Learning ECG Representations via Poly-Window Contrastive Learning

• URL: http://arxiv.org/abs/2508.15225v1
• Date: Thu, 21 Aug 2025 04:26:51 GMT
• Title: Learning ECG Representations via Poly-Window Contrastive Learning
• Authors: Yi Yuan, Joseph Van Duyn, Runze Yan, Zhuoyi Huang, Sulaiman Vesal, Sergey Plis, Xiao Hu, Gloria Hyunjung Kwak, Ran Xiao, Alex Fedorov,
• Abstract summary: We present a poly-window contrastive learning framework for ECG analysis.<n>Inspired by the principle of slow feature analysis, our approach explicitly encourages the model to learn temporally invariant and physiologically meaningful features.<n>Our results demonstrate that poly-window contrastive learning consistently outperforms conventional two-view methods in multi-label superclass classification.
• Score: 5.200583783760777
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Electrocardiogram (ECG) analysis is foundational for cardiovascular disease diagnosis, yet the performance of deep learning models is often constrained by limited access to annotated data. Self-supervised contrastive learning has emerged as a powerful approach for learning robust ECG representations from unlabeled signals. However, most existing methods generate only pairwise augmented views and fail to leverage the rich temporal structure of ECG recordings. In this work, we present a poly-window contrastive learning framework. We extract multiple temporal windows from each ECG instance to construct positive pairs and maximize their agreement via statistics. Inspired by the principle of slow feature analysis, our approach explicitly encourages the model to learn temporally invariant and physiologically meaningful features that persist across time. We validate our approach through extensive experiments and ablation studies on the PTB-XL dataset. Our results demonstrate that poly-window contrastive learning consistently outperforms conventional two-view methods in multi-label superclass classification, achieving higher AUROC (0.891 vs. 0.888) and F1 scores (0.680 vs. 0.679) while requiring up to four times fewer pre-training epochs (32 vs. 128) and 14.8% in total wall clock pre-training time reduction. Despite processing multiple windows per sample, we achieve a significant reduction in the number of training epochs and total computation time, making our method practical for training foundational models. Through extensive ablations, we identify optimal design choices and demonstrate robustness across various hyperparameters. These findings establish poly-window contrastive learning as a highly efficient and scalable paradigm for automated ECG analysis and provide a promising general framework for self-supervised representation learning in biomedical time-series data.

Related papers

• Digital FAST: An AI-Driven Multimodal Framework for Rapid and Early Stroke Screening [0.7136933021609076]
  This study presents a fast, non-invasive multimodal deep learning framework for automatic binary stroke screening based on data collected during the F.A.S.T. assessment.<n>The proposed approach integrates complementary information from facial expressions, speech signals, and upper-body movements to enhance diagnostic robustness.
  arXiv  Detail & Related papers  (2026-01-17T03:35:39Z)
• EnECG: Efficient Ensemble Learning for Electrocardiogram Multi-task Foundation Model [46.84040404474695]
  EnECG is an ensemble-based framework that integrates multiple specialized foundation models, each excelling in different aspects of ECG interpretation.<n>We show that EnECG can help reduce computational and memory costs while maintaining the strong representational power of foundation models.<n>This framework not only enhances feature extraction and predictive performance but also ensures practical efficiency for real-world clinical applications.
  arXiv  Detail & Related papers  (2025-11-28T07:22:33Z)
• An Electrocardiogram Multi-task Benchmark with Comprehensive Evaluations and Insightful Findings [21.836042030973797]
  Analyzing the ECG typically requires domain expertise, which is a roadblock to applying artificial intelligence for healthcare.<n>We evaluate language/general time-series/ECG foundation models in comparison with time-series deep learning models.<n>In-depth analyses and insights are provided along with comprehensive experimental results.
  arXiv  Detail & Related papers  (2025-11-28T06:47:21Z)
• Segmentation over Complexity: Evaluating Ensemble and Hybrid Approaches for Anomaly Detection in Industrial Time Series [36.94429692322632]
  We evaluate the impact of change point-derived statistical features, clustering-based substructure representations, and hybrid learning strategies on detection performance.<n>The ensemble achieved an AUC-ROC of 0.976, F1-score of 0.41, and 100% early detection within the defined time window.
