The Impact of Temporal Context Length and Encoding Strategies on Self-Supervised ECG Representation Learning

• URL: http://arxiv.org/abs/2608.12695v1
• Date: Thu, 13 Aug 2026 01:18:39 GMT
• Title: The Impact of Temporal Context Length and Encoding Strategies on Self-Supervised ECG Representation Learning
• Abstract summary: Self-supervised electrocardiogram (ECG) models are often trained on a few seconds of ECG signal.<n>It remains unclear whether these choices sacrifice information needed for rhythm inference and longitudinal consistency.<n>We present a controlled study on the Icentia11k single-lead dataset.
• Score: 0.8411385346896411
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Self-supervised electrocardiogram (ECG) models are often trained on a few seconds of ECG signal and, increasingly, on discretized token sequences. It remains unclear whether these choices sacrifice information needed for rhythm inference and longitudinal consistency in real-world ambulatory recordings. We present a controlled study on the Icentia11k single-lead dataset that varies (i) the input horizon (16 seconds, 1 minute, 5 minutes, and 10 minutes) and (ii) the front-end representation (continuous convolutional patch embeddings vs. fixed vector-quantized tokens), while holding the Transformer backbone and training protocol constant. Representations are assessed by downstream abnormal rhythm detection and by patient-level retrieval that probes cross-session stability. Our results show that increasing temporal context beyond 16-second snapshots yields stronger transfer and higher retrieval accuracy, with the strongest performance achieved by the 5- and 10-minute models, indicating improved capture of slow-varying rhythm dynamics and individual-specific structure. Across all evaluated horizons, continuous patch embeddings outperform discretized tokens, suggesting that quantization can discard clinically relevant waveform detail. These findings motivate ECG foundation models that emphasize extended context and continuous encoders for clinical prediction and similarity-based applications. Our code and pretrained models are publicly available at https://github.com/muha-0/ecg-ssl-representation-learning.

