Electrocardiogram arrhythmia detection with novel signal processing and persistent homology-derived predictors

Tracking #: 790-1770


Hunter DlugasORCID logo https://orcid.org/0000-0002-6819-0045

Responsible editor: 

Karin Verspoor

Submission Type: 

Research Paper


Many approaches to computer-aided electrocardiogram (ECG) arrhythmia detection have been performed, several of which combine persistent homology and machine learning. We present a novel ECG signal processing pipeline and method of constructing predictor variables for use in statistical models. Specifically, we introduce an isoelectric baseline to yield non-trivial topological features corresponding to the P, Q, S, and T-waves (if they exist) and utilize the N-most persistent 1-dimensional homological features and their corresponding area-minimal cycle representatives to construct predictor variables derived from the persistent homology of the ECG signal for some choice of N. The binary classification of (1) Atrial Fibrillation vs. Non-Atrial Fibrillation, (2) Arrhythmia vs. Normal Sinus Rhythm, and (3) Arrhythmias with Morphological Changes vs. Sinus Rhythm with Bradycardia and Tachycardia Treated as Non-Arrhythmia was performed using Logistic Regression, Linear Discriminant Analysis, Quadratic Discriminant Analysis, Naive Bayes, Random Forest, Gradient Boosted Decision Tree, K-Nearest Neighbors, and Support Vector Machine with a linear, radial, and polynomial kernel Models with stratified 5-fold cross validation. The Gradient Boosted Decision Tree Model attained the best results with a mean F1-score and mean Accuracy of (0.9677,0.946), (0.839,0.946), and (0.943,0.921) across the five folds for binary classifications of (1), (2), and (3), respectively.



  • Reviewed

Data repository URLs: 

Date of Submission: 

Friday, December 29, 2023

Date of Decision: 

Saturday, March 23, 2024

Nanopublication URLs:



Solicited Reviews:

1 Comment

meta-review by editor

The reviewers are in agreement that the work represents a technically sound contribution whose novelty lies in the the introduction of topological features in representing ECG signals for use in classification of ECG rhythms. However they also identify a few areas that require improvement for publication, specifically:

  • improved review of the related literature, with comparison to the proposed methods, as well as discussion of the implications of that literature for the author's work
  • more detailed analysis of the contributions of specific features
  • improved presentation of results in figures, with more detailed analysis/interpretation of those results

Karin Verspoor (https://orcid.org/0000-0002-8661-1544)