An effective PSR-based arrhythmia classifier using self-similarity analysis

Among different cardiac arrhythmias, Ventricular Arrhythmias (VA) are fatal and life-threatening. Therefore, the detection classification of VA is crucial task for cardiologists. However, in some cases, ECG morphologies two kinds - Tachycardia (VT) Fibrillation (VF) similar difficult to distinguish by human eyes. In this study, we present a low computational complexity arrhythmia classifier with high accuracy based on Phase Space Reconstruction (PSR). It used classify normal electrocardiogram (ECG), atrial fibrillation (AF), VT, VF VT followed VF. The Creighton University Tachyarrhythmia Database (CUDB), Physikalisch-Technische Bundesanstalt Diagnostic (PTBDB), MIT-BIH Atrial (MIT-BIH AFDB) from PhysioNet databank Hospital Southampton database (UHSDB) evaluation comparison proposed algorithm. Two PSR diagrams were plotted window length 5 s time delays PSR-based features extracted them using box-counting technique. This process was applied 122 records more than 5500 windows signals. results show an average sensitivity 98.73%, specificity 99.71% 99.56%. our method one processing 1.9 therefore has potential real-time applications.