TY - JOUR
T1 - Revolutionizing healthcare data analytics with federated learning
T2 - A comprehensive survey of applications, systems, and future directions
AU - Madathil, Nisha Thorakkattu
AU - Dankar, Fida K.
AU - Gergely, Marton
AU - Belkacem, Abdelkader Nasreddine
AU - Alrabaee, Saed
N1 - Publisher Copyright:
© 2025 The Author(s)
PY - 2025/1
Y1 - 2025/1
N2 - Federated learning (FL)–a distributed machine learning that offers collaborative training of global models across multiple clients. FL has been considered for the design and development of many FL systems in various domains. Hence, we present a comprehensive survey and analysis of existing FL systems, drawing insights from more than 250 articles published in 2019-2024. Our review elucidates the functioning of FL systems, particularly in comparison with alternative distributed learning approaches. Considering the healthcare domain as an example, we define the building blocks of a typical FL healthcare system, including system architecture, federation scale, data partitioning, open-source frameworks, ML models, and aggregation algorithms. Furthermore, we identify and discuss key challenges associated with the design and implementation of FL systems within the healthcare sector while outlining the directions of future research. In general, through systematic categorization and analysis of existing FL systems, we offer insights to design efficient, accurate, and privacy-preserving healthcare applications using cutting-edge FL techniques.
AB - Federated learning (FL)–a distributed machine learning that offers collaborative training of global models across multiple clients. FL has been considered for the design and development of many FL systems in various domains. Hence, we present a comprehensive survey and analysis of existing FL systems, drawing insights from more than 250 articles published in 2019-2024. Our review elucidates the functioning of FL systems, particularly in comparison with alternative distributed learning approaches. Considering the healthcare domain as an example, we define the building blocks of a typical FL healthcare system, including system architecture, federation scale, data partitioning, open-source frameworks, ML models, and aggregation algorithms. Furthermore, we identify and discuss key challenges associated with the design and implementation of FL systems within the healthcare sector while outlining the directions of future research. In general, through systematic categorization and analysis of existing FL systems, we offer insights to design efficient, accurate, and privacy-preserving healthcare applications using cutting-edge FL techniques.
KW - Aggregation algorithms
KW - Attacks
KW - Data partitioning
KW - Data privacy
KW - Federated learning
KW - Non-identically distributed data
UR - https://www.scopus.com/pages/publications/105007981308
UR - https://www.scopus.com/pages/publications/105007981308#tab=citedBy
U2 - 10.1016/j.csbj.2025.06.009
DO - 10.1016/j.csbj.2025.06.009
M3 - Review article
AN - SCOPUS:105007981308
SN - 2001-0370
VL - 28
SP - 217
EP - 238
JO - Computational and Structural Biotechnology Journal
JF - Computational and Structural Biotechnology Journal
ER -