Using Test-Time Data Augmentation for Cross-Domain Atrial Fibrillation Detection from ECG Signals

Atrial fibrillation (AF) detection from electrocardiogram (ECG) signals is crucial for early diagnosis and management of cardiovascular diseases. However, deploying robust AF detection models across different datasets with significant domain variations remains a challenge. In this paper, we use test-time data augmentation (TTA) to address the cross-domain problem and enhance AF detection performance. We use a publicly available dataset for training - Physionet Computing in Cardiology Challenge 2017 -, while collecting a distinct test set, creating a cross-domain scenario. We employ a neural network architecture that integrates transformer-based encoding of ECG signals and convolutional layers for spectrogram feature extraction. The model combines the latent representations obtained from both encoders to classify the input signals. By incorporating TTA during inference, we enhance the model's performance, achieving an F1 score of 76.6\% on our test set. Furthermore, our experiments demonstrate that the model becomes more resilient to perturbations in the input signal, enhancing its robustness. We show that TTA can be effective in addressing the cross-domain problem, where training and test data originate from disparate sources. This work contributes to advancing the field of AF detection in real-world scenarios.