An Energy-Efficient Distributed Artificial Intelligence Architecture For Real-Time Healthcare Monitoring In Edge Computing Environments

Abstract

Healthcare monitoring systems powered by artificial intelligence have greatly changed the way modern medical services are provided as it allows intelligent observation of the patient, early identification of the disease, and analysis of physiological data on a regular basis. Nevertheless, traditional cloud-based healthcare systems tend to be characterized by long latency, high energy usage, communication waste, and lack of scalability which makes them less appropriate in the real-time healthcare context. To overcome these constraints, this study makes the proposal of an energy-saving distributed artificial intelligence system to accomplish real-time healthcare monitoring in the setting of edge computing components. The proposed model combines IoT-enabled healthcare sensors, distributed edge computing nodes, and artificial intelligence models to provide low-latency and energy-conscious healthcare analytics. Medical information that is gathered by wearables and smart medical devices are processed and analyzed in distributed edge nodes to limit cloud reliance and enhance the efficiency in response. The framework also integrates a lightweight machine learning and distributed AI processing systems to facilitate real-time healthcare prediction and detection of anomalies at the cost of optimizing the use of computational resources. The metrics of experimental evaluation were AI healthcare prediction and edge computing performance metrics such as accuracy, precision, recall, specificity, F1-score, ROC-AUC, and latency, throughput, response time, and energy consumption. As it was shown experimentally, the presented framework made better predictions in healthcare, decreased the processing latency, minimized the use of energy, and was more scalable than traditional centralized healthcare monitoring systems. The given architecture offers an efficient answer to real-time healthcare monitoring, which is intelligent, scalable, and energy-efficient in the next-generation healthcare smart environments.