The paper presents the application of fuzzy self-organizing neural network and higher order statistics for ECG beat classification. The new classification algorithm of the ECG beats, applying the higher order statistics and fuzzy self-organizing neural classifier has been proposed in the paper. The cumulants of the second, third and fourth orders have been used for the feature selection. The GK algorithm for self-organization of the neural network has been applied. The results of experiments have confirmed good efficiency of the proposed solution. The investigations show that the method may find practical application in the recognition of beats. The main features of the proposed method are the good efficiency and real time performance.