  arXiv  Detail & Related papers  (2025-10-30T05:39:44Z)
• ECGXtract: Deep Learning-based ECG Feature Extraction for Automated CVD Diagnosis [0.0]
  This paper presents ECGXtract, a deep learning-based approach for interpretable ECG feature extraction.<n>We develop convolutional neural network models capable of extracting both temporal and morphological features with strong correlations to a clinically validated ground truth.<n>Our findings show that ECGXtract achieves robust performance across most features with a mean correlation score of 0.80 with the ground truth for global features, with lead II consistently providing the best results.
  arXiv  Detail & Related papers  (2025-10-27T12:53:08Z)
• S4ECG: Exploring the impact of long-range interactions for arrhythmia prediction [1.6873748786804317]
  We introduce S4ECG, a novel deep learning architecture leveraging structured state space models for multi-epoch arrhythmia classification.<n>Our joint multi-epoch predictions significantly outperform single-epoch approaches by 1.0-11.6% in macro-AUROC.<n>This work contributes to a paradigm shift toward temporally-aware arrhythmia detection algorithms, opening new possibilities for ECG interpretation.
  arXiv  Detail & Related papers  (2025-10-20T10:48:44Z)
• Enhancing Contrastive Learning-based Electrocardiogram Pretrained Model with Patient Memory Queue [3.7515781255643885]
  How to build a robust ECG pretrained model based on unlabeled data is a key area of focus for researchers.<n>Recent advancements in contrastive learning-based ECG pretrained models highlight the potential of exploiting the additional patient-level self-supervisory signals inherent in ECG.<n>We propose a contrastive learning-based ECG pretrained model enhanced by the Patient Memory Queue (PMQ)
  arXiv  Detail & Related papers  (2025-05-26T05:04:03Z)
• ArrhythmiaVision: Resource-Conscious Deep Learning Models with Visual Explanations for ECG Arrhythmia Classification [0.0]
  We propose ArrhythmiNet V1 and V2, optimized for efficient, real-time arrhythmia classification on edge devices.<n>Inspired by MobileNet's depthwise separable convolutional design, these models maintain memory footprints of just 302.18 KB and 157.76 KB, respectively.<n>Our findings demonstrate the feasibility of combining interpretability, predictive accuracy, and computational efficiency in practical, wearable, and embedded ECG monitoring systems.
  arXiv  Detail & Related papers  (2025-04-30T18:22:45Z)
• Deep End-to-End Survival Analysis with Temporal Consistency [49.77103348208835]
  We present a novel Survival Analysis algorithm designed to efficiently handle large-scale longitudinal data. A central idea in our method is temporal consistency, a hypothesis that past and future outcomes in the data evolve smoothly over time. Our framework uniquely incorporates temporal consistency into large datasets by providing a stable training signal.
  arXiv  Detail & Related papers  (2024-10-09T11:37:09Z)
• PMT: Progressive Mean Teacher via Exploring Temporal Consistency for Semi-Supervised Medical Image Segmentation [51.509573838103854]
  We propose a semi-supervised learning framework, termed Progressive Mean Teachers (PMT), for medical image segmentation. Our PMT generates high-fidelity pseudo labels by learning robust and diverse features in the training process. Experimental results on two datasets with different modalities, i.e., CT and MRI, demonstrate that our method outperforms the state-of-the-art medical image segmentation approaches.
