Hybrid Machine Learning for IOT-Driven Heart Health Prediction: A Review

Heart disease remains one of the leading causes of death worldwide, particularly among elderly individuals and those with sedentary lifestyles. Early detection and real-time monitoring are essential to prevent life-threatening cardiac events. Traditional healthcare systems, which rely on manual supervision and prolonged hospitalization, are neither efficient nor scalable. This project presents a secure, IoT-enabled Body Sensor Network (BSN) integrated with a Hybrid Machine Learning model combining Artificial Neural Network (ANN) and Random Forest (RF) algorithms for accurate and reliable heart disease prediction. IoT sensors interfaced with an Arduino UNO continuously measure vital parameters such as ECG, heart rate, blood pressure, and body temperature. The data is transmitted to a cloud-based database for preprocessing and analysis. The hybrid ANN + RF model enhances classification accuracy by combining ANN’s deep pattern recognition capabilities with RF’s robust feature selection and ensemble learning. This integrated approach ensures high-accuracy disease prediction, real-time monitoring, and automatic alert generation to healthcare professionals. The proposed system promotes efficient, low-cost, and patient-centric healthcare, reducing manual intervention and enabling continuous remote supervision.