A novel convolutional neural network structure for differential diagnosis of wide QRS complex tachycardia

Document Type

Journal Article

Publication Title

Biomedical Signal Processing and Control






Centre for Artificial Intelligence and Machine Learning (CAIML) / School of Science




Fayyazifar, N., Dwivedi, G., Suter, D., Ahderom, S., Maiorana, A., Clarkin, O., . . . Chow, B. J. W. (2023). A novel convolutional neural network structure for differential diagnosis of wide QRS complex tachycardia. Biomedical Signal Processing and Control, 81, article 104506. https://doi.org/10.1016/j.bspc.2022.104506


Background and objectives: Cardiac arrhythmias are a significant cause of morbidity and mortality in patients with cardiovascular disease. Accurate rhythm diagnosis is critical in patients presenting with wide QRS complex tachycardia (WCT). Real-time visual interpretation of electrocardiograms (ECG) of complex arrhythmias is difficult and requires expertise. We designed a convolutional neural network (CNN) that could accurately classify WCT into those that are ventricular in origin (ventricular tachycardia (VT)) or supraventricular tachycardia with aberrancy (SVT). Methods: A total of 3065 patients with wide complex ECGs were screened (415 with VT and 2650 with SVT). A CNN model was designed through a Neural Architecture Search (NAS) method. This CNN consisted of a stem convolution layer and five cells, each cell containing separable-convolution and dilated-separable-convolution layers. Results: Using 5-fold cross-validation and executing algorithm for five independent runs (with five different seeds), the proposed CNN model achieved a detection accuracy of 87.5 ± 0.0025 and 91.7 %±0.0004 for VT and SVT, respectively. The total sensitivity, specificity, positive predictive value, negative predictive value and F1-score of the CNN model were 88.50 %, 88.50 %, 88.54 %, 88.54 %, and 88.49 %, respectively. Conclusions: In a cohort of patients presenting with a WCT, our CNN model achieved an accuracy of 87.5% and 91.7% to correctly diagnose VT and SVT, respectively. This model has the potential of being used in real-time settings and to assist physicians with interpretation and decision making.



Access Rights

subscription content