AUTOMATED NEURAL-NETWORK DETECTION OF WAVELET PREPROCESSED ELECTROCARDIOGRAM LATE POTENTIALS

The aim of the study is 50 investigate the potential of a feedforward neural network for detecting wavelet preprocessed late potentials. The terminal parts of a simulated QRS complex are processed with a contin uous wavelet transform, which leads to a time-frequency represenation of the QRS complex. Then, diagnostic feature vectors are obtained by s ubdividing the representations into several regions and by processing the sum of the decomposition coefficients belonging to each region. Th e neural network is trained with these feature vectors. Simulated ECGs with varying signal-to-noise ratios are used to train and test the cl assifier. Results show that correct classification ranges from 79% (hi gh-level noise) to 99% (no noise). The study shows the potential of ne ural networks for the classification of late potentials that have been preprocessed by a wavelet transform. However, clinical use of this me thod still requires further investigation.