AI Based Cardiovascular Disease Prediction using Ensemble Learning

Cardiovascular diseases are the heart-related illnesses. If not treated, that often turns into serious and complex conditions that often result in the death of an individual. It is one of the top causes of death globally. The heart pumps blood throughout the body. This research focuses on predictive analysis and the determination of the severity of heart disease using machine learning algorithms. The datasets are selected then feature selection is the major step of preprocessing, which involves mechanisms to use impactful columns of the data set for experiments. Feature selection techniques include technical methods like the Pearson Correlation Coefficient, Relief, Minimum Redundancy Maximum Relevance, and Least Absolute Shrinkage and Selection Operator. Any of them generate results based on high relevancy and information gain. Choosing relevant features,due to the existence of labeled data, the classification technique is ideal. The supervised learning algorithms are applicable for this prospective. There also exists a proposed ensemble method algorithm. This approach results in an accuracy of 94.74%. The research is significant since it is helpful to determine early heart disease detection, which is an important aspect of early disease detection, which may save lives by early diagnosis in the future.