Extending Pretrained 10-Second ECG Foundation Models to Longer Horizons

TL;DR

This paper presents a parameter-efficient framework to extend pretrained 10-second ECG models to longer and variable-length recordings, enabling better long-horizon analysis without retraining the backbone.

Contribution

It introduces a lightweight plug-in module that allows existing ECG foundation models to process longer sequences structurally and semantically, without retraining the core model.

Findings

Outperforms sliding-window and pooling baselines on multiple long-horizon ECG tasks.

Demonstrates robustness and parameter efficiency across various datasets and model backbones.

Abstract

Electrocardiogram (ECG) foundation models pretrained on typical diagnostic 10-second ECG segments, have demonstrated strong transferability across a range of clinical applications. However, many real-world applications produce recordings that are typically longer, and are varied in duration during inference time. These 10-second models have no built-in way to combine information across time. Extending them to longer horizons introduces two challenges: structural incompatibilities arising from input-length disparities, and semantic challenges that limit meaningful temporal aggregation. We propose a parameter-efficient framework that extends pretrained ECG foundation models to longer and variable-length ECGs without retraining the backbone. Guided by a frozen pretrained 10-second model, we introduce a lightweight plug-in module that extends the model in two complementary ways: (i) structurally compatible long-sequence processing and (ii) semantically informed temporal modeling. Experiments on multiple long-horizon ECG tasks, datasets, and foundation model backbones demonstrate that our method enables robust long-horizon extension from pretrained snapshot models, consistently outperforming sliding-window and pooling-based baselines with strong parameter efficiency.