A Decentralized Framework for Biostatistics ...
Document type :
Communication dans un congrès avec actes
DOI :
Title :
A Decentralized Framework for Biostatistics and Privacy Concerns
Author(s) :
Mangold, Paul [Auteur correspondant]
École normale supérieure de Lyon [ENS de 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]
École normale supérieure de Lyon [ENS de 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
data privacy
biostatistics
HAL domain(s) :
Informatique [cs]/Bio-informatique [q-bio.QM]
Statistiques [stat]/Machine Learning [stat.ML]
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 >
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 :
Source :
Files
- https://hal.inria.fr/hal-03110739/document
- Open access
- Access the document
- https://doi.org/10.3233/shti200710
- Open access
- Access the document
- https://hal.inria.fr/hal-03110739/document
- Open access
- Access the document
- https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI200710
- Open access
- Access the document
- https://hal.inria.fr/hal-03110739/document
- Open access
- Access the document
- document
- Open access
- Access the document
- SHTI-275-SHTI200710.pdf
- Open access
- Access the document
- SHTI200710
- Open access
- Access the document