The U.S. Food and Drug Administration (FDA) has approved the first artificial intelligence algorithm to detect heart valve disease using a digital stethoscope. The registry writes about it.

Developed by American startup Eko, EMAS software is designed to analyze patients’ pulses and help healthcare professionals detect heart murmurs.

The data is transferred to the cloud, where the system determines in seconds what type of heart disease the patient may have. EMAS then produces the result in JSON format, which is transmitted to the application and displayed in human-readable format.

“The software uses machine learning-based algorithms along with signal processing such as filtering to analyze the information received and generate output for clinicians to support clinical decisions,” the company said.

The developers evaluated the performance of the algorithm against two criteria typical for cardiology: sensitivity and specificity. According to the first parameter, the diagnostic accuracy was 85.6% – 84.4% relative to the second. For comparison, GPs for the same criteria showed a result of 44% and 69%, respectively.

“Cariologists often detect murmurs with greater accuracy than general practitioners, but most patients are seen in primary care,” the company said.

Eco spokespersons described the FDA approval as an important step on the product’s “path to commercialization.”

Recall that in April, the manufacturer of the independent AI X-ray analyzer Oxipit announced its intention to submit an application to the FDA for certification of the device.

In March 2021, the regulator approved the first AI device to diagnose COVID-19.