Multiscale Adaptive Basis Function Modeling of Spatiotemporal Vectorcardiogram Signals

Mathematical modeling of cardiac electrical signals facilitates the simulation of realistic cardiac electrical behaviors, the evaluation of algorithms, and the characterization of underlying space-time patterns. However, there are practical issues pertinent to model efficacy, robustness, and generality. This paper presents a multiscale adaptive basis function modeling approach to characterize not only temporal but also spatial behaviors of vectorcardiogram (VCG) signals. Model parameters are adaptively estimated by the “best matching” projections of VCG characteristic waves onto a dictionary of nonlinear basis functions. The model performance is experimentally evaluated with respect to the number of basis functions, different types of basis function (i.e., Gaussian, Mexican hat, customized wavelet, and Hermitian wavelets), and various cardiac conditions, including 80 healthy controls and different myocardial infarctions (i.e., 89 inferior, 77 anterior-septal, 56 inferior-lateral, 47 anterior, and 43 anterior-lateral). Multiway analysis of variance shows that the basis function and the model complexity have significant effects on model performances while cardiac conditions are not significant. The customized wavelet is found to be an optimal basis function for the modeling of space-time VCG signals. The comparison of QT intervals shows small relative errors (<5%) between model representations and real-world VCG signals when the model complexity is greater than 10. The proposed model shows great potentials to model space-time cardiac pathological behaviors and can lead to potential benefits in feature extraction, data compression, algorithm evaluation, and disease prognostics.