Edge AI and AI driven decision-making

Edge Artificial Intelligence (Edge AI) is redefining the landscape of real-time data processing by enabling AI-driven decision-making directly on devices or near data sources. This paradigm shift is especially transformative in healthcare and Internet of Things (IoT) systems, where low latency, enhanced privacy, and immediate responsiveness are critical. Unlike traditional cloud-centric models, Edge AI supports timely interventions, reduced bandwidth usage, and localized data security—making it a promising solution for time-sensitive and privacy-sensitive applications. This review synthesizes recent literature from peer-reviewed journals, industry whitepapers, and technical case studies to evaluate the applications, benefits, and limitations of Edge AI in healthcare and IoT contexts. Emphasis was placed on studies involving lightweight model design, edge device integration, federated learning, and hierarchical edge-cloud architectures. Sources were systematically analyzed to identify emerging trends, challenges, and technological innovations. The literature reveals that Edge AI can reduce inference latency by up to 90% compared to cloud-based models while maintaining comparable accuracy. Its applications include real-time patient monitoring, anomaly detection, emergency response, and personalized care delivery. Additionally, the adoption of federated learning and on-device processing improves data privacy and reduces reliance on continuous internet connectivity. Technical solutions such as model pruning, quantization, and hardware acceleration are frequently employed to overcome computational limitations on edge devices. Edge AI holds significant potential for revolutionizing healthcare and IoT by offering real-time, secure, and efficient decision-making capabilities. While notable challenges remain—such as device heterogeneity, energy constraints, and security threats—ongoing innovations in model optimization and decentralized learning continue to expand the feasibility and scalability of Edge AI. This review highlights the strategic importance of integrating Edge AI into future digital health and smart infrastructure systems.