Spatio-Temporal Graph Neural Networks for IoT-Based Continuous Cardiac Health Monitoring Systems

Abstract

The rapid growth of Internet of Things (IoT) and Artificial Intelligence (AI) technologies has significantly transformed healthcare systems, particularly in continuous cardiac health monitoring. Wireless Sensor Networks (WSNs) enable real-time acquisition of physiological data such as ECG, heart rate, and blood pressure through wearable and implantable devices. This paper presents a comprehensive survey of methods and architectures for cardiac monitoring systems based on a three-tier architecture comprising edge, fog, and cloud layers. Spatio-Temporal Graph Convolutional Neural Networks (STGCNs) have emerged as a powerful approach for analysing complex cardiac data by capturing both spatial relationships among sensor nodes and temporal dependencies in physiological signals. These models independently extract spatial and temporal features, reducing information loss while maintaining high accuracy and efficiency. Furthermore, IoT-based cardiac monitoring systems enable early detection of abnormalities and generate real-time alerts, improving patient outcomes and reducing hospital admissions. Optimization techniques such as edge computing, model compression, and energy-aware routing enhance system efficiency and scalability. Despite these advancements, challenges such as data heterogeneity, latency, security, and computational complexity remain. This survey highlights current methods, architectural trends, and research challenges, providing insights into future directions for intelligent cardiac monitoring systems.