Système de surveillance médicale en temps réel avec l’intervention de l’intelligence artificielle Smart Health Guardian System

Abstract

The Internet of Medical Things (IoMT) is a specialized branch of the Internet of Things (IoT) dedicated to healthcare applications. This thesis presents the design, implementation, and evaluation of the Smart Health Guardian System (SHGS), an intelligent remote healthcare monitoring platform that integrates a wearable smart bracelet, a mobile application, a cloud backend, a web dashboard, and an artificial intelligence service for automatic health status classification. The system continuously collects physiological parameters such as heart rate, blood oxygen saturation (SpO₂), body movements, and fall detection. It automatically classifies the patient's condition into three risk levels (GREEN, YELLOW, and RED) and triggers appropriate actions, ranging from passive monitoring to emergency coordination and drone-based medication delivery. Special attention is given to system resilience during network failures and to the security of medical data.

The developed prototype demonstrates the feasibility of a complete IoMT solution, highlighting its modular architecture, local alert capabilities, and AI-assisted decision support. It also identifies several limitations, including wearable miniaturization, battery autonomy, the use of synthetic datasets, and the lack of clinical validation.