Abstract Smart healthcare systems are increasingly strained by the limitations of traditional cloud-centric architectures. Cloud computing, while offering robust storage and computational power, struggles with high latency in time-critical scenarios such as Intensive Care Unit (ICU) monitoring and emergency response. Bandwidth constraints further arise as Internet of Medical Things (IoMT) devices generate massive data streams, while centralized data storage introduces significant security and privacy vulnerabilities. These challenges fundamentally limit the effectiveness of cloud-only solutions for real-time patient care. This paper examines how the integration of edge and fog computing with cloud infrastructure addresses these gaps. Edge computing processes data at the point of generation to support low-latency, real-time healthcare applications, while fog computing acts as an intermediate layer that aggregates and preprocesses distributed data sources close to patients. Together, these paradigms form a hierarchical Cloud–Edge–Fog (CEF) framework that enhances responsiveness, reliability, and data security through decentralized processing. Through a PRISMA-guided systematic review and taxonomy-based analysis of 92 peer-reviewed studies, we investigate how emerging technologies such as Artificial Intelligence (AI), Blockchain, Internet of Things (IoT), and Federated Learning (FL) are integrated within CEF architectures to support smart healthcare applications. Our analysis categorizes deployment patterns across telemedicine, chronic disease management, and hospital resource optimization, highlighting how distributed intelligence improves system efficiency and supports real-time clinical decision-making. We identify key challenges including device interoperability, energy efficiency of resource-constrained edge nodes, and the lack of standardized cross-layer communication protocols. Through systematic synthesis of 92 studies, we provide triangulated evidence of CEF benefits while identifying critical gaps—device interoperability (60% of deployments) and standardization—that define future research directions.
Rahman et al. (Mon,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: