Arrhytmia classification with som

The electrocardiogram carries a lot of clinical information for a cardiologist,especially the width or duration of the waves in the ECG are widely used to defineconduction in the heart and to stratify patients at risk of cardiac arrhythmia. Themanual annotation to the waves is a strenuous task; as a result several automatedmethods have been developed to relieve the cardiologist.This study presents an Artificial Neural Network using Self-Organizing Maparchitecture, the evaluation of its performance in the classification of QRS waves ofthe electrocardiogram (ECG) from patients with cardiac arrhythmias and theclassification of data from MIT/BIH Arrhythmia Database.