mlsanityData to 14 Oct 2026

In-Distribution and Out-of-Distribution Self-supervised ECG Representation Learning for Arrhythmia Detection

arXiv 2304.06427 ↗First posted 13 Apr 2023cs.LG cs.AI eess.SPcited by 7

Not on the map. Why?

Abstract (arXiv)

This paper presents a systematic investigation into the effectiveness of Self-Supervised Learning (SSL) methods for Electrocardiogram (ECG) arrhythmia detection. We begin by conducting a novel analysis of the data distributions on three popular ECG-based arrhythmia datasets: PTB-XL, Chapman, and Ribeiro. To the best of our knowledge, our study is the first to quantitatively explore and characterize these distributions in the area. We then perform a comprehensive set of experiments using different augmentations and parameters to evaluate the effectiveness of various SSL methods, namely SimCRL, BYOL, and SwAV, for ECG representation learning, where we observe the best performance achieved by SwAV. Furthermore, our analysis shows that SSL methods achieve highly competitive results to those achieved by supervised state-of-the-art methods. To further assess the performance of these methods on both In-Distribution (ID) and Out-of-Distribution (OOD) ECG data, we conduct cross-dataset training and testing experiments. Our comprehensive experiments show almost identical results when comparing ID and OOD schemes, indicating that SSL techniques can learn highly effective representations that generalize well across different OOD datasets. This finding can have major implications for ECG-based arrhythmia detection. Lastly, to further analyze our results, we perform detailed per-disease studies on the performance of the SSL methods on the three datasets.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 26 of its 46 references that are in the map. First posted on arXiv 13 Apr 2023.

Builds on

26 of 46 references.

References · 26

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  3. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  4. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,898
  5. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  6. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,790
  7. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  8. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,316
  9. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  10. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 453
  11. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 405
  12. 2021Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalizationcited by 220
14 more
  1. 2020CLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and Patientscited by 171
  2. 2019Automatic diagnosis of the 12-lead ECG using a deep neural networkcited by 164
  3. 2020Deep Learning for ECG Analysis: Benchmarks and Insights from PTB-XLcited by 158
  4. 2020Self-supervised ECG Representation Learning for Emotion Recognitioncited by 99
  5. 2021Self-supervised representation learning from 12-lead ECG datacited by 80
  6. 2020Subject-Aware Contrastive Learning for Biosignalscited by 76
  7. 2020A Framework For Contrastive Self-Supervised Learning And Designing A New Approachcited by 52
  8. 2022Lead-agnostic Self-supervised Learning for Local and Global Representations of Electrocardiogramcited by 38
  9. 20213KG: Contrastive Learning of 12-Lead Electrocardiograms using Physiologically-Inspired Augmentationscited by 36
  10. 2021Intra-Inter Subject Self-supervised Learning for Multivariate Cardiac Signalscited by 35
  11. 2019Self-supervised Learning for ECG-based Emotion Recognitioncited by 32
  12. 2022Analysis of Augmentations for Contrastive ECG Representation Learningcited by 12
  13. 2020Detection of Maternal and Fetal Stress from the Electrocardiogram with Self-Supervised Representation Learningcited by 8
  14. 2020CROCS: Clustering and Retrieval of Cardiac Signals Based on Patient Disease Class, Sex, and Agecited by 2

Built on by

Cited by year

Citing papers per year: 2024: 2; 2025: 5.

7 papers.

  1. 2025Generalizable deep learning for photoplethysmography-based blood pressure estimation -- A Benchmarking Studycited by 9
  2. 2025Dynamic Prototype Rehearsal for Continual ECG Arrhythmia Detectioncited by 4
  3. 2024HeartBERT: A Self-Supervised ECG Embedding Model for Efficient and Effective Medical Signal Analysiscited by 3
  4. 2025Uncertainty-Aware Multi-view Arrhythmia Classification from ECGcited by 1
  5. 2024NapTune: Efficient Model Tuning for Mood Classification using Previous Night's Sleep Measures along with Wearable Time-seriescited by 0
  6. 2025Enhancing ECG Classification Robustness with Lightweight Unsupervised Anomaly Detection Filterscited by 0
  7. 2025Investigating ECG Diagnosis with Ambiguous Labels using Partial Label Learningcited by 0