Classification of Single-lead Electrocardiograms: TDA Informed Machine Learning

TL;DR

This paper introduces a novel approach using topological data analysis to classify single-lead ECGs, leveraging delay embeddings and persistent signatures to improve accuracy over traditional feature extraction methods.

Contribution

It demonstrates how topological features can be effectively used in machine learning models for ECG classification, providing an alternative to expert-informed features.

Findings

Topological features improve classification accuracy.

Method benchmarks well against state-of-the-art models.

Delay embeddings effectively transform ECG signals into topological signatures.

Abstract

Atrial Fibrillation is a heart condition characterized by erratic heart rhythms caused by chaotic propagation of electrical impulses in the atria, leading to numerous health complications. State-of-the-art models employ complex algorithms that extract expert-informed features to improve diagnosis. In this note, we demonstrate how topological features can be used to help accurately classify single lead electrocardiograms. Via delay embeddings, we map electrocardiograms onto high-dimensional point-clouds that convert periodic signals to algebraically computable topological signatures. We derive features from persistent signatures, input them to a simple machine learning algorithm, and benchmark its performance against winning entries in the 2017 Physionet Computing in Cardiology Challenge.