HeartEnsembleNet: An Innovative Hybrid Ensemble Learning Approach for Cardiovascular Risk Prediction

Area of Science:

• Cardiology
• Machine Learning
• Artificial Intelligence

Background:

• Cardiovascular disease (CVD) is a leading global cause of mortality, responsible for 17 million deaths annually.
• Accurate CVD risk prediction is crucial for effective patient management and public health strategies.
• Existing machine learning (ML) methods show promise but require further refinement for enhanced forecasting.

Purpose of the Study:

• To introduce HeartEnsembleNet, a novel hybrid ensemble learning model for cardiovascular disease risk assessment.
• To evaluate the performance of HeartEnsembleNet against established ML classifiers and ensemble techniques.
• To demonstrate the clinical utility of advanced ML in improving CVD risk prediction.

Main Methods:

• Developed HeartEnsembleNet, a hybrid ensemble model integrating multiple ML classifiers.
• Compared HeartEnsembleNet against six classical ML models (SVM, GB, DT, LR, KNN, RF) and other ensemble methods (HRFLM, stacking, voting).
• Utilized a dataset of 70,000 cardiac patients with 12 clinical attributes for model evaluation.

Main Results:

• HeartEnsembleNet achieved a prediction accuracy of 92.95%.
• The model demonstrated a precision rate of 93.08%.
• Performance was evaluated on a large dataset of 70,000 patients.

Conclusions:

• Hybrid ensemble learning, as exemplified by HeartEnsembleNet, significantly enhances cardiovascular disease risk prediction.
• The proposed model offers a promising framework for clinical decision support systems.
• Advanced ML techniques can improve the accuracy and reliability of CVD forecasting.