Introduction: Although the presence of left atrial low-voltage areas (LVAs) is strongly associated with the recurrence of atrial fibrillation (AF) after ablation, few methods are available to classify the prevalence of LVAs. The purpose of this study was to establish a risk score for predicting the prevalence of LVAs in patients undergoing ablation for AF. Methods: We enrolled 1004 consecutive patients who underwent initial ablation for AF (age, 68 ± 10 years old; female, 346 (34%); persistent atrial fibrillation, 513 (51%)). LVAs were deemed present when the voltage map after pulmonary vein isolation demonstrated low-voltage areas with a peak-to-peak bipolar voltage of <0.5 mV covering ≥5 cm2 of the left atrium. Results: LVAs were present in 206 (21%) patients. The SPEED score was obtained as the total number of independent predictors as identified on multivariate analysis, namely female sex (odds ratio (OR) 3.4 [95% confidence interval (CI) 2.2-5.2], p <0.01), persistent AF (OR 1.8 [95% CI 1.1-3.0], p=0.02), age ≥70 years (OR 2.3 [95% CI 1.5-3.4], p <0.01), elevated brain natriuretic peptide ≥100 pg/ml or N-terminal pro-brain natriuretic peptide ≥400 pg/ml (OR 1.7 [95% CI 1.02-2.8], p=0.04), and diabetes mellitus (OR 1.8 [95% CI 1.1-2.8], p=0.02). LVAs were more frequent in patients with a higher SPEED score, and prevalence increased with each additional SPEED score point (OR 2.4 [95% CI 2.0-2.8], p <0.01). Conclusion: The SPEED score accurately predicts the prevalence of LVAs in patients undergoing ablation for AF.