Prediction of atrial fibrillation based on nonlinear modeling of heart rate variability signal and SVM classifier

Cardiac arrhythmia is one of the major causes of death worldwide. Atrial fibrillation (AF) is considered as the most prevalent sustained cardiac arrhythmia. It increases the risk of cardiac stroke and heart failure. This study aims to present an automated technique for AF detection by analyzing the ECG signal so that individual heart condition can be monitored accurately and an alarm system can be simulated if any serious cardiac abnormality occurs. The heart rate variability (HRV) signal reflects the fluctuation of heart in different time intervals. The proposed algorithm includes nonlinear methods for characterizing the dynamics of HRV signal to find diagnosis pattern for AF detection. The diagnostically relevant nonlinear parameters are extracted from HRV signal. The extracted features are subjected to decision tree and support vector machine (SVM) classifier to discriminate AF from normal heart condition. The experimental result is evaluated on 25 ECG data set of AF and 54 ECG data sets of normal subjects taken from Physionet database to illustrate the diagnostic ability of the classifiers. The tenfold cross-validation method is also applied for performance evaluation. The proposed algorithm has achieved an average accuracy of 99.11%, sensitivity, specificity, and F-score values of 98.92%, 99.25%, and 99.08%, respectively, using SVM classifier which is better than the result obtained from decision tree classifier having average accuracy of 96.41% and F -score of 95.71%. The proposed algorithm provides great potential for AF diagnosis with high accuracy. This work yields superior performance based on the comparative study with the existing scientific approaches to categorize AF from normal ones.