A4 Refereed article in a conference publication
Hospital Participation in Federated Learning: Evaluating Sustainability and Clinical Utility
Authors: Kazlouski, Andrei; Montoya Perez, Ileana; Pahikkala, Tapio; Airola, Antti
Editors: N/A
Conference name: Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Publication year: 2025
Journal: Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Book title : 2025 47th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
Volume: 47
ISBN: 979-8-3315-8619-5
eISBN: 979-8-3315-8618-8
ISSN: 2375-7477
eISSN: 2694-0604
DOI: https://doi.org/10.1109/EMBC58623.2025.11252903
Publication's open availability at the time of reporting: No Open Access
Publication channel's open availability : No Open Access publication channel
Web address : https://ieeexplore.ieee.org/document/11252903
Prostate cancer (PCa) diagnosis often relies on biopsies, which can lead to unnecessary procedures and complications. Federated learning (FL) offers a privacy-preserving approach for training predictive models across hospitals without sharing sensitive patient data. In this study, we evaluate the feasibility of FL for PCa risk prediction by benchmarking different training strategies, including local, federated models, as well as free-riding (FR) on federated models. Using real-world heterogeneous datasets from 19 hospitals, we analyze the impact of data diversity and consortium size on predictive performance. Our results show that while FL improves model generalizability, local models often perform comparably, making direct participation in FL less beneficial for large hospitals. However, a small consortium of high-data-quality institutions could collaboratively develop robust models for broader clinical use. We discuss the practical implications of FL in healthcare and propose strategies for sustainable deployment in real-world hospital networks.
Funding information in the publication:
This work has received funding from European Union’s Horizon Europe research and innovation programme (grant number 101095384) and from Research Council of Finland (grants 358868, 345804, 345805, 340140, 340182).
