A method based on wavelet analysis for the detection of ventricular late potentials in ECG signals

After recovery from acute myocardial infarction (MI), a significant number of patients remain at risk of sudden death, which is attributed to ventricular tachycardia (VT). Ventricular Late Potentials (VLPs) are associated with VT. VLPs are low amplitude high frequency signals that appear at the end of the QRS complex of an ECG recording. In this work, DWT analysis is performed to identify VLPs in ECG signals and this analysis is used to classify patients with and without VLPs in their ECGs. Discrete Wavelet Transforms (DWT) was carried out for a total of (39) different ECG records that included MI patients with and without VT. The parameters studied in this work included the standard parameters, which are the duration of the QRS the root mean square of the signal in the last 40 ms and the duration of the low amplitude signal. In addition to the standard parameters, two DWT generated parameters were added which are power of the vector magnitude and norm of a chosen level. Introducing new WT parameters improves performance in comparison with the use of standard method parameters alone