Key result
Deep learning from 12-lead ECGs improves VT exit site localization ~26% versus prescribed QRS features.
Why the study?
Does a deep learning model using 12-lead ECG QRS complexes improve the localization accuracy of ventricular tachycardia exit sites compared to linear regression with prescribed QRS integrals?
Does a deep learning model using 12-lead ECG QRS complexes improve the localization accuracy of ventricular tachycardia exit sites compared to linear regression with prescribed QRS integrals?
Absolute Event Rate: 11.83% vs 15.09%
A deep learning model can automatically extract discriminative features from 12-lead ECGs to predict the 3D coordinates of ventricular tachycardia exit sites with higher accuracy than traditional QRS-integral methods, potentially improving catheter ablation efficiency.
May support automated ECG localization in VT ablation; hypothesis-generating and requires prospective outcome validation.
Automatic localization of the exit site of ventricular tachycardia (VT) can improve the efficiency and efficacy of catheter ablation. Because the exit site of the VT gives rise to its QRS complex on electrocardiogram (ECG), it is possible to build a predictive model to directly localize the exit of a VT from its 12-lead ECG. In previous works, prescribed features such as QRS integrals have been used to build such models. In this paper, we propose a deep network to automatically extract more discriminative features from QRS complex to localize the origin of ventricular activation. To improve the resolution of localization compared to previous works based on a small number of pre-defined segments, we localize the origin of ventricular activation as 3D coordinates. Model training and testing were performed on 12-lead ECG data of 1012 distinct pacing sites, collected from patients during routine pace-mapping procedures. Compared with the use of prescribed QRS-integral as an input feature, the presented deep model achieved an improvement of localization accuracy by approximately 4 millimeters (26%) on average.
No takes yet. Share an insight, caveat, or question.
Gyawali et al. (2017) studied Ventricular tachycardia (n=39). Deep learning model (Deep-fDAEs) vs. Linear regression with prescribed QRS integrals was evaluated on Localization accuracy (mean error in millimeters) on the test set. A deep learning model automatically extracting features from 12-lead ECGs improved the localization accuracy of ventricular tachycardia exit sites by approximately 4 millimeters (~26%) compared to using prescribed QRS-integral features.
Synapse has enriched 4 closely related papers on similar clinical questions. Consider them for comparative context: