Abstract

The global public health scenario requires fast, smart, and responsive surveillance mechanisms with early anomaly detection and real-time response. Centralized cloud-based systems, being traditionally common, tend to be plagued with latency, bandwidth constraints, and privacy concerns, making them suboptimal for mission-critical public health solutions. This article discusses how Edge Computing and Artificial Intelligence (AI) integration can be used to improve real-time public health monitoring systems. By deploying computational power near sources of data and placing smart algorithms closer to the sources, edge-AI systems offer quicker response times, reduced bandwidth usage, and increased data privacy. We compare state-of-the-art edge-AI frameworks, review new advances in public health monitoring by leveraging such technologies, and outline a multi-layer design geared towards outbreak detection, contact tracing, and environmental sensing. Experimental test runs utilizing public health benchmark data sets exhibit reductions in latency, accuracy, and scalability relative to traditional cloud infrastructures. The study makes its contribution to a widening debate concerning decentralized health intelligence and establishes an architectural pathway towards future intelligent smart health infrastructure. Additionally, the work provides opportunities for greater expansion of healthcare equity by making sustainable health surveillance capabilities available for geographically dispersed remote or underserved areas at a minimal infrastructural footprint