Wigner-Ville analysis and classification of electrocardiograms during thrombolysis

摘要: Non-stationary analysis of electrocardiograms (ECGs) using Wigner-Ville distribution is presented. Analysis was performed on subjects with acute myocardial infarction who had undergone thrombolysis, in Holter recordings lead V1. The distinction between successfully and non-successfully thrombolysed patients evaluated, based time-frequency features the transformed ECGs at sixth hour after lysis. Characteristic parameters were extracted from areas, linear discriminant these parameters, leading to a prediction index distinguish two classes. Thirteen found statistically significant by t-test used for classification modelling. Out features, four corresponded frequencies lower than 25 Hz higher 50 for, roughly, QRS complex, five all frequency bands of, ST area, last T-wave. feature-vector modelling iteratively generated, iterative 18 significant. method resulted better that standard statistical procedure (3.8% error against 18.1% classic method). evolution time first 12 h different groups. Specifically, successful thrombolysis group, oscillations variation more obvious, indicating possible difference dynamics cardiac system.