Communications of the ACM
sing AI to Detect Heart Disease
USC Viterbi School of Engineering researchers have developed an app that measures arterial stiffness using a smartphone camera.
Credit: Ashleen Knutsen
A new method developed by researchers at USC Viterbi School of Engineering offers a better way to predict and monitor cardiovascular disease.
Using a machine learning model and a patient's pulse data, the researchers can measure arterial stiffness using just a smartphone.
The novel method uses a single, uncalibrated carotid pressure wave that can be captured with a smartphone's camera.
"That’s how you go from an $18,000 tonometry device and intrusive procedure to an iPhone app," says professor Niema Pahlevan.
To calculate key variables related to the phases of the patient’s heartbeat, the method needs only the shape of a patient's pulse wave for the mathematical model, called intrinsic frequency. Using these variables in a machine learning model can determine pulse wave velocity and, therefore, arterial stiffness.
Through validation, the team learned its method is as predictive as actual tonometry.
From USC Viterbi School of Engineering
View Full Article
Abstracts Copyright © 2018 Information Inc., Bethesda, Maryland, USA
No entries found