Federated Learning Applications in Healthcare Informatics: A Comprehensive Review

The healthcare industry has undergone a profound transformation, becoming increasingly reliant on sensitive patient data. However, strict privacy regulations have inadvertently led to the formation of isolated data silos. Federated Learning (FL) has emerged as a promising paradigm to overcome these barriers, enabling collaborative model training across institutions without exposing raw patient data. This survey provides a comprehensive review of FL applications in healthcare informatics and systematically categorise the existing literature based on application domains, FL architectures, and fundamental challenges such as system heterogeneity, computational efficiency, and data security. Furthermore, we discuss the foundational workflows of FL, its transformative potential in medical applications, and the current tools available for deployment, offering a holistic perspective on the state-of-the-art and future research directions.