Artificial intelligence software standardizes electrogram‐based ablation outcome for persistent atrial fibrillation

Abstract

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.

Mapping Atrial Fibrillation to Improve Ablation Outcomes

“…First, mapping was performed only in the left atrium, leaving PRISM sites in the right atrium unstudied. A growing body of literature shows that anatomical right atrial ablation may improve outcomes from current AF ablation strategies, which are predominantly in the left atrium, which is consistent with several mapping studies that revealed a third of potential AF drivers in the right atrium. Second, the authors included patients with prior AF ablation, which may modify the durability of PVI or alter PRISM sites.…”

Mapping for nonpulmonary vein atrial fibrillation sources: The road to improved ablation outcomes

“…In the VX1 system (Volta Medical), an artificial intelligence-based mapping algorithm has been developed to assist in identifying AF drivers. A multicenter, single-arm study showed promising procedural results which were consistent between centers 16 ; randomized multicenter studies are ongoing.…”

“…One limitation of the present work was the fact that AF termination was rare. While the importance of AF termination is debatable, 19 other studies in AF ablation studies have reported significantly greater rates of AF interruption with targeted ablation 6,10,15,16 . It remains to be seen whether this lack of AF termination is related to shortcomings in the mapping system or not, and whether therapy at such sites impacts AF procedural outcomes.…”

Electrogram‐based AF ablation: finally, reproducibility!

“…In this edition of the Journal, Seitz et al 9 present a multicenter study with one expert and seven "satellite centers," which focusses exactly on the two major weaknesses of electrogram-based approaches: (a) reproducibility and (b) an advanced electrogram analysis technology, which combines advanced mathematical algorithms with operators' experience-the latter enhanced by the addition of artificial intelligence (AI). 9 The authors included 85 ablation-naïve patients with persistent AF in 8 centers (1 primary center and 7 satellite centers) with a total of 17 operators performing the ablation.…”

“…In this edition of the Journal, Seitz et al 9 present a multicenter study with one expert and seven "satellite centers," which focusses exactly on the two major weaknesses of electrogram-based approaches: (a) reproducibility and (b) an advanced electrogram analysis technology, which combines advanced mathematical algorithms with operators' experience-the latter enhanced by the addition of artificial intelligence (AI). 9 The authors included 85 ablation-naïve patients with persistent AF in 8 centers (1 primary center and 7 satellite centers) with a total of 17 operators performing the ablation. Of note, almost 30% of the patients suffered from long-lasting persistent AF, the mean age was 70 years, mean CHADSvasc score was 2.5, and mean left atrial volume was 165 ± 31 ml, with a majority of patients suffering of at least one cardiovascular comorbidity-an overall challenging patients' cohort.…”