A CNN-based Local-Global Self-Attention via Averaged Window Embeddings for Hierarchical ECG Analysis
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916702705418240 |
|---|---|
| author | Buzelin, Arthur Dutenhefner, Pedro Robles Rezende, Turi Porfirio, Luisa G. Bento, Pedro Aquino, Yan Fernandes, Jose Santana, Caio Miana, Gabriela Pappa, Gisele L. Ribeiro, Antonio Meira Jr, Wagner |
| author_facet | Buzelin, Arthur Dutenhefner, Pedro Robles Rezende, Turi Porfirio, Luisa G. Bento, Pedro Aquino, Yan Fernandes, Jose Santana, Caio Miana, Gabriela Pappa, Gisele L. Ribeiro, Antonio Meira Jr, Wagner |
| contents | Cardiovascular diseases remain the leading cause of global mortality, emphasizing the critical need for efficient diagnostic tools such as electrocardiograms (ECGs). Recent advancements in deep learning, particularly transformers, have revolutionized ECG analysis by capturing detailed waveform features as well as global rhythm patterns. However, traditional transformers struggle to effectively capture local morphological features that are critical for accurate ECG interpretation. We propose a novel Local-Global Attention ECG model (LGA-ECG) to address this limitation, integrating convolutional inductive biases with global self-attention mechanisms. Our approach extracts queries by averaging embeddings obtained from overlapping convolutional windows, enabling fine-grained morphological analysis, while simultaneously modeling global context through attention to keys and values derived from the entire sequence. Experiments conducted on the CODE-15 dataset demonstrate that LGA-ECG outperforms state-of-the-art models and ablation studies validate the effectiveness of the local-global attention strategy. By capturing the hierarchical temporal dependencies and morphological patterns in ECG signals, this new design showcases its potential for clinical deployment with robust automated ECG classification. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_16097 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A CNN-based Local-Global Self-Attention via Averaged Window Embeddings for Hierarchical ECG Analysis Buzelin, Arthur Dutenhefner, Pedro Robles Rezende, Turi Porfirio, Luisa G. Bento, Pedro Aquino, Yan Fernandes, Jose Santana, Caio Miana, Gabriela Pappa, Gisele L. Ribeiro, Antonio Meira Jr, Wagner Signal Processing Artificial Intelligence Machine Learning Cardiovascular diseases remain the leading cause of global mortality, emphasizing the critical need for efficient diagnostic tools such as electrocardiograms (ECGs). Recent advancements in deep learning, particularly transformers, have revolutionized ECG analysis by capturing detailed waveform features as well as global rhythm patterns. However, traditional transformers struggle to effectively capture local morphological features that are critical for accurate ECG interpretation. We propose a novel Local-Global Attention ECG model (LGA-ECG) to address this limitation, integrating convolutional inductive biases with global self-attention mechanisms. Our approach extracts queries by averaging embeddings obtained from overlapping convolutional windows, enabling fine-grained morphological analysis, while simultaneously modeling global context through attention to keys and values derived from the entire sequence. Experiments conducted on the CODE-15 dataset demonstrate that LGA-ECG outperforms state-of-the-art models and ablation studies validate the effectiveness of the local-global attention strategy. By capturing the hierarchical temporal dependencies and morphological patterns in ECG signals, this new design showcases its potential for clinical deployment with robust automated ECG classification. |
| title | A CNN-based Local-Global Self-Attention via Averaged Window Embeddings for Hierarchical ECG Analysis |
| topic | Signal Processing Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2504.16097 |