• Home
  • Search
  • Toward robust automated cardiovascular arrhythmia detection using self-supervised learning and 1-dimensional vision transformers.
  • https://doi.org/10.1038/s41598-026-41549-5Copy DOI Icon

Toward robust automated cardiovascular arrhythmia detection using self-supervised learning and 1-dimensional vision transformers.

Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

Cardiovascular diseases are the leading cause of death worldwide. With electrocardiogram (ECG) machines becoming more accessible, passive monitoring for arrhythmia detection is now possible. This work highlights the importance of self-supervised learning in detecting arrhythmias by leveraging large-scale unlabelled ECG data to improve performance and reduce overfitting to class imbalance and noise. We propose Masked Patch Modelling (MPM) and use 8.2 million unlabelled ECGs for self-supervised pre-training, introducing PatchECG, a 1D Transformer model that can be fine-tuned for various ECG tasks. PatchECG achieves state-of-the-art results on standard datasets, including PTB-XL multi-label classification, and sets new benchmarks on the largest and highest-quality multi-label dataset to date. Compared to existing methods, PatchECG is five times more computationally efficient while increasing model capacity by a factor of 14. We also compare the 1D PatchECG model to a state-of-the-art 2D vision Transformer, HeartBEiT, and observe significantly higher performance. Finally, ablation studies reveal a 2% performance improvement in handling class imbalance, label noise, and over-parameterization. These findings demonstrate the potential of self-supervised learning in advancing automated arrhythmia detection.

Similar Papers
  • Research Article
  • Citations11

Gradient-aware learning for joint biases: Label noise and class imbalance

  • Dec 18, 2023
  • Neural Networks
  • Shichuan Zhang +4
  • Research Article

Hybrid Approach-RSMOTE for Handling Class Imbalance with Label Noise

  • Oct 13, 2022
  • Jurnal Ilmiah Teknik Elektro Komputer dan Informatika
  • Hartono Hartono +1
  • Research Article
  • Citations20

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

  • Feb 01, 2024
  • IEEE journal of biomedical and health informatics
  • Sahar Soltanieh +2
  • Conference Article
  • Citations11

Investigation of Data Encryption Algorithm for Secured Transmission of Electrocardiograph (ECG) Signal

  • Dec 01, 2018
  • Muhammad Umair Shaikh +2
  • Research Article
  • Citations61

AdaSampling for Positive-Unlabeled and Label Noise Learning With Bioinformatics Applications.

  • Apr 02, 2018
  • IEEE Transactions on Cybernetics
  • Pengyi Yang +5
  • Conference Article

IoT-Enabled Real-Time Arrhythmia Detection Using Modified Transformer Decoder and Conditional ECG-GAN

  • Dec 17, 2025
  • Muhammad Naufal Thariq Ardian +1
  • Conference Article

An Improvement on Class-Imbalanced Cardiovascular Disease Classification using Spectrogram-based 12-Lead ECG

  • Jul 24, 2025
  • Phuong Linh Nguyen +3
  • Research Article

Deep learning analysis of ECGs detects Cardiovascular-Kidney-Metabolic syndrome burden in people with diabetes: a report from the Silesia Diabetes-Heart Project.

  • Jun 29, 2026
  • Cardiovascular diabetology
  • Oliwia Janota-Sosińska +13
  • Research Article
  • Citations13

Foundation models for electrocardiogram interpretation: clinical implications

  • Jan 22, 2026
  • European Heart Journal
  • Alexis Nolin-Lapalme +32
  • Conference Article
  • Citations51

FedNoRo: Towards Noise-Robust Federated Learning by Addressing Class Imbalance and Label Noise Heterogeneity

  • Aug 01, 2023
  • Nannan Wu +4
  • Research Article
  • Citations23

GAN-SkipNet: A Solution for Data Imbalance in Cardiac Arrhythmia Detection Using Electrocardiogram Signals from a Benchmark Dataset

  • Aug 29, 2024
  • Mathematics
  • Hari Mohan Rai +2
  • Research Article
  • Citations33

A Survey on Classifying Big Data with Label Noise

  • Nov 23, 2022
  • Journal of Data and Information Quality
  • Justin M Johnson +1
  • Preprint Article

Pluto: A global volcanic activity early warning system powered by large scale self-supervised deep learning on InSAR data

  • May 15, 2023
  • Nikolaos Ioannis Bountos +4
  • Research Article

Self-supervised learning can tackle life-threatening arrhythmia detection data challenges

  • Jan 12, 2026
  • European Heart Journal. Digital Health
  • G Monachino +4
  • Book Chapter
  • Citations7

Bi-Level Selection via Meta Gradient for Graph-Based Fraud Detection

  • Jan 01, 2022
  • Linfeng Dong +6
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.