Characterization of ECG patterns with the Synchrosqueezing Transform

The processing of ECG signal provides a wealth of information on cardiac function and overall cardiovascular health. While multi-lead ECG recordings are often necessary for a proper assessment of cardiac rhythms, a wide range of small non-obtrusive ambulatory monitoring devices are now available, that provide one or two ECG leads and complicate ECG-derived diagnostics information. In this manuscript, we characterized the heart rate signal as an adaptive non-harmonic model and used the newly developed synchrosqueezing transform (SST) to enhance the R-peak detection, quality assessment and general understanding of the ECG patterns. We show how the proposed model can be used to enhance heart beat detection and classification. In particular, using the MIT-BIH arrhythmia database and the Association for the Advancement of Medical Instrumentation (AAMI) beat classes, we trained a support vector machine (SVM) classifier on a portion of the annotated beat database using the SST-derived instantaneous phase, the R-peak amplitudes and R-peak to R-peak interval durations, based one single ECG lead. We obtained an overall accuracy of 91.02% with a better performance on the normal and ventricular ectopic beat classes than on the supraventricular ectopic and fusion beat classes.