Key result
CNN using body surface potentials estimates AF driver zones with 89% accuracy.
Why the study?
While deep learning methods have been proposed to detect AF, estimating the atrial area where AF drivers are located remains a topic needing further research.
Can Convolutional Neural Networks using body surface potentials accurately detect atrial fibrillation driver locations?
Can Convolutional Neural Networks using body surface potentials accurately detect atrial fibrillation driver locations?
Effect estimate: Cohen's Kappa 0.85
A CNN-based method using body surface potentials can accurately identify AF driver regions, potentially offering a non-invasive alternative to ECG Imaging for guiding ablation.
May support non-invasive AF driver mapping; leaves open prospective clinical validation before adoption.
Atrial fibrillation (AF) is characterized by complex and irregular propagation patterns, and AF onset locations and drivers responsible for its perpetuation are main targets for ablation procedures. Several Deep Learning-based methods have proposed to detect AF, but the estimation of the atrial area where the drivers are found is a topic where further research is needed. In this work, we propose to estimate the zone where AF drivers are found from body surface potentials (BSPs) and Convolutional Neural Networks (CNN), modeling a supervised classification problem. Accuracy in the test set was 0.89 when using noisy BSPs (SNR=20dB), while the Cohen's Kappa was 0.85. Therefore, the proposed method could help to identify target regions for ablation using a non-invasive procedure, and avoiding the use of ECG Imaging (ECGI).
No takes yet. Share an insight, caveat, or question.
Cámara-Vázquez et al. (2021) studied Atrial fibrillation. Convolutional Neural Networks (CNN) and body surface potentials (BSPs) was evaluated on Accuracy of estimating the zone where AF drivers are found (Cohen's Kappa 0.85). A Convolutional Neural Network using body surface potentials estimated the zone of atrial fibrillation drivers with an accuracy of 0.89 and Cohen's Kappa of 0.85.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: