Mayo, Eko team on machine learning to detect heart abnormalities
The Mayo Clinic and health technology vendor Eko are working together to develop and commercialize a machine learning-based algorithm that screens patients for low ejection fraction, which is linked to heart failure.
A low ejection fraction number, often measured by an echocardiogram, suggests problems with the heart’s pumping function. However, echocardiography is an expensive and time-consuming medical imaging test using ultrasound that is less accessible than a doctor with a stethoscope.
“With this collaboration, we hope to transform the stethoscope in the pocket of every physician and nurse from a hand tool to a power tool,” said Paul Friedman, MD, chair of cardiovascular medicine at the Mayo Clinic. “The community practitioner performing high school sports physicals and the surgeon about to operate may be able to seamlessly tap the knowledge of an experienced cardiologist to determine if a weak heart pump is present simply by putting a stethoscope on a person’s chest for a few seconds.”
By leveraging Mayo’s machine-learning algorithm and cardiovascular database—which contains millions of ECGs and healthcare screenings—as well as Eko’s smart stethoscope and software platform, the organizations hope to ultimately help physicians detect heart function abnormalities earlier and in patients who might not otherwise be screened for potentially dangerous heart diseases.
“It’s the perfect partnership, given our technology and software platform and some of the data that Mayo Clinic has collected,” says Connor Landgraf, CEO of Eko. “The algorithm was developed by the Mayo Clinic, and we’re working with them to commercialize it with our products.”
Friedman and the Mayo Clinic have financial interests in the technology. Revenue from commercialization of the product will be used to support Mayo’s not-for-profit mission in patient care, education and research, according to the healthcare organization.
Based on clinical studies with Mayo Clinic, the goal is for Eko to secure Food and Drug Administration approval for the technology by demonstrating the safety and effectiveness of the algorithms for in-clinic screening.
“There’s still quite a bit of work left to do before we can get this to the point where it can be cleared by the FDA,” comments Landgraf.
Last year, Eko received FDA clearance to market DUO, which combines ECG and digital stethoscope technology into a handheld device. Under the collaboration with Mayo, the machine-learning algorithm is being combined with DUO to automatically alert patients and their care teams of suspected decline in cardiac function.
“DUO is the perfect sensor platform for us to be able to connect in this algorithm,” adds Landgraf, who notes that 20 percent to 30 percent of patients with cardiovascular disease are not detected early enough, and heart failure costs the country more than $30 billion each year.