Aim: The study aims to compare the ability of CHA(2)DS(2)-VASc (defined as congestive heart failure, hypertension, age >= 75 years [two scores], type 2 diabetes mellitus, previous stroke, transient ischemic attack, or thromboembolism [TE] [doubled], vascular disease, age 65-74 years, and sex category) and CHADS(2) (defined as congestive heart failure, hypertension, age >= 75 years, type 2 diabetes mellitus, previous stroke [doubled]) scores to predict the risk of ischemic stroke (IS) or TE among patients with nonvalvular atrial fibrillation (NVAF). Methods: A total of 413 patients with NVAF aged >= 65 years, and not on oral anticoagulants for the previous 6 months, were enrolled in the study. The predictive value of the CHA(2)DS(2)-VASc and CHADS(2) scores for IS/TE events was evaluated by the Kaplan-Meier method. Results: During a follow-up period of 1.99 +/- 1.29 years, 104 (25.2%) patients died and 59 (14.3%) patients developed IS/TE. The CHADS(2) score performed better than the CHA(2)DS(2)-VASc score in predicting IS/TE as assessed by c-indexes (0.647 vs 0.615, respectively; P<0.05). Non-CHADS(2) risk factors, such as vascular disease and female sex, were not found to be predictive of IS/TE (hazard ratio 1.518, 95% CI: 0.832-2.771; hazard ratio 1.067, 95% CI: 0.599-1.899, respectively). No differences in event rates were found in patients with the CHADS2 scores of 1 and 2 (7.1% vs 7.8%). It was observed that patients with a CHADS(2) score of >= 3 were most in need of anticoagulation therapy. Conclusion: In patients with NVAF aged >= 65 years, the CHADS(2) score was found to be significantly better in predicting IS/TE events when compared to the CHA(2)DS(2)-VASc score. Patients with a CHADS(2) score of >= 3 were associated with high risk of IS/TE events.