An efficient method for ECG beat classification and correction of ectopic beats.

The analysis of the surface Electrocardiogram (ECG) is the most extended non-invasive technique in cardiological diagnosis. The ectopic beats are heart beats remarkably different to the normal beat morphology that provoke serious disturbances in electrocardiographic analysis. These beats are very common in atrial fibrillation (AF), causing important residua when ventricular activity has to be removed for atrial activity (AA) analysis. These beats may occur in both normal subjects and patients with heart disease, and their presence represents an important source of error which must be handled before any other analysis. In this work, a method is proposed to cancel out ectopics by classification between normal and abnormal beats. The systems is based on Radial Basis Function Neural Network (RBFNN). This new approach is compared to state-of-the-art techniques for the ectopic classification and cancellation in the MIT database. The results clearly demonstrated the improved ECG beats classification accuracy compared with other alternatives and a very accurate reduction of ectopic beats together with low distortion of the QRST complex. [ABSTRACT FROM AUTHOR]