Key result
HPRNet outperforms standard baseline models in ECG arrhythmia classification with ~92% F1-score.
Why the study?
ECG recordings are often non-stationary and susceptible to noise, posing challenges for robust feature extraction in automated arrhythmia diagnosis with existing deep learning models.
Does the proposed HPRNet improve the accuracy and computational efficiency of automated ECG arrhythmia classification compared to existing methods?
Does the proposed HPRNet improve the accuracy and computational efficiency of automated ECG arrhythmia classification compared to existing methods?
HPRNet provides a highly accurate, noise-robust, and computationally efficient deep learning architecture for automated ECG arrhythmia classification without requiring prior signal denoising.
May aid efficient ECG arrhythmia classification; extends DL benchmarks but leaves open prospective clinical validation.
Accurate classification of electrocardiogram (ECG) signals plays a critical role in the automated diagnosis of cardiac arrhythmias. However, ECG recordings are often non-stationary and susceptible to various types of noise, which makes robust feature extraction challenging for many existing deep learning models. To address these challenges, this paper proposes a hierarchical pyramidal residual network (HPRNet) for ECG arrhythmia classification. HPRNet incorporates a hierarchical pyramidal REB-based backbone (HRB) to capture multi-scale morphological characteristics of ECG signals. In the HRB, the temporal resolution is progressively reduced while the number of feature channels is gradually increased, allowing the network to effectively learn multi-scale ECG representations. Furthermore, a multi-level pruning optimization (MLPO) strategy is incorporated, including network-level pruning and block-level pruning, to reduce redundant parameters and improve computational efficiency while preserving classification capability. Experiments on two public benchmark datasets show that HPRNet achieves superior performance compared with five representative methods on MIT-BIH, reaching an F1-score of 92.05%, while obtaining 91.98% on the INCART binary classification task with an average inference latency of 0.031 s. Moreover, visualization analysis highlights the intrinsic difficulty of distinguishing challenging beat classes, and ablation studies confirm the effectiveness of the proposed HRB and MLPO. These findings support the robustness of HPRNet for automated arrhythmia classification. The source code is publicly available at: https://github.com/jyanhuang/HPRNet-ECG.
No takes yet. Share an insight, caveat, or question.
Huang et al. (2026) studied Cardiac arrhythmias. HPRNet (hierarchical pyramidal residual network) vs. Representative classification methods (Ensemble_SVM, SE-ECGNet, ECGTransForm, SRT, LightweightCNN) was evaluated on F1-score for ECG arrhythmia classification on the MIT-BIH dataset. The proposed HPRNet model achieved superior classification performance with an F1-score of 92.05% on the MIT-BIH dataset and 91.98% on the INCART binary classification task, outperforming representative baseline methods.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: