The purpose of this retrospective study is to evaluate the clinical performance of SMD-AFECG, an artificial intelligence-based medical device software that predicts the risk of atrial fibrillation occurring within 2 hours using single-lead electrocardiogram data. A total of 797 eligible electrocardiogram datasets collected through VitalDB at Seoul National University Hospital will be included. The performance of SMD-AFECG will be evaluated separately for new-onset atrial fibrillation in patients without a previous history of atrial fibrillation (NOAF) and atrial fibrillation episodes in patients with a previous history of atrial fibrillation (RAF). Two physicians blinded to the software results will review the electrocardiogram data and relevant medical records to establish the reference-standard classification. The blinded electrocardiogram datasets will then be analyzed using SMD-AFECG, and the software-generated predictions will be compared with the reference standard to evaluate the area under the receiver operating characteristic curve for NOAF and RAF.