Key result
BAM-based deep residual network detects AVNRT and AVRT with up to ~99% precision.
Why the study?
AVNRT and AVRT are common arrhythmias with high similarity, but few studies distinguishing them using automatic ECG detection have been reported.
Does a BAM-based deep residual network accurately classify AVNRT and AVRT from two-lead ECG records?
Does a BAM-based deep residual network accurately classify AVNRT and AVRT from two-lead ECG records?
A BAM-based deep residual network achieved high precision and sensitivity in distinguishing AVNRT from AVRT using two-lead ECG records, potentially assisting in automated diagnosis.
May aid automated SVT classification on ECG; leaves open prospective validation before clinical use.
Atrioventricular nodal reentrant tachycardia (AVNRT) and atrioventricular reentrant tachycardia (AVRT) are two common arrhythmias with high similarity. Automatic electrocardiogram (ECG) detection using machine learning and neural networks has replaced manual detection, but few studies distinguishing AVNRT from AVRT have been reported. This study proposed a classification algorithm using bottleneck attention module (BAM)-based deep residual network (ResNet) through two-lead ECG records. Specifically, ResNet possessed sufficient network depth to extract abundant features, and BAM was introduced to optimize weight assignment of feature maps by fusing together channel and spatial information. Seven types of ECG signals from four public databases were used to pretrain the proposed classification model, which was then fine-tuned using the experimental dataset. The AVNRT and AVRT detection precisions were 98.95% and 87.47%, sensitivities were 87.52% and 98.58%, and the [Formula: see text]1-scores were 92.82% and 92.68%, respectively. These findings showed that our proposed classification model achieved excellent inter-patient classification performance and can assist doctors in the diagnosis of AVNRT and AVRT.
No takes yet. Share an insight, caveat, or question.
Zhang et al. (2021) studied Atrioventricular nodal reentrant tachycardia (AVNRT) and atrioventricular reentrant tachycardia (AVRT). Bottleneck attention module (BAM)-based deep residual network (ResNet) classification algorithm was evaluated on AVNRT and AVRT detection precision, sensitivity, and F1-score. A BAM-based deep residual network classification algorithm achieved AVNRT and AVRT detection precisions of 98.95% and 87.47%, and F1-scores of 92.82% and 92.68%, respectively.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: