A NOVEL APPROACH TO HEART ATTACK PREDICTION IMPROVEMENT VIA EXTREME LEARNING MACHINES CLASSIFIER INTEGRATED WITH DATA RESAMPLING STRATEGY

Abstract

The heart attack is a disorder that is frequently seen in low-income countries and causes the death of many people. Cardiologists benefit from electrocardiography (ECG) tests to determine this condition. Supervised classification algorithms are frequently used and provide very successful results in computer-aided diagnostic systems. In this study, a new approach to predict a heart attack is proposed for classification via extreme learning machines (ELM) integrated with the resampling strategy. This study aims to reveal a new diagnostic system that will increase the success of current studies. The study has three basic steps. In order to determine the features that will ensure the system’s optimized operation, firstly, the ReliefF feature selection method was applied to the data set, and then, the system was modeled by different classifiers via resampling. Besides, the as-proposed approach was applied to the breast cancer data to test the accuracy of the current system. The as-obtained results from both Statlog (heart disease) and the breast cancer data were seemed to be more successful than the studies in the literature. Thus, the as-proposed system reveals a successful and effective approach that can be applied in clinical data sets.