Heart Disease Prediction using Hybrid Machine Learning with ECG Dataset for Healthcare-IOT Application

Heart-disease is one of the leading cause of death around the world, precaution is only if early detection. This research focuses on the development of a heart disease prediction system using a hybrid machine learning (ML) approach combined with electrocardiogram (ECG) data. The system leverages the strengths of multiple ML algorithms to improve prediction accuracy, analyzing both time-domain and frequency-domain features extracted from ECG signals. By integrating feature selection techniques, the system identifies the most relevant parameters, such as heart rate variability and waveform characteristics, to enhance model performance. The hybrid ML model combines from SVM machine learning and ANN deep learning techniques. The system is implemented within a Healthcare-IoT framework, allowing real-time data acquisition, processing, and analysis from wearable or portable ECG devices. The IoT integration facilitates continuous monitoring and remote diagnosis, providing timely alerts to healthcare providers and patients. Evaluation on publicly available ECG datasets demonstrates high prediction accuracy, precision, and recall, indicating the system's reliability in detecting early signs of heart disease.