Improving Cardiovascular Disease Prediction: Machine Learning and Cross-Fold Validation

Cardiovascular Disease (CVD) primarily refers to conditions characterized by narrowed or obstructed blood vessels, which can lead to a heart attack, chest pain (angina), or stroke. The machine learning classifier anticipates the condition based on the symptoms experienced by the patient. The purpose of this paper is to enhance the prediction of Cardiovascular Disease (CVD) by employing cross-fold validation within the framework of machine learning. Various Machine Learning classifiers such as Naïve Bayes, Support Vector Machine, K Nearest Neighbor, Gradient Boosting, and Adaboost were employed to forecast Cardiovascular Disease (CVD) based on metrics like Accuracy, F1 score, Precision, and Recall. The most effective classifier was determined by evaluating the accuracy of each one. The primary focus of this study is to assess the performance metrics across different k-fold cross-validation values. Notably, the Gradient Boosting classifier demonstrated the highest accuracy of 96% with k set to 10 in this analysis.