Bundy JD, Heckbert SR, Chen LY, et al. - Given the prevalence and strong association of atrial fibrillation (AF) with higher cardiovascular disease (CVD) risk, researchers examined how the addition of novel candidate variables identified by machine learning to the CHARGE-AF Enriched score, which includes age, race/ethnicity, height, weight, systolic and diastolic blood pressure, current smoking, use of antihypertensive medication, diabetes, and NT-proBNP, influences the prediction of 5-year AF risk. From the prospective MESA, they identified 3,534 participants (mean age, 61.3 years; 52.0% female) with complete data; of these, 124 participants had incident AF within 5 years of baseline. The prediction did not improve significantly using variables identified by machine learning, including biomarkers, cardiac MRI variables, electrocardiogram variables, and subclinical CVD variables, when compared with the CHARGE-AF Enriched model (c-statistic, 0.804). This analysis establishes that the performance of CHARGE-AF Enriched model and a parsimonious 6-item model was comparable to a more extensive model derived by machine learning. Findings thereby support these simple models as the gold standard for risk prediction of AF, although they recommend considering the addition of the coronary artery calcium score.