Key result
Two-stage ResNet model classifies arrhythmias with ~97% accuracy while cutting memory 5-fold.
Why the study?
The study was conducted to develop an effective ECG recurrence plot-based arrhythmia classification algorithm capable of implementation in resource-constricted environments such as portable devices.
Does a two-stage deep residual CNN using recurrence plots improve ECG arrhythmia classification accuracy while maintaining low memory requirements suitable for portable devices?
Does a two-stage deep residual CNN using recurrence plots improve ECG arrhythmia classification accuracy while maintaining low memory requirements suitable for portable devices?
A novel two-stage ResNet deep learning algorithm using ECG recurrence plots demonstrates high diagnostic accuracy for arrhythmia classification with minimized memory requirements, enabling potential use in portable edge-computing devices.
May enable portable arrhythmia detection; leaves open prospective clinical validation.
In this paper, an effective electrocardiogram (ECG) recurrence plot (RP)-based arrhythmia classification algorithm that can be implemented in portable devices is presented. Public databases from PhysioNet were used to conduct this study including the MIT-BIH Atrial Fibrillation Database, the MIT-BIH Arrhythmia Database, the MIT-BIH Malignant Ventricular Ectopy Database, and the Creighton University Ventricular Tachyarrhythmia Database. ECG time series were segmented and converted using an RP, and two-dimensional images were used as inputs to the CNN classifiers. In this study, two-stage classification is proposed to improve the accuracy. The ResNet-18 architecture was applied to detect ventricular fibrillation (VF) and noise during the first stage, whereas normal, atrial fibrillation, premature atrial contraction, and premature ventricular contractions were detected using ResNet-50 in the second stage. The method was evaluated using 5-fold cross-validation which improved the results when compared to previous studies, achieving first and second stage average accuracies of 97.21% and 98.36%, sensitivities of 96.49% and 97.92%, positive predictive values of 95.54% and 98.20%, and F1-scores of 95.96% and 98.05%, respectively. Furthermore, a 5-fold improvement in the memory requirement was achieved when compared with a previous study, making this classifier feasible for use in resource-constricted environments such as portable devices. Even though the method is successful, first stage training requires combining four different arrhythmia types into one label (other), which generates more data for the other category than for VF and noise, thus creating a data imbalance that affects the first stage performance.
No takes yet. Share an insight, caveat, or question.
Mathunjwa et al. (2022) studied Arrhythmia (n=127). Two-stage deep residual CNN (ResNet-18 and ResNet-50) using recurrence plot 2D images was evaluated on First and second stage average accuracy of arrhythmia classification. The two-stage ResNet classification algorithm using ECG recurrence plots achieved average accuracies of 97.21% and 98.36% for the first and second stages, with a 5-fold memory reduction.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: