IMPROVING CORONARY HEART DISEASE PREDICTION BY OUTLIER ELIMINATION

Nowadays, heart disease is the major cause of deaths globally. According to a survey conducted by World Health Organization, almost 18 million people die diseases (or cardiovascular diseases) every day. So, there should be system for early detection and prevention disease. Detection mostly depends on huge pathological clinical data that quite complex. researchers other medical professionals are showing keen interest in accurate prediction Heart general term large number conditions related one them coronary (CHD). Coronary caused amassing plaque artery walls. In this paper, various machine learning base ensemble classifiers have been applied dataset efficient Various employed include k-nearest neighbor, multilayer perceptron, multinomial naïve bayes, logistic regression, decision tree, random forest support vector classifiers. Ensemble used majority voting, weighted average, bagging boosting The study obtained from Framingham Study which long-term, ongoing city Massachusetts, USA. To evaluate performance classifiers, evaluation metrics including accuracy, precision, recall f1 score used. our results, best accuracy was achieved forest, average but highest among these using classifier.