November 14th, 2018
At the just concluded American Heart Association’s Scientific Sessions 2018 in Chicago, Eko, the makers of popular digital stethoscopes, showed off a neural network AI algorithm that is able to detect murmurs better than a group of cardiologists. The study, titled “Artificial Intelligence Detects Pediatric Heart Murmurs With Cardiologist-Level Accuracy,” involved teaching a computer to spot suspicious murmurs by first giving it thousands of previously diagnosed sound recordings. The computer analyzed these for unique audio signatures and found enough nuances to be able to identify murmurs in a sample auscultation.
This important, as general practice and internal family physicians routinely misdiagnose murmurs at an incredible rate. Access to cardiologists is limited, so an automated system that can help during regular screenings can go a long way. Moreover, this is an excellent sign that machine learning and other AI techniques can really help with daily medical care by bringing virtual experts in different fields to the doctor’s office.
The software can be coupled with Eko’s Core and Duo digital stethoscopes, so it only takes a regulatory approval to introduce the technology into clinical practice.
Via: Eko…