AI-INTEGRATED IoT SYSTEM USING MACHINE LEARNING TECHNIQUES FOR CONTINUOUS HEALTH TRACKING AND PREDICTIVE PATIENT MONITORING

Abstract

The combination of Artificial Intelligence (AI) and the Internet of Things (IoT) is transforming modern healthcare, especially in the area of remote patient monitoring and disease management. This study focuses on designing and improving an intelligent remote health-monitoring framework that utilizes IoT-based sensing devices together with machine learning techniques. The aim is to enhance diagnostic accuracy, enable real-time health data processing, ensure secure data transmission, and support seamless system integration to improve patient outcomes. To overcome key challenges—including unreliable data, privacy risks, and limited computational resources—a novel and efficient monitoring approach is presented. Multiple machine learning models, such as Random Forest, Support Vector Machine (SVM), and K-Nearest Neighbors (KNN), are applied to analyze vital parameters like heart rate, blood pressure, and ECG signals. Experimental results show that the Random Forest classifier delivers superior performance across accuracy, precision, and recall metrics, making it well suited for real-time healthcare applications. Overall, this research contributes practical insights into AI-driven remote health systems and sets a strong foundation for future advancements in personalized, scalable, and cost-effective healthcare technologies.