Learning Without Sharing: A Comparative Study of Federated Learning Models for Healthcare

Anja Campmans, Mina Alishahi, Vahideh Moghtadaiee

2025

Abstract

Federated Learning (FL) has emerged as a powerful approach for training machine learning (ML) models on decentralized healthcare data while maintaining patient privacy. However, selecting the most suitable FL model remains a challenge due to inherent trade-offs between accuracy and privacy. This study presents a comparative analysis of multiple FL optimization strategies applied to two real-world tabular health datasets. We evaluate the performance of FL models in terms of predictive accuracy, and resilience to privacy threats.Our findings provide insights into the practical deployment of FL in healthcare, highlighting key trade-offs and offering recommendations for selecting suitable FL models based on specific privacy and accuracy requirements.

Paper Citation

in Harvard Style

Campmans A., Alishahi M. and Moghtadaiee V. (2025). Learning Without Sharing: A Comparative Study of Federated Learning Models for Healthcare. In Proceedings of the 22nd International Conference on Security and Cryptography - Volume 1: SECRYPT; ISBN 978-989-758-760-3, SciTePress, pages 735-740. DOI: 10.5220/0013635000003979

in Bibtex Style

@conference{secrypt25,
author={Anja Campmans and Mina Alishahi and Vahideh Moghtadaiee},
title={Learning Without Sharing: A Comparative Study of Federated Learning Models for Healthcare},
booktitle={Proceedings of the 22nd International Conference on Security and Cryptography - Volume 1: SECRYPT},
year={2025},
pages={735-740},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013635000003979},
isbn={978-989-758-760-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 22nd International Conference on Security and Cryptography - Volume 1: SECRYPT
TI - Learning Without Sharing: A Comparative Study of Federated Learning Models for Healthcare
SN - 978-989-758-760-3
AU - Campmans A.
AU - Alishahi M.
AU - Moghtadaiee V.
PY - 2025
SP - 735
EP - 740
DO - 10.5220/0013635000003979
PB - SciTePress