [On Sharing Models Instead of Data using Mimic learning for Smart Health Applications](https://mlsanity.com/paper/1912.11210/) (2019)
- [Learning structures of the French clinical language:development and validation of word embedding models using 21 million clinical reports from electronic health records](https://mlsanity.com/paper/2207.12940/) (2022)
- [Towards De-identification of Legal Texts](https://mlsanity.com/paper/1910.03739/) (2019)

## Built on by (most cited first, 3 of 3)

- [PARHAF, a human-authored corpus of clinical reports for fictitious patients in French](https://mlsanity.com/paper/2603.20494/) (2026)
- [Detecting automatically the layout of clinical documents to enhance the performances of downstream natural language processing](https://mlsanity.com/paper/2305.13817/) (2023)
- [Towards the Anonymization of the Language Modeling](https://mlsanity.com/paper/2501.02407/) (2025)

## Abstract (arXiv)

The objective of this study is to address the critical issue of de-identification of clinical reports in order to allow access to data for research purposes, while ensuring patient privacy. The study highlights the difficulties faced in sharing tools and resources in this domain and presents the experience of the Greater Paris University Hospitals (AP-HP) in implementing a systematic pseudonymization of text documents from its Clinical Data Warehouse. We annotated a corpus of clinical documents according to 12 types of identifying entities, and built a hybrid system, merging the results of a deep learning model as well as manual rules. Our results show an overall performance of 0.99 of F1-score. We discuss implementation choices and present experiments to better understand the effort involved in such a task, including dataset size, document types, language models, or rule addition. We share guidelines and code under a 3-Clause BSD license.