Author(s)

Wenbo Sun

Corresponding Author

Wenbo Sun

ABSTRACT

Cardiovascular disease is one of the most threatening diseases to human health today. Exploring the performance of different models in predicting cardiovascular diseases will help medical practitioners to make more accurate medical diagnoses using non-invasive means to save lives. In this paper, a comparative analysis of different classification prediction models was applied to predicting heart disease cases using heart disease data from the UCI machine learning Repository. This data source contains 14 dimensions of data for 303 patients. The classifiers applied in this study were decision trees, random forests, support vector machines (SVM) and logistic regression. To examine the performance of each classifier, criteria such as accuracy, sensitivity, and specificity were used, and a 10-fold cross-validation method was used to measure the unbiased estimates of these prediction models. According to our results, SVM can make predictive judgments for suspected cardiovascular disease cases to the maximum extent possible.

KEYWORDS

Heart disease, Random Forest, ANOVA Analysis, Classification