‹ back to 2026-09-19

Multi-center Medical Data Mining with FL-Net - A One-stop Shop for Federated Learning

arXiv cs.LG Medical/Healthcare AI Simon Süwer, Julian Klemm, Elisa Acitelli, Mathieu Almeida, Lucia Altucci, Zsolt Bagyura, Michelangela Barbieri, Zsolt-Zoltán Bedő, Rosaria Benedetti, Béla Bihari, Csongor Csalóka, Lucia Dicunta, Stanislav Ehrlich, Bjoern M. Eskofier, Sándor-József Fejér, Georg Fröwis, Walter Hötzendorfer, Alexandra Kautzky-Willer, Jens Johann Georg Lohmann, Marianna Maranghi, Lorenzo Marconi, Rudolf Mayer, Wouter Leonard Megchelenbrink, Monika Moga, Adham Mottalib, Sanjeev Mehta, Madeleine Müller, Thomas Nyström, Balázs-Attila Orbán, Paul O'Toole, Giuseppe Paolisso, Paolo Parini, Matteo Pedrelli, Enrico Petrillo, Philipp Poindl, Niklas Probul, Anastasia Pustozerova, Tanja Šarčević, Lukas Weilguny, Jan Baumbach, Andreas Maier 2026-09-17

TL;DR - FL-Net is an end-to-end federated learning framework for privacy-preserving, multicenter clinical research. It aims to move beyond simulations by supporting reusable harmonized data, secure workflows, auditing, and deployment across real hospital networks.

A review of 14 existing federated learning frameworks found that none met all five requirements derived from the literature.
FL-Net integrates modular data harmonization, cross-study data discovery, disclosure control, versioned tools, and containerized workflow execution.
Evaluations covered MIMIC and US-130 patient discovery plus reproducible, audited workflows with up to 50 concurrent clients.
Its planned deployment spans over 800,000 patients across 10 hospitals in nine countries through two EU projects.

view merged work →