Rochester, Minn.-based Mayo Clinic entered into a collaboration with software developer Eko to create and commercialize a tool that helps physicians detect patients with low ejection fraction, a dangerous heart condition.
The tool will use machine learning — a type of artificial intelligence in which a computer learns over time, rather than having to be programmed like typical software — to analyze data from a digital “smart stethoscope.” This analysis will flag patients who suffer from low ejection fraction, or a weak heart pump, in a matter of seconds.
The machine-learning tool would streamline the screening process for patients at risk for low ejection fraction, according to Eko and Mayo Clinic. The two organizations said their method would stand in contrast to more traditional, expensive and time-consuming imaging techniques, such as echocardiography, a sonogram of the heart.
“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 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.”
Eko will work with physicians from Mayo Clinic to bring the health system’s expertise in AI and heart disease screening — along with information from its large-scale cardiovascular database — into its existing cardiac monitoring platform. Eko said it will seek FDA approval for the technology after running clinical studies with Mayo Clinic focused on the accuracy of in-clinic screenings.
Mayo Clinic and Dr. Friedman both have a financial interest in the AI tool. Mayo Clinic said it will use any revenue it receives to support its patient care, education and research mission.