IoT-Enabled Heart Disease Risk Prediction Using Machine Learning Algorithms: A Comparative Analysis of ML Models

This Study will explore how the IoT and machine learning predict heart disease risks through real-time wearable device and sensor data. The Cleveland and Hungarian datasets have relevant health information: age, blood pressure, cholesterol, and ECG readings. The system has three components: data gathering, cleaning and preparing the data, and heart disease risk prediction. We applied Machine Learning Models to the heart disease prediction task and compared each of the using classification metrices. Decision Trees scored high on accuracy and precision, while Logistic Regression worked better on recall and F1-score. Highly accurate results were obtained with Random Forest and SVM on all metrics. This study improves health care by demonstrating support for increased early detection of heart disease and improved clinical decision-making.