Exploring Complexity Changes in Diseased ECG Signals for Enhanced Classification

TL;DR

This study investigates how ECG signal complexity varies with cardiac disease using nonlinear analysis, revealing significant differences and improving machine learning classification accuracy.

Contribution

It introduces the use of nonlinear and cross-channel complexity measures from ECGs to enhance disease classification accuracy.

Findings

Significant differences in complexity measures between healthy and diseased ECGs.

Inclusion of nonlinear measures improves classification AUC from 0.86 to 0.87.

Cross-channel metrics further increase AUC to 0.90.

Abstract

The complex dynamics of the heart are reflected in its electrical activity, captured through electrocardiograms (ECGs). In this study we use nonlinear time series analysis to understand how ECG complexity varies with cardiac pathology. Using the large PTB-XL dataset, we extracted nonlinear measures from lead II ECGs, and cross-channel metrics (leads II, V2, AVL) using Spearman correlations and mutual information. Significant differences between diseased and healthy individuals were found in almost all measures between healthy and diseased classes, and between 5 diagnostic superclasses ($p<.001$). Moreover, incorporating these complexity quantifiers into machine learning models substantially improved classification accuracy measured using area under the ROC curve (AUC) from 0.86 (baseline) to 0.87 (nonlinear measures) and 0.90 (including cross-time series metrics).