AI-Driven Fog-Edge Computing for IoMT Systems: Architecture and Use Cases

Abstract

The Internet of Medical Things (IoMT) transforms healthcare by enabling real-time monitoring, diagnostics, and treatment through interconnected medical devices. However, data security, privacy, and latency remain critical concerns. This paper proposes an AI-driven fog-edge computing architecture designed to enhance the performance, security, and responsiveness of IoMT systems. We first review recent advancements in AI-enabled IoMT platforms and highlight their limitations. We then introduce a novel fog-edge model that integrates artificial intelligence to optimize data processing and decision-making at the network edge, reducing latency and improving system reliability. Strategies for strengthening data security within IoMT environments are also presented. Furthermore, we examine real-world use cases demonstrating the effectiveness of AI-powered fog-edge architectures in healthcare, including their role in enabling contactless patient care. Finally, we discuss problem formulations and data acquisition methods and outline future research directions. This study provides a comprehensive framework for advancing secure and efficient IoMT systems using AI at the fog-edge layer.