Automatic Recognition of Ventricular Abnormal Potentials in Intracardiac Electrograms

Ventricular abnormal potentials are low-amplitude electrical signals that appear in intracardiac electrograms during a QRS or with an unpredictable delay with respect to it. Their spatial localization can be exploited by cardiologists for the identification of the ablation targets in substrate-guided mapping and ablation procedures. In this work, an automatic approach for a reliable detection of such potentials in intracardiac electrograms is proposed. To this aim, 86 intracardiac electrograms from five patients with post-ischemic ventricular tachycardia, acquired by the CARTO3 System, were retrospectively annotated by an expert cardiologist, to be used for a supervised classifier training and test. The automatic detection was based on a non-linear denoising followed by a time-scale decomposition based on the continuous wavelet transform. Then, different morphological features were extracted from both the time-scale domain and the time domain, and used to feed a support vector machine trained to discriminate between physiological and abnormal potentials. The recognition accuracy exceeded 93%, paving the way to further developments and more extensive studies.