DataMining Clustering Techniques in the Prediction of Heart Disease using Attribute Selection Method

Abstract

Heart disease is the leading cause of death in the world over the past 10 years. In this paper proposes the performance of clustering algorithm using heart disease data. We are evaluating the performance of clustering algorithms of EM, Cobweb, Farthest First, Make Density Based Clusters, Simple K-Means algorithms. The performance of clusters will be calculated using the mode of classes to clusters evaluation. The selected attributes after the Common Features Subset Evaluator (CFs) and Best-First Search (BFs) are cp, restecg, thalach, exang, oldpeak, ca, thal, and num. In the final result, Make Density Based Clusters shows the high performance algorithms for heart disease data after applying the Attribute selection Method and their Prediction Accuracy is 85.80%.