Key result
A CNN-LSTM network locates AF drivers from body surface potentials with ~94% accuracy.
Why the study?
The mechanisms underlying AF initiation and maintenance remain mostly unknown, while ECGI is an ill-posed problem with limitations and few deep learning methods localize AF drivers.
Does a CNN-LSTM network using Body Surface Potentials accurately locate Atrial Fibrillation drivers in computerized models?
Does a CNN-LSTM network using Body Surface Potentials accurately locate Atrial Fibrillation drivers in computerized models?
Effect estimate: Cohen's Kappa 0.87
A hybrid CNN-LSTM deep learning model can accurately localize atrial fibrillation drivers using simulated body surface potentials, offering a potential non-invasive approach to guide ablation.
CNN-LSTM accurately localizes AF drivers from simulated body surface potentials; hypothesis-generating for non-invasive mapping, requires prospective human validation.
Ablation is the main therapy to control Atrial Fibrillation (AF).However, the underlying mechanism for AF initiation and maintenance remains mostly unknown and represent a major challenge.ECG Imaging (ECGI) has been presented to address this issue, but it is an ill-posed problem and presents several limitations.Many Deep Learning methods have been proposed for AF characterization, but few provide a solution involving the location of the AF driver.In this work, we propose finding the location of AF drivers using Body Surface Potentials (BSPs) and CNN-LSTM with an attention layer networks as a supervised classification problem.The AF driver was correctly located the 94.42% of the time with an average Cohen's Kappa of 0.87.Hence, the proposed model could provide an effective solution for identifying AF driver location for ablation procedures as a non-invasive approach.
No takes yet. Share an insight, caveat, or question.
Fernández-Calvillo et al. (2022) studied Atrial Fibrillation (n=130). CNN-LSTM with attention layer was evaluated on AF driver location accuracy (Cohen's Kappa 0.87). A CNN-LSTM network with an attention layer correctly located atrial fibrillation drivers from body surface potentials 94.42% of the time with an average Cohen's Kappa of 0.87.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: