Key result
A novel arrhythmia classification scheme based on modified HRNet and efficient channel attention achieved an average accuracy of 99.86% for classifying five arrhythmia types on the MIT-BIH database.
Why the study?
Visual inspection of ECG signals is time-consuming and prone to misdiagnosis, and existing high-resolution HRNet architectures are designed for two-dimensional images rather than ECG signal classification.
Does a modified HRNet and ECA-based classification scheme improve the accuracy of arrhythmia detection in ECG signals compared to benchmarking methods?
Does a modified HRNet and ECA-based classification scheme improve the accuracy of arrhythmia detection in ECG signals compared to benchmarking methods?
A novel modified HRNet and ECA-based classification scheme achieves 99.86% accuracy in detecting five types of cardiac arrhythmias from ECG signals.
May support AI arrhythmia detection research; leaves open prospective clinical validation before any practice change.
Electrocardiogram (ECG) signals have been widely used to detect cardiac arrhythmia. Visual inspection is not only time consuming, but also may lead to misdiagnosis and affect the prevention or treatment of the disease. Therefore, automatic diagnosis which can greatly improve the efficiency and accuracy of diagnosis is needed to assist doctors with arrhythmia diagnosis. Due to its capacity for high resolution, HRNet has attracted extensive attention for classification in recent years. However, HRNet is only designed for two-dimensional images, and thus is not suitable for ECG signal classification. In this paper, we propose an arrhythmia classification scheme which is based on a modified HRNet and efficient channel attention (ECA) to classify five arrhythmia types. The proposed scheme first divides the original ECG signal into 5 s segments of 1800 sampling points. Then, the segments are fed into the improved HRNet network for automatic learning and classification. Extensive simulations have been performed on the MIT-BIH database to validate the effectiveness of the proposed scheme. Experimental results have shown that the proposed scheme achieves an average accuracy of 99.86%, which is superior to the benchmarking methods.
No takes yet. Share an insight, caveat, or question.
Hua et al. (2022) studied Cardiac arrhythmia. Modified HRNet and efficient channel attention (ECA) scheme vs. Benchmarking methods was evaluated on Classification of five arrhythmia types. A novel arrhythmia classification scheme based on modified HRNet and efficient channel attention achieved an average accuracy of 99.86% for classifying five arrhythmia types on the MIT-BIH database.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: