Exploring Feature Selection and Classification Algorithms For Cardiac Arrhythmia Disease Prediction

Abstract

Cardiac Arrhythmia is the disease in which heartbeats abnormally due to which death of a person may occur if not diagnosed on time. Timely and accurate detection of cardiac arrhythmia can save the life of the patient. In this study fourteen classification algorithms and six feature selection algorithms are explored to find the best combination which can accurately detect cardiac arrhythmia. On the features selected through feature selection techniques fourteen classification algorithms are applied to classify cardiac arrhythmia. The random forest algorithm for feature selection and random forest classification algorithm found best among all the models applied with an accuracy of 86.57%, precision 79.12%, recall 79.12%, and f1-score 79.12%.