Authors : R. Suganya, S. Rajaram, A. Sheik Abdullah and V. Rajendran
Abstract: This study introduces a new approach for prediction problem with the objective of attaining maximum classification accuracy with smallest number of features selected. Cardiac diseases are very common and one of the main reasons of death. According to a recent literature study by the Indian Council of Medical Research, about 25% of cardiac problems are between age group of 25-69 years. Hence, the main objective of this work is to predict the possibility of heart diseases at its early stages with less number of attributes. Our approach integrates anthropometric data and physiological data of cardiac diseases by proposing Novel Feature Selection method for prediction of heart diseases. The dataset used in this work is collected from Cleveland heart disease database. The results show the proposed approach leads to a superior feature selection process in terms of sinking the number of variable required and increased in classification accuracy for better prediction.
R. Suganya, S. Rajaram, A. Sheik Abdullah and V. Rajendran, 2016. A Novel Feature Selection Method for Predicting Heart Diseases with Data Mining Techniques. Asian Journal of Information Technology, 15: 1314-1321.