Machine Learning and Ensemble Methods for Cardiovascular Disease Prediction: A Systematic Review of Approaches, Performance Trends, and Research Challenges

Knowledge discovery helps mitigate the shortcomings of classical machine learning, especially those so-called imbalanced, high-dimensional, and noisy data challenges. Adaptive combination of multiple models, voting and other data fusion strategies, and the incorporation of other disparate information fusion methods characterize ensemble learning, which addresses the improvement of a predictive model’s accuracy, stability, and generalization. This paper provides a summary of the important approaches to ensemble learning and their real-world uses, emphasizing challenges and opportunities for future work. This paper also discusses how ensemble learning integrates with emergent areas such as deep learning and reinforcement learning. This paper also describes the most important machine learning methods for predicting heart disease, which include decision trees, support vector machines, artificial neural networks, Naïve Bayes, random forest, and K-nearest neighbors.