  arXiv  Detail & Related papers  (2024-09-08T15:02:25Z)
• ECC-PolypDet: Enhanced CenterNet with Contrastive Learning for Automatic Polyp Detection [88.4359020192429]
  Existing methods either involve computationally expensive context aggregation or lack prior modeling of polyps, resulting in poor performance in challenging cases. In this paper, we propose the Enhanced CenterNet with Contrastive Learning (ECC-PolypDet), a two-stage training & end-to-end inference framework. Box-assisted Contrastive Learning (BCL) during training to minimize the intra-class difference and maximize the inter-class difference between foreground polyps and backgrounds, enabling our model to capture concealed polyps. In the fine-tuning stage, we introduce the IoU-guided Sample Re-weighting
  arXiv  Detail & Related papers  (2024-01-10T07:03:41Z)
• Learning Beyond Similarities: Incorporating Dissimilarities between Positive Pairs in Self-Supervised Time Series Learning [4.2807943283312095]
  This paper pioneers an SSL approach that transcends mere similarities by integrating dissimilarities among positive pairs. The framework is applied to electrocardiogram (ECG) signals, leading to a notable enhancement of +10% in the detection accuracy of Atrial Fibrillation (AFib) across diverse subjects.
  arXiv  Detail & Related papers  (2023-09-14T08:49:35Z)
• Improving Generalization Capability of Deep Learning-Based Nuclei Instance Segmentation by Non-deterministic Train Time and Deterministic Test Time Stain Normalization [0.674572634849505]
  nuclei instance segmentation plays a fundamental role in a wide range of clinical and research applications. Deep learning (DL)-based approaches have been shown to deliver the best performances. We propose a novel method to improve the generalization capability of a DL-based automatic segmentation approach.
  arXiv  Detail & Related papers  (2023-09-12T11:29:35Z)
• CARLA: Self-supervised Contrastive Representation Learning for Time Series Anomaly Detection [53.83593870825628]
  One main challenge in time series anomaly detection (TSAD) is the lack of labelled data in many real-life scenarios. Most of the existing anomaly detection methods focus on learning the normal behaviour of unlabelled time series in an unsupervised manner. We introduce a novel end-to-end self-supervised ContrAstive Representation Learning approach for time series anomaly detection.
  arXiv  Detail & Related papers  (2023-08-18T04:45:56Z)
• Training Strategies for Improved Lip-reading [61.661446956793604]
  We investigate the performance of state-of-the-art data augmentation approaches, temporal models and other training strategies. A combination of all the methods results in a classification accuracy of 93.4%, which is an absolute improvement of 4.6% over the current state-of-the-art performance. An error analysis of the various training strategies reveals that the performance improves by increasing the classification accuracy of hard-to-recognise words.
  arXiv  Detail & Related papers  (2022-09-03T09:38:11Z)
• Self-supervised contrastive learning of echocardiogram videos enables label-efficient cardiac disease diagnosis [48.64462717254158]
  We developed a self-supervised contrastive learning approach, EchoCLR, to catered to echocardiogram videos. When fine-tuned on small portions of labeled data, EchoCLR pretraining significantly improved classification performance for left ventricular hypertrophy (LVH) and aortic stenosis (AS) EchoCLR is unique in its ability to learn representations of medical videos and demonstrates that SSL can enable label-efficient disease classification from small, labeled datasets.
  arXiv  Detail & Related papers  (2022-07-23T19:17:26Z)
• Diagnosis of Coronavirus Disease 2019 (COVID-19) with Structured Latent Multi-View Representation Learning [48.05232274463484]
  Recently, the outbreak of Coronavirus Disease 2019 (COVID-19) has spread rapidly across the world. Due to the large number of affected patients and heavy labor for doctors, computer-aided diagnosis with machine learning algorithm is urgently needed. In this study, we propose to conduct the diagnosis of COVID-19 with a series of features extracted from CT images.
  arXiv  Detail & Related papers  (2020-05-06T15:19:15Z)
• Robustly Pre-trained Neural Model for Direct Temporal Relation Extraction [10.832917897850361]
  We studied several variants of BERT (Bidirectional Representations using Transformers) We evaluated these methods using a direct temporal relations dataset which is a semantically focused subset of the 2012 i2b2 temporal relations challenge dataset. Results: RoBERTa, which employs better pre-training strategies including using 10x larger corpus, has improved overall F measure by 0.0864 absolute score (on the 1.00 scale) and thus reducing the error rate by 24% relative to the previous state-of-the-art performance achieved with an SVM (support vector machine) model.
  arXiv  Detail & Related papers  (2020-04-13T22:01:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.