Key result
The MSW-Transformer model achieved state-of-the-art performance on five classification tasks of the PTB-XL dataset, with average macro-F1 scores ranging from 34.29% to 77.85%.
Why the study?
Existing CNN-based methods may not fully capture subtle pathological differences in ECG signals, while standard Transformer networks are complex and depend on large-scale datasets.
Answers are grounded in this paper and cite their sources.
The MSW-Transformer model demonstrates state-of-the-art performance and improved computational efficiency for automated 12-lead ECG classification.
Automatic classification of electrocardiogram (ECG) signals plays a crucial role in the early prevention and diagnosis of cardiovascular diseases. While ECG signals can be used for the diagnosis of various diseases, their pathological characteristics exhibit minimal variations, posing a challenge to automatic classification models. Existing methods primarily utilize convolutional neural networks to extract ECG signal features for classification, which may not fully capture the pathological feature differences of different diseases. Transformer networks have advantages in feature extraction for sequence data, but the complete network is complex and relies on large-scale datasets. To address these challenges, we propose a single-layer Transformer network called Multi-Scale Shifted Windows Transformer Networks (MSW-Transformer), which uses a multi-window sliding attention mechanism at different scales to capture features in different dimensions. The self-attention is restricted to non-overlapping local windows via shifted windows, and different window scales have different receptive fields. A learnable feature fusion method is then proposed to integrate features from different windows to further enhance model performance. Furthermore, we visualize the attention mechanism of the multi-window shifted mechanism to achieve better clinical interpretation in the ECG classification task. The proposed model achieves state-of-the-art performance on five classification tasks of the PTBXL-2020 12-lead ECG dataset, which includes 5 diagnostic superclasses, 23 diagnostic subclasses, 12 rhythm classes, 17 morphology classes, and 44 diagnosis classes, with average macro-F1 scores of 77.85%, 47.57%, 66.13%, 34.60%, and 34.29%, and average sample-F1 scores of 81.26%, 68.27%, 91.32%, 50.07%, and 63.19%, respectively.
No takes yet. Share an insight, caveat, or question.
Cheng et al. (2023) studied Cardiovascular diseases (ECG classification) (n=18,885). MSW-Transformer (Multi-Scale Shifted Windows Transformer Networks) vs. Existing advanced network models was evaluated on Classification performance (macro-F1 and sample-F1 scores) on the PTB-XL dataset. The MSW-Transformer model achieved state-of-the-art performance on five classification tasks of the PTB-XL dataset, with average macro-F1 scores ranging from 34.29% to 77.85%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: