Beat detection and classification of ECG using self organizing maps

A procedure for beat detection and classification was developed using ECG recordings. This procedure can be used for beat detection with one or two leads, and then a portion of each detected beat is used for classifying. This task is performed by a neural network. In the authors' work the morphology of the QRS portion of the ECG feeds a self organizing map (SOM). The SOM was previously trained with different QRS complexes such as normal and ectopic beat morphologies. The beat classification is very important in heart rate variability (HRV) analysis, because one must use only the normal beats and reject the ectopic ones for the construction of the RR intervals beat series.