University of Washington researchers have evaluated a new system that they believe could enable people to self-screen for prediabetes using any smartphone.
The research, published last week in the Proceedings of the Association for Computing Machinery on Interactive, Mobile, Wearable and Ubiquitous Technologies, was funded in part by the Bill & Melinda Gates Foundation.
The Centers for Disease Control and Prevention (CDC) estimates that 33% of U.S. adults have prediabetes, a condition marked by elevated blood sugar levels. Early detection can reverse prediabetes through lifestyle changes including improved diet and exercise. However, eight out of 10 Americans with prediabetes don’t know they have it, putting them at risk of type 2 diabetes, as well as heart disease, kidney failure, and vision loss.
Current screening methods involve laboratory testing at health care facilities and/or the use of portable glucometers for at-home testing.
The researchers sought a less costly, more accessible screening method. They developed GlucoScreen -- a system that leverages any smartphone’s touch sensing capabilities to measure blood glucose levels. The modified commercially available test strip uses photodiodes to draw power from the phone's flash, and the GlucoScreen app walks users through the testing process.
Users first affix each end of a test strip to the front and back of the phone. Next, they prick their finger with a lancet, as in a conventional test, and apply a drop of blood to the test strip’s biosensor. The test strip samples the amplitude of the electrochemical reaction that occurs when the blood mixes with enzymes.
Data generated by that reaction are communicated to the smartphone through simulated tapping on the screen, as a human might do, in patterns comparable to Morse code. The app then applies machine learning to analyze the data and calculate a blood glucose reading, which is displayed on the phone with a link to interpret the result.
The researchers evaluated GlucoScreen in a clinical study involving 75 participants already scheduled to have blood drawn for a glucose test. The team found the system accurate at the crucial threshold between normal blood glucose levels below 99 mg/dL and prediabetes levels between 100 and 125 mg/dL. They found GlucoScreen comparable in accuracy to standard glucometer testing.
GlucoScreen is currently in the prototype stage, awaiting further study before it can become commercially available. However, given the prevalence of prediabetes and diabetes, researchers believe that this technology demonstrates the smartphone’s potential as a health screening tool that can improve clinical care.
"One of the barriers I see in my clinical practice is that many patients can't afford to test themselves, as glucometers and their test strips are too expensive. And it's usually the people who most need their glucose tested who face the biggest barriers," Dr. Matthew Thompson, co-author and a University of Washington professor, said in a statement. "A system like GlucoScreen could really transform our ability to screen and monitor people with prediabetes and even diabetes."
