Artificial intelligence (AI) software developer Bay Labs announced that its EchoMD AutoEF deep-learning software has less variability in evaluating left ventricular ejection fraction (EF) when compared with the average variability of cardiologists, as demonstrated in a study conducted with the Minneapolis Heart Institute.
The average variability of cardiologist readers using the Simpson's biplane method in estimating EF is 9.2%, according to the literature. The observed variability of EchoMD AutoEF was 8.29%. The study, presented at the American Society of Echocardiography (ASE) 2018 meeting, also demonstrated that EchoMD AutoEF is an accurate and fully automated method of calculating EF from complete echocardiographic patient studies without user intervention. In addition to normal patients, it performed well on obese patients and on patients with a range of normal and abnormal ejection fractions.
The study included 405 echocardiographic patient studies from the Minneapolis Heart Institute representing a wide range of body mass indexes, EF values, and ultrasound systems. For each patient study, the Bay Labs' software automatically selected optimal apical four chamber and apical two chamber digital video clips and used them to perform EF calculations. These calculations were compared with the standard Simpson's biplane method.
Bay Labs EchoMD AutoEF was shown to automatically provide accurate EF calculations, according to the company.
