Manifold learning for analysis of low-order nonlinear dynamics in high-dimensional electrocardiographic signals

The dynamical structure of electrical recordings from the heart or torso surface is a valuable source of information about cardiac physiological behavior. In this paper, we use an existing data-driven technique for manifold identification to reveal electrophysiologically significant changes in the u...

Full description

Saved in:
Bibliographic Details
Published in:2012 9th IEEE International Symposium on Biomedical Imaging (ISBI) 2012-07, Vol.2012, p.844-847
Main Authors: Erem, B., Stovicek, P., Brooks, D. H.
Format: Article
Language:English
Subjects:
Bioelectric Signal Processing
Cardiac Dynamics
Differential Geometry
Electric potential
Heart
Laplace equations
Manifold Learning
Manifolds
Surface waves
Torso
Trajectory
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The dynamical structure of electrical recordings from the heart or torso surface is a valuable source of information about cardiac physiological behavior. In this paper, we use an existing data-driven technique 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.
ISSN:1945-7928
1945-8452
DOI:10.1109/ISBI.2012.6235680