
This study developed a machine learning (ML) model to predict new-onset atrial fibrillation (AF) in patients with hypertrophic cardiomyopathy (HCM). The ML model, based on clinical variables, significantly outperformed the conventional HCM-AF score, achieving a higher area under the receiver-operating characteristic curve (AUC), sensitivity, and specificity. Important variables included left atrial volume, left ventricular outflow tract gradient, and exercise stress tests. This model provides a more accurate prediction of AF in HCM patients.
Like
Save
Share