Artificial Intelligence Enhances EKG Testing for Heart Condition

Using artificial intelligence, EKGs may soon be able to screen for hypertrophic cardiomyopathy, an underdiagnosed condition that interferes with the heart’s ability to function properly. With hypertrophic cardiomyopathy, the heart’s walls thicken and make it harder for the heart to pump blood. The disease also predisposes some patients to potentially fatal abnormal rhythms. Hypertrophic cardiomyopathy often doesn’t cause symptoms, and patients are often unaware they have it until they experience complications. The condition is the leading cause of death in adolescents and young adults playing sports, so early detection is critical. Researchers at the Mayo Clinic developed an AI method for earlier diagnosis of hypertrophic cardiomyopathy through an EKG. The team trained and validated a convolutional neural network using digital 12-lead EKG from 2,448 patients known to have hypertrophic cardiomyopathy and 51,153 who did not, matching control subjects for age and sex.