Search

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., (© 2024 Wiley Periodicals LLC.)

Background: Catheter ablation (CA) is an established treatment for atrial fibrillation (AF), but the recurrence of AF is not neglected. Young patients with AF were generally more symptomatic and intolerant to long-term drug treatment. We aim to explore clinical outcomes and predictors of late recurrence (LR) in AF patients younger than 45 years after CA to better manage them., Methods: We retrospectively studied 92 symptomatic AF patients who accepted CA from September 1, 2019, to August 31, 2021. Baseline clinical data (including N-terminal prohormone of brain natriuretic peptide, NT-proBNP), ablation outcomes, and follow-up outcomes were collected. Patients were followed up at 3, 6, 9, and 12 months. Follow-up data were available for 82/92 (89.1%) patients., Results: One-year arrhythmia-free survival was 81.7% (67/82) in our study group. Major complications occurred in 3/82 (3.7%) patients with an acceptable rate. The value of ln(NT-proBNP) ( P = 0.025, odds ratio [OR] = 1.977, 95% confidence interval [CI] 1.087-3.596) and a family history of AF ( P = 0.041, HR = 9.269, 95% CI 1.097-78.295) could independently predict AF recurrence. The ROC analysis of ln(NT-proBNP) showed that NT-proBNP greater than 200.05 pg/ml (area under the curve: 0.772, 95% CI 0.642-0.902, P = 0.001, sensitivity 0.800, specificity 0.701) was the cut-off point for predicting late recurrence., Conclusions: CA is a safe and effective treatment for AF patients younger than 45 years. Elevated NT-proBNP level and a family history of AF could be used as predictors for late recurrence in young patients. The result of this study may help us take more comprehensive management of those with high-recurrence risks to reduce disease burden and improve quality of life., Competing Interests: The authors declare that there is no conflict of interest regarding the publication of this paper., (Copyright © 2023 Haonan Xu et al.)