Northwestern Medicine Testing Artificial Intelligence for Heart Disease Screening

Researchers at Northwestern Medicine’s cardiovascular institute are exploring how artificial intelligence could help with more accurate cardiac screening.

The study, officials announced last week, will involve a cardiac monitoring platform from digital health company EKO, and specifically aims to demonstrate that Eko's digital stethoscopes and AI algorithms can interpret heart sounds accurately to help screen for pathologic heart murmurs and valvular heart disease. 

Officials noted that the stethoscope can be a challenging tool for healthcare providers to master, since they require “a highly trained musical ear that can separate subtle abnormalities from normal sounds with cardiologist-level precision.” As such, “while more objective cardiac screening tools, such as echocardiograms, are available in specialty clinics, the low cost and speed of the stethoscope exam makes it the standard for heart disease screening. Machine learning can combine the data from tens of thousands of heart sound patterns and provide that accuracy to physicians anywhere,” they attested.

The clinical trial will take place at the Bluhm Cardiovascular Institute—part of the Northwestern Medicine health system, with multiple sites of care in Chicago and the region—and is part of the organization’s Center for Artificial Intelligence, where Northwestern's cardiovascular clinical program works with early innovators in AI, develops new products and trains physicians in this new field.

Eko is funding the study of the AI systems at two sites, planning to enroll 1,000 patients, 800 of them at Northwestern. The company’s first FDA-cleared device, CORE, is a smart stethoscope and software used by clinicians at over 1,000 hospitals and health systems around the globe and was recognized as a "Best Invention of the Year" by TIME Magazine.

"If proven effective, Eko's platform could be a much simpler, lower cost way to identify patients with heart disease," said James Thomas, M.D. director of the Northwestern Center for Heart Valve Disease and the principal investigator for the study at Northwestern. "We are looking to support and advance work that broadens access to the best diagnostic tools in healthcare, regardless of whether a patient lives in the city or a more rural area. Deep learning provides that expert knowledge, regardless of a patient's location."

Added Patrick M. McCarthy, M.D., chief of cardiac surgery at Northwestern Memorial Hospital and executive director of the Bluhm Cardiovascular Institute, “Artificial intelligence is transitioning into clinical studies with potentially revolutionary implications for the practice of cardiovascular care.”