Attia ZI, Noseworthy PA, Lopez-Jimenez F, et al. - Researchers intended to create a quick, low-cost, point-of-care means of recognizing individuals with atrial fibrillation using machine learning. Using standard 10-second, 12-lead ECGs, an artificial intelligence (AI)-enabled ECG via a convolutional neural network to detect the electrocardiographic signature of atrial fibrillation seen during normal sinus rhythm was made. A total of 180,922 individuals, 649,931 with ECG-confirmed normal sinus rhythm, who were aged 18 years or older with at least one digital, normal sinus rhythm, standard 10-second, 12-lead ECG obtained in the supine position at the Mayo Clinic ECG laboratory between December 31, 1993 and July 21, 2017 with rhythm labels verified by trained personnel under cardiologist supervision were recruited in the study. In the testing dataset, a total of 3,051 individuals had confirmed atrial fibrillation prior to the normal sinus rhythm ECG tested by the model. With an AUC of 0.87, the sensitivity of 79.0%, the specificity of 79.5%, F1 score of 39.2%, and overall accuracy of 79.4%, a single AI-enabled ECG determined atrial fibrillation. Including all ECGs obtained during the first month of each individual's window of interest (ie, the study start date or 31 days prior to the first recorded atrial fibrillation ECG) raised the AUC to 0.90, sensitivity to 82.3%, specificity to 83.4%, F1 score to 45.4%, and overall exactitude to 83.3%. In conclusion, an AI-enabled ECG obtained during normal sinus rhythm granted the determination at the point of care of individuals with atrial fibrillation.