Key result
MRAST-Net achieves ~97% AUC for multi-label 12-lead ECG classification.
Why the study?
Existing high-performing ECG classification methods typically rely on complex deep learning architectures with large parameter counts, high computational costs, and limited deployability in resource-constrained settings.
Does MRAST-Net achieve high multi-label classification performance on 12-lead ECG datasets while maintaining a lightweight parameter scale?
Does MRAST-Net achieve high multi-label classification performance on 12-lead ECG datasets while maintaining a lightweight parameter scale?
MRAST-Net provides high 12-lead ECG diagnostic classification accuracy with a lightweight architecture suitable for deployment in portable monitoring devices and resource-constrained clinical settings.
Answers are grounded in this paper and cite their sources.
MRAST-Net supports efficient multi-class ECG classification on public datasets; leaves open prospective clinical validation before adoption.
Electrocardiogram (ECG) signals play an important role in cardiovascular disease screening, clinical monitoring, and remote healthcare. However, existing high-performing ECG classification methods usually rely on complex deep learning architectures, which often involve a large number of parameters, high computational cost, and limited deployability in resource-constrained scenarios. To balance classification performance and lightweight deployment, this paper proposes MRAST-Net, a lightweight multi-receptive-field residual temporal network for 12-lead ECG classification. The proposed model first employs a lead mixing layer to enable cross-lead information interaction. It then uses a lightweight multi-scale residual depthwise convolution module to extract local waveform morphology features under different receptive fields, while an efficient channel attention mechanism is introduced to enhance informative channel responses. On this basis, a temporal convolutional network is further incorporated to model long-range dynamic dependencies, and attentive statistics pooling is used to aggregate global statistical features for final multi-label classification. Experiments on two public 12-lead ECG datasets, PTB-XL and CPSC-2018, show that the proposed model achieves AUC scores of 93.12 ± 0.16%, 92.29 ± 0.80%, and 92.62 ± 0.51%, and ACC scores of 89.17 ± 0.09%, 96.40 ± 0.02%, and 97.72 ± 0.07% on the 5-superclass, 23-subclass, and 44-diagnostic-class tasks of PTB-XL, respectively. On CPSC-2018, MRAST-Net achieves an AUC of 96.57 ± 0.43% and an ACC of 96.59 ± 0.26% under 5×3 nested cross-validation. These results demonstrate that MRAST-Net achieves competitive classification performance while maintaining a low parameter scale, indicating its potential for deployment in resource-constrained scenarios such as portable monitoring devices, real-time assisted diagnosis, and primary healthcare.
No takes yet. Share an insight, caveat, or question.
Wang et al. (2026) studied 12-lead ECG classification for cardiovascular disease screening. MRAST-Net (lightweight multi-receptive-field residual temporal network) was evaluated on 12-lead ECG multi-label classification performance (AUC and Accuracy). MRAST-Net achieved an AUC of 96.57% and accuracy of 96.59% on CPSC-2018, and AUCs of 92.29% to 93.12% across PTB-XL 12-lead ECG classification tasks.
Synapse has enriched 10 related papers. Consider them for comparative context: