Key result
The MultiECGNet image-based ensemble classifier detected atrial fibrillation with an F1 score of 0.87, outperforming a single EfficientNet-B3 model (0.71) and performing comparably to a signal-based model (0.83).
Why the study?
The study evaluated an ensemble classifier (MultiECGNet) using multi-format ECG images for diagnosing AF and compared its performance to a signal-based deep learning model.
Does an image-based ensemble classifier (MultiECGNet) improve the diagnosis of atrial fibrillation from multi-format ECG images compared to single image-based models or signal-based models?
Does an image-based ensemble classifier (MultiECGNet) improve the diagnosis of atrial fibrillation from multi-format ECG images compared to single image-based models or signal-based models?
Absolute Event Rate: 0.87% vs 0.83%
An image-based ensemble deep learning model trained on multiple ECG formats achieved high accuracy for atrial fibrillation detection, comparable to signal-based models, facilitating the use of historical ECG image archives.
Image-based AF classifiers show feasibility; leaves open prospective validation versus signal-based models before clinical use.
Aim To evaluate the performance of an ensemble classifier, MultiECGNet, using multi-format electrocardiographic (ECG) images for the diagnosis of atrial fibrillation (AF), and to compare its performance with a signal-based deep learning model. Methods An ensemble of ECG classifiers was developed using four models derived by truncating the pre-trained EfficientNet B3 model at different feature extraction layers. Transfer learning was employed to train the ensemble on the publicly available PTB-XL dataset for AF detection. External validation was performed using the Chinese Physiological Society Signal Challenge 2018 dataset. ECG samples were converted into two image formats (2x6 and 4x3), and performance was evaluated across same-format, cross-format, and mixed-format classification tasks. Results The ensemble classifier detected AF in the external validation dataset with an accuracy of 0.95 and F1 score of 0.87, which was comparable to a signal-based model (F1-score: 0.87 vs 0.83) and outperformed a single EfficientNet-B3 model (F1-score: 0.87 vs 0.71). Training on one ECG format and testing on a different format resulted in reduced performance (F1 score: 0.66-0.71). However, training on a dataset containing a balanced mix of both formats improved performance compared to same-format training alone (F1-score: 0.86 vs 0.87). Conclusion The proposed image-based ensemble classifier demonstrated comparable performance to a strong signal-based model for AF detection. While cross-format generalization posed a challenge, incorporating multiple ECG formats during training mitigated this limitation and improved model robustness.
No takes yet. Share an insight, caveat, or question.
Phan et al. (2025) studied Atrial fibrillation (n=28,676). MultiECGNet (image-based ensemble classifier) vs. Signal-based deep learning model (DigitalNet) and single EfficientNet-B3 model was evaluated on Detection of atrial fibrillation (F1-score). The MultiECGNet image-based ensemble classifier detected atrial fibrillation with an F1 score of 0.87, outperforming a single EfficientNet-B3 model (0.71) and performing comparably to a signal-based model (0.83).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: