Reliable prediction of very late recurrence of atrial fibrillation (VLRAF) occuring >12 months after catheter ablation (CA) in apparently "cured" patients could optimize long-term follow-up and modify decision-making regarding the discontinuation of oral anticoagulant therapy. In a single-centre cohort of consecutive patients post radiofrequency AFCA, we retrospectively derived a novel score for VLRAF prediction. Of 133 consecutive post AFCA patients (mean age 56.9 ± 11.8 years, 63.9% male, 69.2% with paroxysmal AF) who were arrhythmia-free at 12 months (excluding 3-month "blanking period"), Catheter-ablation (CA) is superior to antiarrhythmic drugs (AADs) in patients with symptomatic atrial fibrillation (AF), but AF may re-occur despite multiple re-do procedures and recent technical improvements 1,2 . Most arrhythmia recurrences are identified within the first year after the procedure, while further long-term follow-up strategy for initially "successfully" treated patients is less well defined and inconsistently reported 1-9 .Several studies described a progressive increase in the arrhythmia recurrence rates over time in patients with initial post-ablation suppression of AF 4-6 . It is reported that 10-40% of patients who were arrhythmia free within the first post-procedural year experienced very late recurrence of AF (VLRAF) over long-term follow-up 2-9 . Several scoring systems (i.e., the APPLE, ALARMc and BASE-AF2 score) were recently proposed to predict the short-term risk of AF recurrence after the procedure 10-12 . However, none of these scores have addressed VLRAF occurring in patients who were free of AF at 1 year post procedure. Importantly, reliable identification of increased risk of VLRAF could strongly influence decision-making regarding the long-term use of oral anticoagulation and/or AAD therapy as well as the long-term monitoring strategy after the procedure 1,2 . Due to altered risk/benefit ratio, multiple AF ablation procedures may not be justified in patients at high risk of recurrent AF, and reliable prediction of VLRAF could optimize the patient selection for re-do CA 1,2,9,11 .