Prediction of Heart Disease using Data Mining Classifiers

Fist size muscle acquires the name of an important part of the human body by pumping blood to all the parts of the body. Cardiovascular disease is the major cause of death in the nation. Though the data available in the health field is vast, still there is a need to develop decision supporting system to maintain, analyze, and knowledge evaluation. One such technique that can be used to address such a problem is data mining. Data mining techniques can help to classify the whether a patient having heart disease or not. This paper explores the different classification techniques for heart disease prediction. Logistic Regression, Support Vector Machine, Naïve Bayes, Nearest Neighbor, and Decision Tree methods are applied. To assess performance of the classifiers various measures are taken includes accuracy, recall, precision and F1-score. Methods: An abundant data generated by the healthcare industry leads to exploring the required information to make a decision-making system using data mining techniques. Classification methods such as SVM, Naive Bayes, KNN, Logistic Regression, and Decision Tree are applied to predict heart disease with a different dataset. Results: Five classification techniques are applied to predict the two different heart disease datasets. By inference, the different classifiers work differently on selected attributes of datasets in terms of accuracy, precision, recall, and F1-score measurements. Conclusion: Our research focuses on comparing the results of classification techniques applied to two different heart disease datasets. Various performance metrics were used to compare and contrast the two datasets of heart disease.