Manifold Learning for Analysis of Low-Order Nonlinear Dynamics in High-Dimensional Electrocardiographic Signals

Abstract

The dynamical structure of electrical recordings from the heart or torso surface is a valuable source of information about cardiac physiological behavior. We use an existing data-driven technique called “Laplacian eigenmaps” for manifold identification to reveal electrophysiologically significant changes in the underlying dynamical structure of these signals. Our results suggest that this analysis tool characterizes and differentiates important parameters of cardiac bioelectric activity through their dynamic behavior, suggesting the potential to serve as an effective dynamic constraint in the context of inverse solutions.