Data-driven classification of left atrial morphology and its predictive impact on atrial fibrillation catheter ablation

INTRODUCTION

Various left atrial (LA) anatomical structures are correlated with postablative recurrence for atrial fibrillation (AF) patients. Comprehensively integrating anatomical structures, digitizing them, and implementing in-depth analysis, which may supply new insights, are needed. Thus, we aim to establish an interpretable model to identify AF patients' phenotypes according to LA anatomical morphology, using machine learning techniques.

METHODS AND RESULTS

Five hundred and nine AF patients underwent first ablation treatment in three centers were included and were followed-up for postablative recurrent atrial arrhythmias. Data from 369 patients were regarded as training set, while data from another 140 patients, collected from different centers, were used as validation set. We manually measured 57 morphological parameters on enhanced computed tomography with three-dimensional reconstruction technique and implemented unsupervised learning accordingly. Three morphological groups were identified, with distinct prognosis according to Kaplan-Meier estimator (p < .001). Multivariable Cox model revealed that morphological grouping were independent predictors of 1-year recurrence (Group 1: HR = 3.00, 95% CI: 1.51-5.95, p = .002; Group 2: HR = 4.68, 95% CI: 2.40-9.11, p < .001; Group 3 as reference). Furthermore, external validation consistently demonstrated our findings.

CONCLUSIONS

Our study illustrated the feasibility of employing unsupervised learning for the classification of LA morphology. By utilizing morphological grouping, we can effectively identify individuals at different risks of postablative recurrence and thereby assist in clinical decision-making.

Reverse electrical and structural remodeling of the left atrium occurs early after pulmonary vein isolation for persistent atrial fibrillation

PURPOSE

Adverse left atrial (LA) remodeling is known to be associated with persistent atrial fibrillation (PeAF). The time course and pattern of reversal of LA remodeling following catheter ablation is poorly understood. We aimed to evaluate LA chamber volumes and dimensions, LA conduction velocities, and LA bipolar voltages at baseline and at 2 months after catheter ablation for PeAF.

METHODS

Twenty-three patients with PeAF underwent detailed LA mapping during fixed rate atrial pacing using the CARTO3 navigation system prior to undergoing pulmonary vein isolation. All patients returned for protocol-mandated repeat electrophysiology study at 2 months, irrespective of symptoms or arrhythmia recurrence, during which all measurements were repeated using an identical mapping protocol. Patients then underwent daily ECG monitoring for 12 months.

RESULTS

Nineteen out of twenty-three (83.6%) patients had durable PVI of all veins at repeat electrophysiology study, while 4 (17.4%) patients had late reconnection of a single vein each. In the blinded offline analysis, LA volume at follow-up was significantly lower as compared with baseline (55 ± 14 mL/m² vs. 65 ± 15 mL/m², P < 0.001). LA conduction velocities were significantly greater at 2 months (0.90 ± 0.13 m/s vs. 0.78 ± 0.13 m/s, P = 0.01). There was non-uniform regional LA voltage evolution, with a significant increase in bipolar voltages observed on the LA posterior wall (2.18 ± 0.85 mV vs. 1.83 ± 0.49 mV, P = 0.04), but not elsewhere. Individual variables of remodeling were not associated with AF recurrence.

CONCLUSION

Significant structural and electrical reverse remodeling of the LA can be seen as early as 2 months following successful catheter ablation for PeAF.

Effect of epicardial fat and metabolic syndrome on reverse atrial remodeling after ablation for atrial fibrillation

BACKGROUND

Metabolic syndrome/epicardial adipose tissue (EAT) plays an important role in atrial fibrillation (AF). Although reverse atrial remodeling (RAR) often occurs after AF ablation, the effects of EAT on RAR remain unknown.

METHODS

Study subjects were 104 patients in whom transthoracic echocardiography (TTE) was performed before AF ablation and 3, 6, and 12 months afterward. EAT was assessed in terms of its thickness adjacent to the right ventricular anterior wall in the TTE parasternal view. RAR was defined as >10% reduction in the left atrial volume (LAV) index by the 3-month follow-up examination.

RESULTS

Postablation RAR occurred in 57/104 (55%) patients. RAR absence was associated with a relatively thick EAT (4.92 ± 1.65 vs. 3.92 ± 1.17 mm, P = 0.0005), small LAV index (24.6 ± 7.5 vs. 28.8 ± 10.6 mL/m2, P = 0.0233), and metabolic syndrome (62% vs. 28%, P = 0.0006). Metabolic syndrome and EAT were shown to be independent predictors of RAR absence. Thick EAT was significantly associated with AF recurrence after ablation (5.05 ± 2.19 mm vs. 4.17 ± 1.16 mm for no AF recurrence group, P = 0.0116), but metabolic syndrome was not (48% vs. 42%, P = 0.6189). Despite no change in body weight, EAT thickness decreased significantly by 12 months in patients without AF recurrence (4.17 ± 1.16 vs. 3.65 ± 1.16 mm, P < 0.0001).

CONCLUSIONS

EAT and metabolic syndrome appear to be strongly associated with RAR absence, but only the thick EAT was significantly associated with the postablation AF recurrence. Our findings, especially the thinning of EAT, suggest that thick EAT lead to AF vulnerability but that EAT reduction favorably affects ablation outcome.