Communications of the ACM
'face Time' For the Heart Diagnoses Cardiac Disease
Researchers at the University of Rochester have developed software that can show whether someone is experiencing atrial fibrillation, based on subtle changes in skin color.
Credit: C. Bickel/Science Translational Medicine
University of Rochester (UR) researchers have developed software that show whether or not an individual is experiencing atrial fibrillation. The pilot project, which also relies on a Web camera, demonstrates that subtle changes in skin color can be used to detect the uneven blood flow caused by atrial fibrillation.
"This technology holds the potential to identify and diagnosis cardiac disease using contactless video monitoring," says UR researcher Jean-Phillippe Courderc.
The software scans the face and can detect changes in skin color that are imperceptible to the naked eye. Hemoglobin absorbs more of the green spectrum of light and this change can be spotted by the camera's sensor. The researchers note the face is the best place to detect this phenomenon because the skin is thinner than other parts of the body and blood vessels are closer to the surface. They found the color changes detected by the system correspond with an individual's heart rate as detected by an electrocardiogram (ECG). The video-monitoring technique has an error rate of 20 percent, compared to the 17 to 29 percent error rate associated with automated ECG measurements.
"This study was intended to be a proof of concept and, as is the case with many new technologies, we believe that we can significantly improve its accuracy and the usability," Courderc says.
From University of Rochester Medical Center
View Full Article
Abstracts Copyright © 2014 Information Inc., Bethesda, Maryland, USA
No entries found