Search

Secure extraction of Personally Identifiable Information (PII) from Electronic Health Records (EHRs) presents significant privacy and security challenges. This study explores the application of Federated Learning (FL) to overcome these challenges within the context of French EHRs. By utilizing a multilingual BERT model in an FL simulation involving 20 hospitals, each represented by a unique medical department or pole, we compared the performance of two setups: individual models, where each hospital uses only its own training and validation data without engaging in the FL process, and federated models, where multiple hospitals collaborate to train a global FL model. Our findings demonstrate that FL models not only preserve data confidentiality but also outperform the individual models. In fact, the Global FL model achieved an F1 score of 75,7%, slightly comparable to that of the Centralized approach at 78,5%. This research underscores the potential of FL in extracting PIIs from EHRs, encouraging its broader adoption in health data analysis.

Background: 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., Methods: 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., Results: 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., Conclusions: 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., (© 2024. The Author(s).)

In this paper, we propose a new approach for performing privacy-preserving genome-wide association study (GWAS) in cloud environments. This method allows a Genomic Research Unit (GRU) who possesses genetic variants of diseased individuals (cases) to compare his/her data against genetic variants of healthy individuals (controls) from a Genomic Research Center (GRC). The originality of this work stands on a secure version of the collapsing method based on the logistic regression model considering that all data of GRU are stored into the cloud. To do so, we take advantage of fully homomorphic encryption and of secure multiparty computation. Experiment results carried out on real genetic data using the BGV cryptosystem indicate that the proposed scheme provides the same results as the ones achieved on clear data.

In this paper, we propose a secure protocol that allows processing encrypted data emitted by a medical IOT device. Its originality stands on a new fast algorithm which makes possible the conversion of Combined Linear Congruential Generator (CLCG) encrypted data into data homomorphically encrypted with the Damgard-Jurik (D-J) cryptosystem. By doing so, an honest-but-curious third party, like a smartphone, can process data issued from the IOT devices (e.g. raising a health alert) without endangering data privacy while CLCG can be integrated in an IOT of low computation capabilities. Moreover, in order to reduce communication and computation complexities compared to existing solutions and to achieve a real time solution, we further propose a secure packed version of CLCG in the D-J domain. With it a medical IOT can encrypt several pieces of data at once while allowing a third party to independently convert and process them in their D-J homomorphic encrypted form. We theoretically and experimentally demonstrate the performance of our solution in the case of a connected knee prosthesis, the data of which are processed for patient monitoring.

In this paper, we propose a new scheme of data hiding of encrypted images for the purpose of verifying the reliability of an image into both encrypted and spatial domains. This scheme couples the Quantization Index Modulation (QIM) and the Paillier cryptosystem. It relies on the insertion into the image, before its encryption, of a predefined watermark, a "pre-watermark". Message insertion (resp. extraction) is conducted into (resp. from) the encrypted image using a modified version of QIM. It is the impact of this insertion process onto the "pre-watermark" that gives access to the message in the spatial domain, i.e. after the image has been decrypted. With our scheme, encryption/decryption processes are completely independent from message embedding/extraction. One does not need to know the encryption/decryption key for hiding a message into the encrypted image. Experiments conducted on ultrasound medical images show that the image distortion is very low while offering a high capacity that can support different watermarking based security objectives.

In this paper, we propose a new secure content based image retrieval (SCBIR) system adapted to the cloud framework. This solution allows a physician to retrieve images of similar content within an outsourced and encrypted image database, without decrypting them. Contrarily to actual CBIR approaches in the encrypted domain, the originality of the proposed scheme stands on the fact that the features extracted from the encrypted images are themselves encrypted. This is achieved by means of homomorphic encryption and two non-colluding servers, we however both consider as honest but curious. In that way an end to end secure CBIR process is ensured. Experimental results carried out on a diabetic retinopathy database encrypted with the Paillier cryptosystem indicate that our SCBIR achieves retrieval performance as good as if images were processed in their non-encrypted form.

In this paper, we propose a secure implementation of a content-based image retrieval (CBIR) method that makes possible diagnosis aid systems to work in externalized environment and with outsourced data as in cloud computing. This one works with homomorphic encrypted images from which it extracts wavelet based image features next used for subsequent image comparison. By doing so, our system allows a physician to retrieve the most similar images to a query image in an outsourced database while preserving data confidentiality. Our Secure CBIR is the first one that proposes to work with global image features extracted from encrypted images and does not induce extra communications in-between the client and the server. Experimental results show it achieves retrieval performance as good as if images were processed non-encrypted.