Ppulsed field ablation and ultra-high-density mapping for PVI: use of machine learning and data augmentation to guide procedure and identify recurrent tachycardia mechanisms at one-year follow-up

Background In managing atrial fibrillation (AF), radiofrequency and cryoablation have been cornerstone techniques for achieving pulmonary vein isolation (PVI). Recently, pulsed-field ablation (PFA) has introduced a novel method for PVI. There remains a gap in knowledge regarding the permanent efficacy of ablation, related explicitly to acute lesion characteristics following PVI. Purpose Our study delves into an in-depth examination of acute lesion characteristics following PFA-PVI through ultra-high-density mapping (UHDM). We aim to identify specific clinical, anatomical, and periprocedural lesion features independently related to 1) intraoperative identification of UHDM non-isolated gaps with electrical conduction after first isolation and 2) three months follow-up recurrency of specific arrhythmias. Methods Results The present study includes 204 patients submitted to PFA-PVI for AF. UHDM guided all procedures to identify non-isolated gaps with electrical conduction. Perioperative and 3-month follow-up data were collected prospectively and analyzed. To build our prediction model, avoiding biases related to the unbalanced nature of the data, data augmentation was performed with SMOTE (Synthetic Minority Over-sampling Technique). Two machine learning (ML) models have been built, using logistic regression as learner, to predict the presence of isolation gaps identified by UHDM and follow-up recurrence of arrhythmias. A 20-fold cross-validation has been performed to train and test the models. The non-isolated gap was detected and immediately corrected in 14 (6.9%) patients and was present more often in patients with larger left atria (LA) (p<0.0001) and those with persistent AF (p=0.02). The ML model achieved an AUC of 0.88 in the prediction of the non-isolated gap after PFA (Precision: 0.65; Sens.: 0.90; F1: 0.76; Spec.: 0.83; NPV: 0.96). At three months follow-up, no patient experienced recurrent AF; recurrent roof-dependent atrial tachycardia was present in 10 (4.9%). Patients with recurrent atrial tachycardia had a significantly narrower remaining atrial-roof conduction bridge (p=0.01) identified intra-procedurally by UHDM, significantly larger LA (p=0.03), and non-significant trend for older age (p=0.07). The ML model achieved an AUC of 0.86, predicting recurrent tachycardia after PFA (Precision: 0.63; Sens.: 0.86; F1: 0.72; Spec.: 0.82; NPV: 0.94). Conclusions Consistent use of UHDM can help identify non-isolated gaps with electrical conduction that may occur even after PVI with updated technologies, such as PFA. Non-isolated gaps should be expected, particularly in patients with larger LA, where UHDM could be of particular use. Moreover, UHDM can help predict the eventual recurrence of arrhythmias. Again, LA size plays an essential role in such recurrencies, together with the size of the remaining conducting tissue "bridges" within the LA roof, measure by UHDM.