Over at the University of California, San Francisco, researchers constructed a digital biomarker functioning within a smartphone’s camera for the detection of type 2 diabetes.
The study, released in Nature Medicine, may place us one step closer toward an easier, in-home alternative to clinic-based screening tools for diabetes. The condition could be asymptomatic in some people, often becoming difficult to diagnose. A smartphone-based test could make a diagnosis quicker.
“The ability to detect a condition like diabetes that has so many severe health consequences using a painless, smartphone-based test raises so many possibilities,” said Geoffrey Tison, co-author of the study.
“The vision would be for a tool like this to assist in identifying people at higher risk of having diabetes, ultimately helping to decrease the prevalence of undiagnosed diabetes.”
In their new study, the identification of vascular damage caused by diabetes was detected and measured using a built-in smartphone camera. Close to 3 million photoplethysmography (PPH) recordings, taken from more than 50,000 participants, were assessed by researchers using a mobile application.
The data was inputted into a deep-learning algorithm to diagnose diabetes using PPG signals from smartphones.
Upon the study’s conclusion, researchers uncovered that the algorithm was able to accurately detect diabetes in more than 80 percent of patients.
“A widely accessible smartphone-based tool like this could be used to identify and encourage individuals at higher risk of having prevalent diabetes to seek medical care and obtain a low-cost confirmatory test,” said Jeffrey Olgin, another author of the study.
“The vision would be for a tool like this to assist in identifying people at higher risk of having diabetes, ultimately helping to decrease the prevalence of undiagnosed diabetes.”
