Mayo Clinic study uses AI to detect heart rhythm disorder

An artificial intelligence algorithm is able to identify patients with congenital Long QT syndrome using limited electrocardiogram data, according to an abstract published May 10 at the Heart Rhythm Scientific Sessions conference in Boston. LQTS is a heart rhythm disorder that, if left untreated, puts patients at an increased risk for arrhythmias and sudden cardiac death. For the study, a team of researchers from Rochester, Minn.-based Mayo Clinic and AliveCor sought to determine whether AI could identify patients with congenital LQTS despite patients having a normal QTc on their EKG. The researchers applied an AI algorithm that used deep neural networks to patient data from lead I of a 12-lead EKG and evaluated whether the algorithm was able to distinguish between patients with concealed LQTS and those without the condition. The researchers found the deep neural network achieved 79 percent accuracy, along with specificity of 81 percent and sensitivity of 73 percent.