Federated learning: a privacy-preserving approach to data-centric regulatory cooperation

Regulatory agencies aim to ensure the safety and efficacy of medical products but often face legal and privacy concerns that hinder collaboration at the data level. In this paper, we propose federated learning as an innovative method to enhance data-centric collaboration among regulatory agencies by...

Full description

Saved in:
Bibliographic Details
Main Authors: Alexander Horst, Paul Loustalot, Sanjeev Yoganathan, Ting Li, Joshua Xu, Weida Tong, David Schneider, Nicolas Löffler-Perez, Erminio Di Renzo, Michael Renaudin
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-05-01
Series:Frontiers in Drug Safety and Regulation
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fdsfr.2025.1579922/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850255628674531328
author Alexander Horst
Paul Loustalot
Sanjeev Yoganathan
Ting Li
Joshua Xu
Weida Tong
David Schneider
Nicolas Löffler-Perez
Erminio Di Renzo
Michael Renaudin
author_facet Alexander Horst
Paul Loustalot
Sanjeev Yoganathan
Ting Li
Joshua Xu
Weida Tong
David Schneider
Nicolas Löffler-Perez
Erminio Di Renzo
Michael Renaudin
author_sort Alexander Horst
collection DOAJ
description Regulatory agencies aim to ensure the safety and efficacy of medical products but often face legal and privacy concerns that hinder collaboration at the data level. In this paper, we propose federated learning as an innovative method to enhance data-centric collaboration among regulatory agencies by enabling collaborative training of machine learning models without the need for direct data sharing, thereby preserving privacy and overcoming legal hurdles. We illustrate how Swissmedic, the Swiss Agency for Therapeutic Products, together with its partner agencies, proposes to use federated learning to improve TRICIA, an AI tool for assessing incoming reports of serious incidents related to medical devices. This approach enables the development of robust, generalisable risk assessment models that can potentially improve current processes. A proof of concept was deployed and thoroughly tested during the 14th Global Summit on Regulatory Science using synthetic data with participants from Swissmedic, the U.S. Food and Drug Administration (FDA), and the Danish Medicines Agency (DKMA), with promising initial results. This innovation has the potential to serve as a roadmap for other regulators to adopt similar approaches to optimize their own regulatory processes, contributing to a more integrated and efficient regulatory environment worldwide.
format Article
id doaj-art-676dae16beda46c4bb07dbad9013c99b
institution OA Journals
issn 2674-0869
language English
publishDate 2025-05-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Drug Safety and Regulation
spelling doaj-art-676dae16beda46c4bb07dbad9013c99b2025-08-20T01:56:49ZengFrontiers Media S.A.Frontiers in Drug Safety and Regulation2674-08692025-05-01510.3389/fdsfr.2025.15799221579922Federated learning: a privacy-preserving approach to data-centric regulatory cooperationAlexander Horst0Paul Loustalot1Sanjeev Yoganathan2Ting Li3Joshua Xu4Weida Tong5David Schneider6Nicolas Löffler-Perez7Erminio Di Renzo8Michael Renaudin9Swissmedic 4.0 and Medical Device Vigilance, Swissmedic, Swiss Agency for Therapeutic Products, Bern, SwitzerlandQuinten Health, Paris, FranceDivision of Medical Devices, The Danish Medicines Agency, Copenhagen, DenmarkNational Center for Toxicological Research, U.S. Food and Drug Administration, Jefferson, AR, United StatesNational Center for Toxicological Research, U.S. Food and Drug Administration, Jefferson, AR, United StatesNational Center for Toxicological Research, U.S. Food and Drug Administration, Jefferson, AR, United StatesSwissmedic 4.0 and Medical Device Vigilance, Swissmedic, Swiss Agency for Therapeutic Products, Bern, SwitzerlandSwissmedic 4.0 and Medical Device Vigilance, Swissmedic, Swiss Agency for Therapeutic Products, Bern, SwitzerlandSwissmedic 4.0 and Medical Device Vigilance, Swissmedic, Swiss Agency for Therapeutic Products, Bern, SwitzerlandSwissmedic 4.0 and Medical Device Vigilance, Swissmedic, Swiss Agency for Therapeutic Products, Bern, SwitzerlandRegulatory agencies aim to ensure the safety and efficacy of medical products but often face legal and privacy concerns that hinder collaboration at the data level. In this paper, we propose federated learning as an innovative method to enhance data-centric collaboration among regulatory agencies by enabling collaborative training of machine learning models without the need for direct data sharing, thereby preserving privacy and overcoming legal hurdles. We illustrate how Swissmedic, the Swiss Agency for Therapeutic Products, together with its partner agencies, proposes to use federated learning to improve TRICIA, an AI tool for assessing incoming reports of serious incidents related to medical devices. This approach enables the development of robust, generalisable risk assessment models that can potentially improve current processes. A proof of concept was deployed and thoroughly tested during the 14th Global Summit on Regulatory Science using synthetic data with participants from Swissmedic, the U.S. Food and Drug Administration (FDA), and the Danish Medicines Agency (DKMA), with promising initial results. This innovation has the potential to serve as a roadmap for other regulators to adopt similar approaches to optimize their own regulatory processes, contributing to a more integrated and efficient regulatory environment worldwide.https://www.frontiersin.org/articles/10.3389/fdsfr.2025.1579922/fullfederated learningregulatory sciencesmedical devicesrisk assessmentswissmedicdata privacy
spellingShingle Alexander Horst
Paul Loustalot
Sanjeev Yoganathan
Ting Li
Joshua Xu
Weida Tong
David Schneider
Nicolas Löffler-Perez
Erminio Di Renzo
Michael Renaudin
Federated learning: a privacy-preserving approach to data-centric regulatory cooperation
Frontiers in Drug Safety and Regulation
federated learning
regulatory sciences
medical devices
risk assessment
swissmedic
data privacy
title Federated learning: a privacy-preserving approach to data-centric regulatory cooperation
title_full Federated learning: a privacy-preserving approach to data-centric regulatory cooperation
title_fullStr Federated learning: a privacy-preserving approach to data-centric regulatory cooperation
title_full_unstemmed Federated learning: a privacy-preserving approach to data-centric regulatory cooperation
title_short Federated learning: a privacy-preserving approach to data-centric regulatory cooperation
title_sort federated learning a privacy preserving approach to data centric regulatory cooperation
topic federated learning
regulatory sciences
medical devices
risk assessment
swissmedic
data privacy
url https://www.frontiersin.org/articles/10.3389/fdsfr.2025.1579922/full
work_keys_str_mv AT alexanderhorst federatedlearningaprivacypreservingapproachtodatacentricregulatorycooperation
AT paulloustalot federatedlearningaprivacypreservingapproachtodatacentricregulatorycooperation
AT sanjeevyoganathan federatedlearningaprivacypreservingapproachtodatacentricregulatorycooperation
AT tingli federatedlearningaprivacypreservingapproachtodatacentricregulatorycooperation
AT joshuaxu federatedlearningaprivacypreservingapproachtodatacentricregulatorycooperation
AT weidatong federatedlearningaprivacypreservingapproachtodatacentricregulatorycooperation
AT davidschneider federatedlearningaprivacypreservingapproachtodatacentricregulatorycooperation
AT nicolaslofflerperez federatedlearningaprivacypreservingapproachtodatacentricregulatorycooperation
AT erminiodirenzo federatedlearningaprivacypreservingapproachtodatacentricregulatorycooperation
AT michaelrenaudin federatedlearningaprivacypreservingapproachtodatacentricregulatorycooperation