Introduction Multiple groups have reported on the usefulness of ablating in atrial regions exhibiting abnormal electrograms during atrial fibrillation (AF). Still, previous studies have suggested that ablation outcomes are highly operator‐ and center‐dependent. This study sought to evaluate a novel machine learning software algorithm named VX1 (Volta Medical), trained to adjudicate multipolar electrogram dispersion. Methods This study was a prospective, multicentric, nonrandomized study conducted to assess the feasibility of generating VX1 dispersion maps. In 85 patients, 8 centers, and 17 operators, we compared the acute and long‐term outcomes after ablation in regions exhibiting dispersion between primary and satellite centers. We also compared outcomes to a control group in which dispersion‐guided ablation was performed visually by trained operators. Results The study population included 29% of long‐standing persistent AF. AF termination occurred in 92% and 83% of the patients in primary and satellite centers, respectively, p = 0.31. The average rate of freedom from documented AF, with or without antiarrhythmic drugs (AADs), was 86% after a single procedure, and 89% after an average of 1.3 procedures per patient (p = 0.4). The rate of freedom from any documented atrial arrhythmia, with or without AADs, was 54% and 73% after a single or an average of 1.3 procedures per patient, respectively (p < 0.001). No statistically significant differences between outcomes of the primary versus satellite centers were observed for one (p = 0.8) or multiple procedures (p = 0.4), or between outcomes of the entire study population versus the control group (p > 0.2). Interestingly, intraprocedural AF termination and type of recurrent arrhythmia (i.e., AF vs. AT) appear to be predictors of the subsequent clinical course. Conclusion VX1, an expertise‐based artificial intelligence software solution, allowed for robust center‐to‐center standardization of acute and long‐term ablation outcomes after electrogram‐based ablation.

Up to half of patients implanted for high-degree AVCD after TAVI had conduction recovery. Patients with cDDD programming at hospital discharge had more pacemaker dependency and a worse cardiac prognosis. Thus, pacemaker mode should be systematically set to promote spontaneous atrioventricular conduction in patients with pacemaker implantation after TAVI.

Funding Acknowledgements Type of funding sources: Other. Main funding source(s): Volta Medical Saint Joseph Hospital Marseille, France Background Spatiotemporal dispersion is an electrical footprint of atrial fibrillation (AF) drivers that has been successfully implemented to target extra-pulmonary veins (PVs) regions during persistent AF ablation. Purpose The aim of the study is to characterize spatiotemporal dispersion extent and location and to compare dispersion atrial localization and extent between pacing-induced AF and spontaneous AF. Methods Spatiotemporal dispersion maps were built with an artificial intelligence software (VX1, Volta Medical) and analyzed in 71 consecutives persistent (66%) and long-standing persistent (34%) AF patients admitted for a first ablation procedure. Fifty-two patients were in spontaneous AF (73%) at the outset of the procedure while AF was induced in 19 patients (27%) by burst pacing ± isoproterenol infusion. A semi-quantitative visual quantification of dispersion extent was conducted by implementing an atrial segmentation into 22 regions and a region-centered score from 0 (no dispersion) to 3 (high dispersion). Also, an automated quantification was performed as follows: (i) a gradient filter designed to extract atrial shapes from background was applied, (ii) dispersion areas were segmented using a color thresholding method, and (iii) a structuring element was used to connect segmented dispersion areas. Results The regional characterization of dispersion shows that dispersion distribution follows a similar pattern and is present in similar atrial regions, regardless of whether AF is spontaneous or induced (Figure 1). Global dispersion extent, however, is significantly higher in the left atrium of patients in spontaneous AF compared to patients with induced AF (15.43% ± 9.04 versus 9.86% ± 6.41, P=0.0025, Figure 2). Accordingly, the regional dispersion score tends to be lower when AF is induced. Dispersion hotspots are: LSPV anterior antrum -ridge (R1), RSPV anterior antrum (R5), anterior wall (R9), roof (R10), posterior wall (R11), and low left atrial septum (R15) in the left atrium. In the right atrium: low right atrial septum (R15) and posterior right atrium (R20) (Figure 1). Conclusions Artificial intelligence-enabled dispersion persistent AF mapping indicates that dispersion is reduced in induced vs. spontaneous-AF but that its distribution follows a similar pattern.