According to the company, the AI can identify heart murmurs with 87 percent sensitivity and 87 percent specificity. In comparison, primary care physicians unaided by AI had a 43 percent sensitivity and 69 percent specificity, according to a study in European Heart Journal. When used with the Eko DUO stethoscope, the AI reportedly detected AFib with 99 percent sensitivity and 97 percent specificity.

“Two centuries after its invention, the stethoscope is still the front line tool to detect cardiovascular disease,” says Dr. Patrick McCarthy, Executive Director of the Bluhm Cardiovascular Institute at Northwestern Medicine and member of Eko’s Scientific Advisory Board. “Eko’s development of artificial intelligence algorithms to help clinicians better interpret sounds, identify arrhythmias and detect heart murmurs during a physical exam is going to make a huge difference in our ability to care for patients.”

The AI is meant to be used with Eko’s digital stethoscopes, which are already on the market. This FDA clearance gives the company the greenlight to deploy its murmur- and AFib-detection algorithms. In December, the FDA granted another Eko algorithm “breakthrough status,” fast-tracking it for approval. That algorithm uses ECG data to identify Left Ventricular Ejection Fraction (LVEF), a measure commonly used to diagnose heart failure. If and when that algorithm is cleared, Eko’s digital stethoscopes will be able to use AI to screen for heart failure, valve disease and AFib, and all of that will be possible during routine physical exams.

The algorithm was introduced in a study published in Nature Medicine in January 2019. It was trained on 44,959 patients and tested on 52,870 patients. In those initial tests, it showed 87.5 percent accuracy.

The algorithm is designed to work with Eko’s DUO digital stethoscope. The handheld device can be placed on the left side of a patient’s chest and collects both heart sounds and ECG data. The device could make gathering that ECG data easier during routine exams, and in the future, it could be used in telehealth settings. Patients might use the device at home, and the data, including the algorithm’s findings, would be sent to their healthcare provider.

The “breakthrough” designation indicates that the FDA sees the algorithm as a potential solution for an unmet medical need for a life-threatening disease. It will help accelerate the FDA’s regulatory review process. Though, it’s too soon to say if or when the algorithm will receive FDA clearance. If the algorithm is sold in the future, Mayo Clinic says it will use any revenue it receives to support patient care, education and research.