AF, a common cause of stroke, affects millions of people and can be challenging to diagnose. This clearance solidifies Tempus’ innovative approach to offering clinicians AI-based clinical solutions that support the potential for earlier identification of cardiovascular disease and conditions. ECG-AF is the first of a suite of next generation diagnostics that Tempus has designed to identify patients at risk for a variety of cardiovascular conditions.

Read the full press release here.

See our Research in ECG based Cardiology Algorithms:

• • rECHOmmend: An ECG-based machine learning approach for identifying patients at increased risk of undiagnosed structural heart disease detectable by Echocardiography: In this study, we developed a novel ECG-based machine learning approach to predict multiple structural heart conditions, hypothesizing that a composite model would yield higher prevalence and positive predictive values to facilitate meaningful recommendations for echocardiography.

  • Deep neural networks can predict new-onset Atrial Fibrillation from the 12-lead ECG and help identify those at risk of Atrial Fibrillation-related stroke (link): Atrial fibrillation (AF) is associated with substantial morbidity, especially when it goes undetected. If new-onset AF can be predicted, targeted screening could possibly be used to find it early. In this study, we explore if a deep neural network can predict new-onset AF from the resting 12-lead ECG and study whether this prediction may help identify those at risk of AF-related stroke.

  • Prospective evidence generation via ECG-AID Study: We have launched a multi-site prospective study with our beta partners to test our algorithms for atrial fibrillation and structural heart disease.

  • Prediction of mortality from 12-lead electrocardiogram voltage data using a deep neural network: We hypothesized that a deep neural network (DNN) can predict an important future clinical event, 1-year all-cause mortality, from ECG voltage-time traces. In this study we used ECGs collected over a 34-year period in a large regional health system, to train a deep neural network with 1,169,662 12-lead resting ECGs obtained from 253,397 patients, in which 99,371 events occurred.

Our Experts
Brandon Fornwalt, MD, PhD Senior Vice President of Cardiology, Tempus	John Pfeifer, MD, MPH Vice President of Clinical Cardiology, Tempus