Cardiovascular Disease Prediction Using ML and DL Approaches

Abstract

Healthcare is very important aspects of human life. Cardiovascular disease, also known as the coronary artery disease, is one of the many deadly infections that kill people in India and around the world. Accurate predictions can prevent heart disease, but incorrect predictions can be fatal. Therefore, here this paper describes a method for predicting cardiovascular disease that makes use of Machine Learning (ML) and Deep Learning (DL). In this paper, SMOTE-ENN (Synthetic Minority Oversampling Technique Edited Nearest Neighbor) was used to equalize the distribution of training data. The K-Nearest Neighbor method (KNN), Naive Bayes (NB), Decision Tree (DT), Support Vector Machine (SVM), XGBoost (Extreme Gradient Boosting), Artificial Neutral Network (ANN), and Convolutional Neutral Network (CNN) are among the classifiers used in this paper. From Public Health Dataset required data is collected and focused on recognizing the best approach for predicting the disease in preliminary phase. This experiment end results show that the use of Artificial Neural Networks can be of much useful in prediction with better accuracy (95.7%) than compared to any other ML approaches.