Automatic discrimination of arrhythmia waveforms using fuzzy logic

摘要

A method was proposed for discrimination of ventricular arrhythmias using fuzzy logic. The classifier uses four features of ECG waveforms; amplitude variation ratio, interval variation ratio, peak sharpness, QRS complex width, and assigns each waveform a number of 0-100. The performance of the algorithm was evaluated on the surface and intracardiac electrocardiograms of ventricular tachycardia (VT), ventricular fibrillation (VF) and normal sinus rhythm (NSR) in mongrel dogs. NSRs were evaluated 90-100 while VFs less than 10. VTs were assigned the numbers of 30-75. An automatic detection and defibrillation experiment was performed with this algorithm.