Automatic Classification Normal ECGs Based on Normal PathECG and WaveECG Features

Abstract

Classification of the ECG waveform to normal or abnormal is important to the non-experienced ECG-reader. We propose an algorithm to use solely the waveform of a single ECG beat to classify the ECG as normal or abnormal. In this study we used a subset of the normal classified ECGs from the PTB-XL database to create a normal distribution of the ECG waveform (WaveECG) and its PathECG positions. The aim of this study was to use these distributions to classify all human validated ECGs from the PTB-XL database as either normal or abnormal. Our initial results show an accuracy of 87% to determine whether an ECG is normal or abnormal, irrespective of the gender group used. Using solely the ECG waveform can detect the vast majority of abnormal ECGs, including conduction disorders, ischemia, and arrhythmias.