Investigating the Prediction of Cardiovascular Diseases using Different Machine Learning Methods

This study will examine the use of machine learning algorithms to predict cardiovascular disorders using a dataset of 100 patient records from many databases related to heart disease. The dataset, which was divided into training (80 records) and testing (20 records), contained characteristics including age, blood pressure, and cholesterol levels. Feature selection, outlier management, and missing value handling were all part of data preprocessing Machine learning models including Logistic Regression, Naive Bayes, Random Forest, SVM, and Gradient Boosting were assessed for specificity, sensitivity, and accuracy. After that, Random Forest and the other models lagged behind Gradient Boosting, which outperformed all of them by sustaining an accuracy of up to 92.5%. Based on the results, ensemble methods—more especially, the usage of Random Forest and Gradient Boosting—are primarily recommended.