EDGE-CLOUD CONTINUUM FOR AI-DRIVEN REMOTE PATIENT MONITORING A SCALABLE FRAMEWORK

Abstract

The rapid advancements in healthcare technology, coupled with the increasing demand for real-time patient monitoring, have catalyzed the development of innovative frameworks such as Edge-Cloud convergence. This study presents a scalable architecture leveraging the edge-cloud continuum to enhance remote patient monitoring systems. By integrating lightweight edge devices for real-time anomaly detection and cloud platforms for comprehensive data analytics, the framework addresses critical challenges in latency, scalability, and computational efficiency. Statistical evidence underscores its efficacy: latency reductions of up to 40% and a 20% improvement in early anomaly detection accuracy have been observed in hospital trials involving ICU patients. The framework incorporates IoT devices such as ECG monitors and pulse oximeters, edge gateways for data preprocessing, and AI models retrained in the cloud for continuous optimization. Tools like MQTT, Kafka, and TensorFlow Lite ensure seamless data transmission and efficient AI model deployment, while Apache Spark enhances batch data processing capabilities. By bridging the gap between local computation and centralized data processing, the framework offers a robust solution to modern healthcare challenges, particularly in pandemic scenarios requiring rapid scaling.This study demonstrates how the convergence of AI, edge computing, and cloud platforms can transform patient monitoring systems, delivering scalable, real-time healthcare solutions.