Clinical Trials

The purpose of this study is to determine the performance of AI-ECG as a screening tool in clinical practice identifying patients with moderate or severe AS, to determine the ability of POCUS in detecting moderate or severe AS amongst in patients with positive AI-ECG.

Additionally, to identify which clinical features (presence of cardiac murmur, prevalence of hypertension, age or sex) can improve decision making process of applying echocardiography exam in patients with positive AI-ECG.

The aim of this study is to compare artificial intelligence (AI) based disease predictions across different electrocardiogram (ECG) devices. The ECG is a test that records your heart’s rhythm. The goal is to evaluate the impact of ECG device type on AI-based heart disease predictions.

The postnatal diagnosis of Long QT Syndrome (LQTS) is suggested by a prolonged QT interval on 12 lead electrocardiogram (ECG),a positive family history and/or characteristic arrhythmias and confirmed by genetic testing.  LQTS testing cannot be performed successfully before birth as   fetal ECG is not possible and direct measure of the fetal QT interval by magnetocardiography is limited. Genetic testing can be performed in utero, but there is risk to the pregnancy and the fetus. Although some fetuses present with arrhythmias easily recognized as LQTS (torsade des pointes (TdP) and/or 2° atrioventricular (AV) block, this is uncommon, occurring in <25% of fetal LQTS cases. Rather, the most common presentation of fetal LQTS is sinus bradycardia, a subtle rhythm disturbance that often is unappreciated to be abnormal. Consequently, the majority of LQTS cases are unsuspected and undiagnosed during fetal life, with dire consequences. For example, maternal medications commonly used during pregnancy can prolong the fetal QT interval and may provoke lethal fetal ventricular arrhythmias. But the most significant consequence is the missed opportunity for primary prevention of life threatening ventricular arrhythmias after birth because the infant is not suspected to have LQTS before birth. The over-arching goal of the study is to overcome the barriers to prenatal detection of LQTS. The investigators plan to do so by developing an algorithm using fetal heart rate (FHR) which will discriminate fetuses with or without LQTS. Immediate Goal: The investigators propose a multicenter pre-birth observational cohort study to develop a Fetal Heart Rate (FHR)/Gestational Age (GA) algorithm from a cohort of fetuses recruited from 13 national and international centers where one parent is known by prior genetic testing to have a mutation in one of the common LQTS genes: potassium voltage-gated channel subfamily Q member 1 (KCNQ1), potassium voltage-gated channel subfamily H member 2 (KCNH2), or sodium voltage-gated channel alpha subunit 5 (SCN5A). The investigators have chosen this population because 1) These mutations are the most common genetic causes of LQTS, and 2) Offspring will have high risk of LQTS as inheritance of these LQTS gene mutations is autosomal dominant. Thus, progeny of parents with a known mutation are at high (50%) risk of having the same parental LQTS mutation. The algorithm will be developed using FHR measured serially throughout pregnancy. All offspring will undergo postnatal genetic testing for the parental mutation as the gold standard for diagnosing the presence or absence of LQTS.

The purpose of this study is to show the artificial intelligence enhanced single-lead ECG Apple Watch has similar, robust performance comparable to an AI enhanced 12 lead ECG and AI enhanced single lead (LI) of a 12 lead ECG.

The purpose of this study is to assess the feasibility of using the current FDA-approved AliveCor Kardia device and their AliveCor Tripod device (FDA Approval pending) to measure the QT/QTc in patients presenting to the Genetic Heart Rhythm Clinic.

The purpose of this study is to assess cardiovascular health and detect unknown and asymptomatic diseases using Mayo AI-ECG algorithms.

We hypothesize that using single lead ECGs and symptoms data collected by patients using their personal Apple Watch (FDA approved for AF detection) via a Mayo Clinic app, will allow data to be shared within a dashboard in Epic, so physicians may have a way to remotely assess cardiovascular health.

The main objective of this study to assess the quality of the ECG readings between different filters from both the GE machine and the Smartheart device.