Related papers

• Self-Supervised Cardiac Phase Detection via Single-Parameter Latent Orbits [44.45620787098836]
  Accurate identification of end-diastole (ED) and end-systole (ES) in echocardiography underpins the quantification of ventricular function.<n>Recent self-supervised methods either prescribe strict periodic trajectories or learn an unconstrained low-dimensional motion subspace from reconstruction or registration objectives.<n>We learn an effective latent orbit, significantly improves upon the previous state of the art in ED localisation and matches it in ES localisation while using a more constrained representation and fewer training epochs.
  arXiv  Detail & Related papers  (2026-09-10T14:56:16Z)
• Physics-Informed Deep Learning for False Ventricular Tachycardia Alarm Reduction in the ICU [44.313512671851306]
  False ventricular tachycardia (VT) alarms are a leading contributor to alarm fatigue in intensive care units.<n>We propose a deep learning framework combining a 1D SE-ResNet with ICU-realistic data augmentations and a physics-informed auxiliary reconstruction task.
  arXiv  Detail & Related papers  (2026-09-08T16:33:07Z)
• ProCA: Progressive Contrastive Alignment for Robust EEG Visual Decoding [47.35612571473169]
  EEG visual decoding aims to recover visual semantics from non-invasive neural time-series signals.<n>Existing methods rely on fixed visual or textual anchors whose semantic relations may become misaligned with EEG representations that vary across trials, subjects, and learning stages.<n>We propose Progressive Contrastive Alignment (ProCA), a unified and model-agnostic framework for adaptive neural-semantic alignment.
  arXiv  Detail & Related papers  (2026-09-04T12:48:25Z)
• GARLIC: Graph Attention-based Relational Learning of Multivariate Time Series in Intensive Care [5.469342914844525]
  We present Attention-based Graph Learning for Intensive Care (GARLIC) model.<n>GARLIC imputes missing data through exponential learnable neural network architecture.<n>On three ICU benchmarks, GARLIC sets the new state of the art in outcome prediction.
  arXiv  Detail & Related papers  (2026-08-11T14:29:48Z)
• Can Conversational Temporal Dynamics Improve Depression Detection in Dyads? A Preliminary Investigation in Multi-Modality Perspectives [45.77288458953584]
  We investigate conversational temporal dynamics, specifically dyadic turn-pair timing, as a primary modality fused with self-supervised encoders.<n>We compare a compact 24-dimensional timing module against frozen WavLM-large and RoBERTa-large baseline detectors.<n>The learned fusion effectively assigns zero weight to acoustics, demonstrating that conversational timing serves as a lightweight, interpretable complement for dyadic depression screening.
  arXiv  Detail & Related papers  (2026-07-04T07:33:22Z)
• Using Explainability as a Training-Time Reliability Signal for Efficient ECG Classification [14.279568423870572]
  We introduce ERTS, an explainability-based reliability training signal for efficient ECG classification.<n>ERTS uses explanation quality during training to distinguish between informative and unreliable uncertainty.<n>We evaluate ERTS across three ECG datasets and multiple backbone architectures, showing consistent improvements in macro-F1 alongside reduced effective training cost.
  arXiv  Detail & Related papers  (2026-06-10T15:55:00Z)
• 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)
• Cross-Sample Augmented Test-Time Adaptation for Personalized Intraoperative Hypotension Prediction [45.67071315035565]
  Intraoperative hypotension poses significant surgical risks, but accurate prediction remains challenging due to patient-specific variability.<n>We propose CSA-TTA, a novel Cross-Sample Augmented Test-Time Adaptation framework that enhances training by incorporating hypotension events from other individuals.<n>We evaluate the proposed CSA-TTA on both the VitalDB dataset and a real-world in-hospital dataset by integrating it with state-of-the-art time series forecasting models.
  arXiv  Detail & Related papers  (2025-12-12T08:02:37Z)
• Comparative Analysis of Data Augmentation for Clinical ECG Classification with STAR [0.0]
  Sinusoidal Time--Amplitude Resampling (STAR) is a beat-wise augmentation that operates strictly between successive R-peaks.<n>STAR is designed for practical pipelines and offers: (i) morphology-faithful variability that broadens training diversity without corrupting peaks or intervals; (ii) source-resilient training, improving stability across devices, sites, and cohorts without dataset-specific tuning; and (iv) better learning on rare classes via beat-level augmentation.
  arXiv  Detail & Related papers  (2025-10-15T14:18:03Z)
• Masked Autoencoders that Feel the Heart: Unveiling Simplicity Bias for ECG Analyses [24.039917512972977]
  We show that ECG models tend to overfit dominant and repetitive patterns, overlooking fine-grained but clinically critical cues, known as Simplicity Bias (SB)<n>We propose a novel method comprising two key components: 1) Temporal-frequency aware Filters to capture temporal-frequency features reflecting the dynamic characteristics of ECG signals, and 2) building on this, Multi-Grained Prototype Reconstruction for coarse and fine representation learning across dual domains, further mitigating SB.
  arXiv  Detail & Related papers  (2025-06-25T03:25:49Z)
• PSDNorm: Test-Time Temporal Normalization for Deep Learning in Sleep Staging [63.05435596565677]
  We propose PSDNorm that leverages Monge mapping and temporal context to normalize feature maps in deep learning models for signals.<n> PSDNorm achieves state-of-the-art performance on unseen left-out datasets while being 4-times more data-efficient than BatchNorm.
  arXiv  Detail & Related papers  (2025-03-06T16:20:25Z)
• Improving Diffusion Models for ECG Imputation with an Augmented Template Prior [43.6099225257178]
  noisy and poor-quality recordings are a major issue for signals collected using mobile health systems. Recent studies have explored the imputation of missing values in ECG with probabilistic time-series models. We present a template-guided denoising diffusion probabilistic model (DDPM), PulseDiff, which is conditioned on an informative prior for a range of health conditions.
  arXiv  Detail & Related papers  (2023-10-24T11:34:15Z)
• Generalizing electrocardiogram delineation: training convolutional neural networks with synthetic data augmentation [63.51064808536065]
  Existing databases for ECG delineation are small, being insufficient in size and in the array of pathological conditions they represent. This article delves has two main contributions. First, a pseudo-synthetic data generation algorithm was developed, based in probabilistically composing ECG traces given "pools" of fundamental segments, as cropped from the original databases, and a set of rules for their arrangement into coherent synthetic traces. Second, two novel segmentation-based loss functions have been developed, which attempt at enforcing the prediction of an exact number of independent structures and at producing closer segmentation boundaries by focusing on a reduced number of samples.
  arXiv  Detail & Related papers  (2021-11-25T10:11:41Z)

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.