Key result
ResNet model using aVF and esophageal ECG achieves ~1.0 AUC for differentiating PSVT types.
Why the study?
The study aimed to develop a deep learning model combining surface and esophageal ECG data to accurately differentiate types of PSVT, including S-F AVNRT, AVRT-L, and AVRT-R.
Does a ResNet-based deep learning model using surface and esophageal ECG data improve diagnostic accuracy for differentiating PSVT types compared to traditional machine learning classifiers?
Observational (n=775)
Yes
Does a ResNet-based deep learning model using surface and esophageal ECG data improve diagnostic accuracy for differentiating PSVT types compared to traditional machine learning classifiers?
p-value: p=<0.001
A deep learning model combining surface and esophageal ECG data provides highly accurate differentiation of PSVT types, outperforming traditional machine learning methods.
Objective This study aims to develop a deep learning model utilizing both surface and esophageal electrocardiogram (ECG) data to accurately differentiate types of paroxysmal supraventricular tachycardia (PSVT), including slow-fast atrioventricular nodal re-entrant tachycardia (S-F AVNRT), and orthodromic atrioventricular reentrant tachycardia with left-sided (AVRT-L) and right-sided (AVRT-R) accessory pathways. Methods We analyzed 921 ECG cases from 775 patients from four hospitals between 2014 and 2022, segmented into 6261 ten-second ECG segments. A Residual Network (ResNet)-based model was developed. For comparison, Random Forest (RF) and eXtreme Gradient Boosting (XGBoost) classifiers were also constructed using handcrafted time-domain and frequency-domain features. It was thoroughly evaluated using a comprehensive set of metrics. These metrics included accuracy (ACC), the area under the receiver operating characteristic curve (AUC); sensitivity (SEN), specificity (SPE), positive predictive value (PPV), negative predictive value (NPV), and F1-Score. Results The diagnostic efficacy of ECG lead configurations was robust. Among surface-only leads, the three-lead combination II+V 1 +aVF achieved the highest AUC (0.989). The single-lead aVF demonstrated remarkable efficiency (AUC 0.961), approaching the performance of the full 12-lead ECG (0.974). The bipolar esophageal lead (EB) alone achieved an AUC of 0.989, comparable to II+V 1 +aVF (AUC 0.989). The combination aVF+EB yielded the highest overall AUC of 0.996. ResNet significantly outperformed RF and XGBoost across all lead configurations ( P < 0.001). Conclusion This model effectively distinguishes between PSVT types, surpassing traditional diagnostics in accuracy and reliability. Future research should focus on model optimization and dataset expansion to enhance diagnostic capabilities and interpretability.
No takes yet. Share an insight, caveat, or question.
Li et al. (2026) conducted an observational in paroxysmal supraventricular tachycardia (n=775). ResNet-based deep learning model vs. Random Forest and XGBoost classifiers was evaluated on Area under the receiver operating characteristic curve (AUC) for differentiating PSVT types (p=<0.001). A ResNet-based deep learning model combining aVF and bipolar esophageal ECG leads achieved an AUC of 0.996 for differentiating PSVT types, significantly outperforming RF and XGBoost (P<0.001).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: