The solution is claimed to be the first and only machine-learning algorithm to help healthcare professionals in detecting structural heart murmurs using a smart stethoscope
Eko receives FDA clearance for its EMAS. (Credit: PRNewswire/ Eko)
Eko has received the US Food and Drug Administration (FDA) approval for its Eko Murmur Analysis Software (EMAS) for the detection and characterisation of heart murmurs found in adults and paediatric patients.
EMAS is a cloud-based machine-learning algorithm that evaluates heart sounds, phonocardiogram and ECG signals collected by leveraging the company’s smart stethoscopes.
The solution uses several methods to decode the captured signals, including signal processing and convolutional neural networks.
It is claimed to be the first and only machine-learning algorithm to help healthcare professionals in detecting structural heart murmurs using a smart stethoscope.
By combining murmur analysis AI with its digital stethoscopes, the firm has converted the conventional stethoscope into an objective, affordable, and scalable screening tool that can detect major structural heart disease in seconds on the front lines of treatment.
Eko co-founder and CEO Connor Landgraf said: “This latest FDA clearance is another way in which Eko is improving access to better heart health through clinically-validated algorithms and best-in-class medical devices.
“By making heart disease screening algorithms and digital stethoscopes accessible in exam rooms around the country, we are moving towards a future in which more objective and consistent valvular heart disease screening can become the standard of care.”
With an overall sensitivity of 85.6% and a specificity of 84.4%, the EMAS algorithm enhances the ability of healthcare practitioners to reliably and effectively diagnose valvular heart disease.
Further investigation revealed that EMAS algorithm detected structural murmurs in people 18 years and older with a sensitivity of 90.2% and specificity of 90.6%.
The firm said that using conventional stethoscopes, general practitioners were shown to have a sensitivity of 44% and a specificity of 69% for detecting serious valvular heart disease.