Automatic de-identification of French electronic health records: a cost-effective approach exploiting distant supervision and deep learning models

• Published in: BMC medical informatics and decision making Vol. 24; no. 1; pp. 54 - 18
• Main Authors: Azzouzi, Mohamed El, Coatrieux, Gouenou, Bellafqira, Reda, Delamarre, Denis, Riou, Christine, Oubenali, Naima, Cabon, Sandie, Cuggia, Marc, Bouzillé, Guillaume
• Format: Journal Article
• Language: English
• Published: England BioMed Central Ltd 16-02-2024; BioMed Central; BMC
• Series: Bmc Medical Informatics and Decision Making
• Subjects: Analysis; Annotations; Automatic annotation; Bioengineering; Clinical de-identification; Datasets; Deep learning; Distant supervision; Effectiveness; Electronic health records; Electronic medical records; Electronic records; Government regulations; Knowledge bases (artificial intelligence); Life Sciences; Machine learning; Medical care, Cost of; Medical records; Named entity recognition; Neural networks; Privacy; State-of-the-art reviews; Word representations; France; Deep learning; Distant supervision; Clinical de-identification; Named entity recognition; Automatic annotation; Word representations; French language
• ISSN: 1472-6947; 1472-6947
• DOI: 10.1186/s12911-024-02422-5

Electronic health records (EHRs) contain valuable information for clinical research; however, the sensitive nature of healthcare data presents security and confidentiality challenges. De-identification is therefore essential to protect personal data in EHRs and comply with government regulations. Named entity recognition (NER) methods have been proposed to remove personal identifiers, with deep learning-based models achieving better performance. However, manual annotation of training data is time-consuming and expensive. The aim of this study was to develop an automatic de-identification pipeline for all kinds of clinical documents based on a distant supervised method to significantly reduce the cost of manual annotations and to facilitate the transfer of the de-identification pipeline to other clinical centers.
We proposed an automated annotation process for French clinical de-identification, exploiting data from the eHOP clinical data warehouse (CDW) of the CHU de Rennes and national knowledge bases, as well as other features. In addition, this paper proposes an assisted data annotation solution using the Prodigy annotation tool. This approach aims to reduce the cost required to create a reference corpus for the evaluation of state-of-the-art NER models. Finally, we evaluated and compared the effectiveness of different NER methods.
A French de-identification dataset was developed in this work, based on EHRs provided by the eHOP CDW at Rennes University Hospital, France. The dataset was rich in terms of personal information, and the distribution of entities was quite similar in the training and test datasets. We evaluated a Bi-LSTM + CRF sequence labeling architecture, combined with Flair + FastText word embeddings, on a test set of manually annotated clinical reports. The model outperformed the other tested models with a significant F1 score of 96,96%, demonstrating the effectiveness of our automatic approach for deidentifying sensitive information.
This study provides an automatic de-identification pipeline for clinical notes, which can facilitate the reuse of EHRs for secondary purposes such as clinical research. Our study highlights the importance of using advanced NLP techniques for effective de-identification, as well as the need for innovative solutions such as distant supervision to overcome the challenge of limited annotated data in the medical domain.