SL-S4Wave: Self-Supervised Learning of Physiological Waveforms with Structured State Space Models

2026-06-18

AI Summary

This work addresses the challenges of modeling long-range dependencies and noise-invariant features in high-sample-rate, multichannel, noisy physiological waveforms—such as electrocardiograms—with scarce annotations. To this end, the authors propose SL-S4Wave, a novel framework that adapts structured state space models (S4) to multichannel physiological signals for the first time. It introduces a multiscale sub-kernel global convolution mechanism and integrates contrastive learning for self-supervised representation learning, effectively capturing both fine-grained local details and long-range temporal dynamics. Experiments demonstrate that SL-S4Wave outperforms existing supervised and self-supervised methods in arrhythmia detection, significantly reduces reliance on labeled data, maintains robustness on long sequences, and generalizes successfully to unseen arrhythmia types as well as diverse electroencephalogram-based tasks.

Abstract

Modeling long-sequence medical time series data, such as electrocardiograms (ECG), poses significant challenges due to high sampling rates, multichannel signal complexity, inherent noise, and limited labeled data. While recent self-supervised learning (SSL) methods, based on various encoder architectures such as convolutional neural networks, have been proposed to learn representations from unlabeled data, they often fall short in capturing long-range dependencies and noise-invariant features. Structured state space models (S4) excel at long-sequence modeling, but existing S4 architectures fail to capture the unique characteristics of multichannel physiological waveforms. In this work, we propose SL-S4Wave, a self-supervised learning framework that combines contrastive learning with a tailored encoder built on structured state space models. The encoder incorporates multi-layer global convolution using multiscale subkernels, enabling the capture of both fine-grained local patterns and long-range temporal dependencies in noisy, high-resolution multichannel waveforms. Extensive experiments on real-world datasets demonstrate that SL-S4Wave (1) consistently outperforms state-of-the-art supervised and self-supervised baselines in a challenging arrhythmia detection task, (2) achieves high performance with significantly fewer labeled examples, showcasing strong label efficiency, and (3) maintains robust performance on long waveform segments, highlighting its capacity to model complex temporal dynamics in long sequences that most existing approaches fail to efficiently model, and (4) transfers effectively to unseen arrhythmia types, underscoring its robust cross-domain generalization. We additionally evaluate SL-S4Wave on multiple EEG tasks, achieving superior performance over strong baselines, demonstrating generalizability of our approach beyond cardiac waveforms.

Problem

• physiological waveforms
• long-sequence modeling
• self-supervised learning
• multichannel time series
• noise-invariant representation

Innovation

• Self-Supervised Learning
• Structured State Space Models
• Physiological Waveforms
• Long-Sequence Modeling
• Contrastive Learning