Robust and Generalizable Atrial Fibrillation Detection from ECG Using Time-Frequency Fusion and Supervised Contrastive Learning

TL;DR

This paper introduces a novel deep learning framework combining time-frequency fusion and supervised contrastive learning to improve the robustness and generalization of atrial fibrillation detection from ECG signals, outperforming existing methods.

Contribution

The paper proposes a cross-modal deep learning approach with a Bidirectional Gating Module and Cross-modal Supervised Contrastive Learning to enhance ECG-based AF detection robustness and cross-dataset generalization.

Findings

Consistent performance improvements over state-of-the-art methods.

High intra-dataset robustness and cross-dataset generalization.

Efficient computation suitable for edge deployment.

Abstract

Atrial fibrillation (AF) is a common cardiac arrhythmia that significantly increases the risk of stroke and heart failure, necessitating reliable and generalizable detection methods from electrocardiogram (ECG) recordings. Although deep learning has advanced automated AF diagnosis, existing approaches often struggle to exploit complementary time-frequency information effectively, limiting both robustness under intra-dataset and generalization across diverse clinical datasets. To address these challenges, we propose a cross-modal deep learning framework comprising two key components: a Bidirectional Gating Module (BGM) and a Cross-modal Supervised Contrastive Learning (CSCL) strategy. The BGM facilitates dynamic, reciprocal refinement between time and frequency domain features, enhancing model robustness to signal variations within a dataset. Meanwhile, CSCL explicitly structures the joint embedding space by pulling together label-consistent samples and pushing apart different ones, thereby improving inter-class separability and enabling strong cross-dataset generalization. We evaluate our method through five-fold cross-validation on the AFDB and the CPSC2021 dataset, as well as bidirectional cross-dataset experiments (training on one and testing on the other). Results show consistent improvements over state-of-the-art methods across multiple metrics, demonstrating that our approach achieves both high intra-dataset robustness and excellent cross-dataset generalization. We further demonstrate that our method achieves high computational efficiency and anti-interference capability, making it suitable for edge deployment.