Advancing the State-of-the-Art for ECG Analysis through Structured State Space Models

TL;DR

This paper demonstrates that structured state space models (SSMs) significantly improve ECG classification by capturing long-term dependencies, challenging existing assumptions about sampling rates and input window sizes, and proposing SSMs as a new paradigm.

Contribution

The study introduces structured state space models to ECG analysis, showing their superiority over convolutional architectures in capturing long-term dependencies and improving classification accuracy.

Findings

SSMs outperform convolutional models in ECG classification.

No benefit from sampling at 500Hz versus 100Hz.

Extending input size beyond 3 seconds offers no advantage.

Abstract

The field of deep-learning-based ECG analysis has been largely dominated by convolutional architectures. This work explores the prospects of applying the recently introduced structured state space models (SSMs) as a particularly promising approach due to its ability to capture long-term dependencies in time series. We demonstrate that this approach leads to significant improvements over the current state-of-the-art for ECG classification, which we trace back to individual pathologies. Furthermore, the model's ability to capture long-term dependencies allows to shed light on long-standing questions in the literature such as the optimal sampling rate or window size to train classification models. Interestingly, we find no evidence for using data sampled at 500Hz as opposed to 100Hz and no advantages from extending the model's input size beyond 3s. Based on this very promising first assessment, SSMs could develop into a new modeling paradigm for ECG analysis.