A Hybrid Predictive Ensemble of Machine Learning and Deep Neural Networks for Early Cardiovascular Disease Risk Assessment

Researchers have proposed an intelligent prediction framework that integrates machine learning and deep neural networks, aimed at optimizing the detection and prognosis assessment of early-stage cardiovascular diseases. The system integrates real-time physiological data from IoT devices such as electrocardiogram sensors, heart rate monitors, and blood pressure trackers. Preprocessing techniques such as noise removal, normalization, and missing value filling are used to ensure data quality. The architecture uses classifiers such as support vector machines, random forests, and XGBoost to build an integrated model, which is deployed on cloud infrastructure to support scalability and real-time processing. Experiments show that this framework performs better than traditional methods on real-world cardiovascular disease datasets, significantly improving the accuracy of early risk screening, reducing the rate of false positives, and enhancing the consistency of diagnostic results, providing efficient support for clinical decision-making.