Title :

A Decentralized Framework for Biostatistics and Privacy Concerns

Author(s) :

Mangold, Paul [Auteur correspondant]
École normale supérieure - Lyon [ENS Lyon]
Machine Learning in Information Networks [MAGNET]
Centre Hospitalier Régional Universitaire [Lille] [CHRU Lille]
Filiot, Alexandre [Auteur]
Centre Hospitalier Régional Universitaire [Lille] [CHRU Lille]
Moussa, Mouhamed [Auteur]
Centre Hospitalier Régional Universitaire [Lille] [CHRU Lille]
Sobanski, Vincent [Auteur]
Centre Hospitalier Régional Universitaire [Lille] [CHRU Lille]
Ficheur, Grégoire [Auteur]
Evaluation des technologies de santé et des pratiques médicales - ULR 2694 [METRICS]
Centre Hospitalier Régional Universitaire [Lille] [CHRU Lille]
Andrey, Paul [Auteur]
Centre Hospitalier Régional Universitaire [Lille] [CHRU Lille]
Lamer, Antoine [Auteur]
Centre Hospitalier Régional Universitaire [Lille] [CHRU Lille]
Evaluation des technologies de santé et des pratiques médicales - ULR 2694 [METRICS]

Conference title :

EFMI Special Topic Conference

City :

Virtual

Country :

Finlande

Start date of the conference :

2020-11-26

Journal title :

Studies in health technology and informatics

Publisher :

IOS Press

Publication date :

2020-11-23

English keyword(s) :

federated learning
data privacy
biostatistics

HAL domain(s) :

Informatique [cs]/Bio-informatique [q-bio.QM]
Statistiques [stat]/Machine Learning [stat.ML]

English abstract : [en]

Biostatistics and machine learning have been the cornerstone of a variety of recent developments in medicine. In order to gather large enough datasets, it is often necessary to set up multi-centric studies; yet, centralization ...
Show more >Biostatistics and machine learning have been the cornerstone of a variety of recent developments in medicine. In order to gather large enough datasets, it is often necessary to set up multi-centric studies; yet, centralization of measurements can be difficult, either for practical, legal or ethical reasons. As an alternative, federated learning enables leveraging multiple centers' data without actually collating them. While existing works generally require a center to act as a leader and coordinate computations, we propose a fully decentralized framework where each center plays the same role. In this paper, we apply this framework to logistic regression, including confidence intervals computation. We test our algorithm on two distinct clinical datasets split among different centers, and show that it matches results from the centralized framework. In addition, we discuss possible privacy leaks and potential protection mechanisms, paving the way towards further research.Show less >

Language :

Anglais

Peer reviewed article :

Oui

Audience :

Internationale

Popular science :

Non

Collections :

• Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL