FDA paves way for AI stethoscope to detect heart disease • The Register

The US Food and Drug Administration has approved the first artificial intelligence algorithm that powers a digital stethoscope so doctors can detect heart valve disease more accurately.

Valvular heart disease occurs when the heart valves do not function properly, affecting the pumping of blood to the body and ingested into the chambers of the heart as the valves do not open or close properly.

About 2.5 percent of the U.S. population has heart valve disease, and tens of thousands die each year from complications such as heart failure or cardiac arrest, according to the Centers for Disease Control and Prevention.

It can be difficult to detect heart valve disease. It requires doctors to listen to a patient’s heartbeat and be able to recognize an unusual sound or pattern and find out which valve is weakened and what problem it is causing. Recognizing whether the sound and pattern of a heartbeat is irregular can be subjective, and this means that the condition is often misdiagnosed or completely overlooked.

Here is where AI algorithms can come in handy. Eko, a digital healthcare startup based in Oakland, California, has developed software to analyze a patient’s heart rate and help healthcare professionals detect heart murmurs. Its Eco Murmur Analysis Software (EMAS) is the first of its kind to receive FDA approval.

Heart rate data collected by physicians using Eco’s smart stethoscopes are analyzed by EMAS. EMAS characterizes heart failure to detect and better understand what type of heart valve disease a patient may have in seconds, we are told.

“EMAS is a cloud-based service that allows users to upload heart sounds and optional electrocardiogram data via an application programming interface for analysis,” a company spokesman said. The register. “The software uses signal processing, such as waveform filtering, as well as machine learning algorithms, to analyze the data obtained and generate clinical decision support for clinicians.

“The EMAS algorithm analyzes the heart sound data and outputs a JSON file with the algorithm results, which is passed to the requesting application and displayed by the requesting application to the user in the human readable format.”

Eko claims that their EMAS tool has an overall sensitivity and specificity – two measures of how accurately it can identify the disease – of 85.6 percent and 84.4 percent, respectively. By comparison, similar tests performed with general practitioners using traditional stethoscopes to detect heart valve disease reportedly had a sensitivity and specificity of 44 percent and 69 percent, respectively.

“It takes specialist clinicians many years to master the art of hearing and interpreting heart sounds, and there is still great variation. Experts such as cardiologists tend to detect sounds with higher accuracy than primary care physicians, but most patients are seen in primary care. Care practice. Patients only , who is suspected or known to have a heart disease, is referred to a cardiologist, “the Eco-spokesman told us.

FDA approval means that Eko can market its EMAS algorithm in the US and start selling its technology to the healthcare industry. “FDA approval is an important step toward commercialization. We are seeking to partner with U.S. healthcare institutions that want to be among the early users of this new solution for increased detection of heart valve disease.” ®

Leave a Comment