Edge AI for Real-Time Medical Monitoring Using Wearable and Implantable Healthcare Devices

Abstract

Abstract. This study explores the synergy of edge artificial intelligence (AI), wearables, and Internet of Medical Things (IoMT) in real-time healthcare monitoring and clinical decision support. The goal is to analyze medical and physiological information at the edge to lower latency, protect privacy and enable early detection of abnormal health conditions. A structured literature review was carried out on 24 recent publications of wearable health sensors, edge intelligence, IoMT architectures, embedded AI, remote patient monitoring, personalized rehabilitation, chronic disease management, and secure healthcare applications. The papers examined show that edge AI allows for faster data processing, real-time patient monitoring, efficient anomaly detection, reduced reliance on the cloud environment and enhanced energy efficiency in wearable and IoT medical devices. Multimodal deep learning and personalized edge analytics provide additional assistance to predictive and patient specific healthcare services. Yet there are some issues that need to be addressed - such as computational constraints, interoperability, data security, the reliability of the models, and deployment that uses limited resources. Overall, the results highlight the potential of wearable devices, IoMT, and edge AI for developing scalable, low-latency, privacy-preserving, and intelligent health monitoring systems that can facilitate remote and personalized health care delivery.