Intelligent IoT-Enabled Framework for Real-Time Prediction of Heart Disease Using Machine Learning

Abstract

This study presents a machine learning–inspired IoT framework designed for the real-time prediction of heart disease using data collected from Internet of Medical Things (IoMT) devices. The proposed system integrates physiological data from various sensors such as blood pressure monitors, heart rate sensors, and ECG devices, enabling continuous health monitoring. Preprocessing techniques like noise reduction, normalization, and missing value imputation are applied to ensure data quality. Feature selection methods are used to identify the most relevant health indicators, which are then fed into optimized machine learning models, including Support Vector Machines (SVM), Random Forests, and eXtreme Gradient Boosting (XGBoost), for effective classification. The framework is designed for scalability and real-time responsiveness, leveraging cloud infrastructure for fast processing and storage. Experimental results on a real-world cardiovascular dataset show improved accuracy, reduced false positives, and enhanced reliability compared to conventional methods. This framework aims to support early diagnosis, timely intervention, and improved patient outcomes in smart healthcare environments.