Enhancing Cardiovascular Diseases Classification using CNN Algorithm.

Abstract

In this research, the primary focus is the detection of cardiovascular diseases using machine learning algorithms. The problem addressed is the critical need for accurate and timely diagnosis of cardiovascular conditions, a leading cause of global morbidity and mortality. The research objectives encompass evaluating the performance Of several machine learning algorithms, which encompass Convolutional Neural Network (CNN), Support Vector Machine (SVM), Decision Tree, K-Nearest Neighbors (KNN), Gaussian Naive Bayes (GNB), and Gradient Boosting, in classifying patients into 'yes' or 'no' categories for cardiovascular diseases based on a comprehensive dataset. The methodology involves data preprocessing, feature selection, and model training and evaluation. The research results reveal that CNN and SVM exhibit strong and balanced performance, while Decision Tree showcases high sensitivity but potential overfitting. These findings provide valuable insights into algorithm selection and model refinement for cardiovascular disease detection, laying the foundation for future research in enhancing diagnostic accuracy, clinical applicability, and healthcare outcomes..