RESUMO
BACKGROUND: Atrial arrhythmogenic substrate is a key determinant of atrial fibrillation (AF) recurrence after pulmonary vein isolation (PVI), and reduced conduction velocities have been linked to adverse outcome. However, a noninvasive method to assess such electrophysiologic substrate is not available to date. OBJECTIVE: This study aimed to noninvasively assess regional conduction velocities and their association with arrhythmia-free survival after PVI. METHODS: A consecutive 52 patients scheduled for AF ablation (PVI only) and 19 healthy controls were prospectively included and received electrocardiographic imaging (ECGi) to noninvasively determine regional atrial conduction velocities in sinus rhythm. A novel ECGi technology obviating the need of additional computed tomography or cardiac magnetic resonance imaging was applied and validated by invasive mapping. RESULTS: Mean ECGi-determined atrial conduction velocities were significantly lower in AF patients than in healthy controls (1.45 ± 0.15 m/s vs 1.64 ± 0.15 m/s; P < .0001). Differences were particularly pronounced in a regional analysis considering only the segment with the lowest average conduction velocity in each patient (0.8 ± 0.22 m/s vs 1.08 ± 0.26 m/s; P < .0001). This average conduction velocity of the "slowest" segment was independently associated with arrhythmia recurrence and better discriminated between PVI responders and nonresponders than previously proposed predictors, including left atrial size and late gadolinium enhancement (magnetic resonance imaging). Patients without slow-conduction areas (mean conduction velocity <0.78 m/s) showed significantly higher 12-month arrhythmia-free survival than those with 1 or more slow-conduction areas (88.9% vs 48.0%; P = .002). CONCLUSION: This is the first study to investigate regional atrial conduction velocities noninvasively. The absence of ECGi-determined slow-conduction areas well discriminates PVI responders from nonresponders. Such noninvasive assessment of electrical arrhythmogenic substrate may guide treatment strategies and be a step toward personalized AF therapy.
RESUMO
BACKGROUND AND OBJECTIVE: Atrial Fibrillation (AF) is a supraventricular tachyarrhythmia that can lead to thromboembolism, hearlt failure, ischemic stroke, and a decreased quality of life. Characterizing the locations where the mechanisms of AF are initialized and maintained is key to accomplishing an effective ablation of the targets, hence restoring sinus rhythm. Many methods have been investigated to locate such targets in a non-invasive way, such as Electrocardiographic Imaging, which enables an on-invasive and panoramic characterization of cardiac electrical activity using recording Body Surface Potentials (BSP) and a torso model of the patient. Nonetheless, this technique entails some major issues stemming from solving the inverse problem, which is known to be severely ill-posed. In this context, many machine learning and deep learning approaches aim to tackle the characterization and classification of AF targets to improve AF diagnosis and treatment. METHODS: In this work, we propose a method to locate AF drivers as a supervised classification problem. We employed a hybrid form of the convolutional-recurrent network which enables feature extraction and sequential data modeling utilizing labeled realistic computerized AF models. Thus, we used 16 AF electrograms, 1 atrium, and 10 torso geometries to compute the forward problem. Previously, the AF models were labeled by assigning each sample of the signals a region from the atria from 0 (no driver) to 7, according to the spatial location of the AF driver. The resulting 160 BSP signals, which resemble a 64-lead vest recording, are preprocessed and then introduced into the network following a 4-fold cross-validation in batches of 50 samples. RESULTS: The results show a mean accuracy of 74.75% among the 4 folds, with a better performance in detecting sinus rhythm, and drivers near the left superior pulmonary vein (R1), and right superior pulmonary vein (R3) whose mean sensitivity bounds around 84%-87%. Significantly good results are obtained in mean sensitivity (87%) and specificity (83%) in R1. CONCLUSIONS: Good results in R1 are highly convenient since AF drivers are commonly found in this area: the left atrial appendage, as suggested in some previous studies. These promising results indicate that using CNN-LSTM networks could lead to new strategies exploiting temporal correlations to address this challenge effectively.