At the American Heart Association Scientific Sessions 2019, Eko, a digital health company applying artificial intelligence (AI) and machine learning in the fight against heart disease, presented results in collaboration with Mayo Clinic demonstrating the use of the DUO digital stethoscope as a heart failure screening tool. When tested on 100 patients, the DUO combined with an AI model was able to detect ejection fraction < 35% with an area under the curve (AUC) of 0.90, which is comparable to previously published research in Nature Medicine. These findings could help identify patients with a low ejection fraction during routine physical examinations, facilitating rapid clinical recognition of those requiring further testing. This marks the first time that a point of care device with a single lead ECG combined with an AI algorithm identified low ejection fraction in patients.
Ejection fraction is an important method of mortality prediction among cardiac patients and a low ejection fraction number suggests problems with the heart’s pumping function, and may be associated with heart failure. An estimated 6.2 million Americans suffer from heart failure, according to federal statistics. The American Heart Association predicts that more than eight million will have the condition by 2030.
“With treatment many people live well with heart failure, but detection is critical,” said Dr. Steve Pham, MD and vice president of clinical research and affairs at Eko, and co-author of the study. “Eko is working to change how auscultation is done, using cutting-edge machine learning and data science to predict, and prevent, the progression of chronic cardiovascular diseases. The results presented today validate Eko’s reinvention of the 200-year-old stethoscope and further cement its place in modern healthcare practices as a tool for detection and improved treatment.”
The research was presented at the AHA event on November 16. Eko is also exhibiting at this event, booth #1001.
Eko will continue to collaborate with the Mayo Clinic to test the low ejection fraction screening algorithm, and intends to eventually submit for regulatory clearance.