Smartphone App Uses Picture of Fingertip to Detect Diabetes
Screening technology uses a phone’s camera and flashlight to identify poor blood flow.
A popular smartphone app that monitors heart rate may also help diagnose diabetes, based on a recent study that successfully identified adults with diabetes using their phone’s camera and flashlight. The study correctly identified people who had diabetes in up to 81% of users. According to experts, this technology could be used in combination with existing screening tools.
Presented at the American College of Cardiology’s 68th Annual Scientific Session, this study tested a new use for the Azumio Instant Heart Rate smartphone app. The app is already one of the most widely downloaded and used smartphone apps for heart health. It uses the phone’s built-in camera to monitor heart rate with a visual assessment of blood vessels in the fingertip.
In the recent study, researchers tested whether the same technology can also detect diabetes, which affects an estimated 1 in 10 U.S. adults. The study included 54,269 individuals who downloaded the Azumio app and opted to join the online Health eHeart Study.
Participants were 45 years of age on average; 53 percent were male and 7 percent had self-reported diabetes.
Using a new algorithm developed for this study, researchers used their existing camera technology to correctly identify diabetes in 72% of participants. The test also was 97% accurate in ruling out users without diabetes.
When combining the algorithm above with self-reported risk factors for diabetes like age, gender and weight, the ability to identify users with diabetes jumped to 81%. According to authors, the accuracy of this tool is similar to many traditional tools used in clinics to predict diabetes.
So how does the app actually work? As experts explain, changes in blood volume that happen with every heartbeat can be captured by shining a flashlight on a fingertip. Using the smartphone’s camera and flashlight, the app monitors changes for a short period of time and estimates the change of blood volume in a vessel. Similar to how it uses the technology to spot abnormal heart rhythms, it can also identify poor blood flow that is common with diabetes.
Findings are extremely encouraging, as 84 million U.S. adults have prediabetes and 1 in 3 adults with diabetes does not know they have it. According to authors, this app could more easily screen adults for diabetes than existing tools.
“Diabetes can be asymptomatic for a long period of time, yet adverse vascular changes still occur silently, which can lead to cardiovascular complications,” said Robert Avram, MD, post-doctoral fellow at UCSF Medical Center and the study’s lead author. “This makes it especially important for us to examine low-cost, noninvasive opportunities that make it easy to screen millions of people. To date, a noninvasive, widely-scalable screening tool for diabetes has been lacking. Based on our findings, this strategy could become a low-cost way to screen for diabetes at home because it can be derived from any optical system that has a camera and a flashlight, and most people have a smartphone.”
Currently available screening tools, such as glycated hemoglobin or fasting plasma glucose, require a blood draw and an in-person clinic visit. But many Americans either don’t have easy access to a clinician, simply don’t go or can't afford it. In addition, millions of people living with diabetes are undiagnosed, leaving them vulnerable to worsening outcomes and other health conditions such as heart attack, heart failure and stroke.
“The potential to transition screening that’s normally done by physicians or nurses to the patient themselves through a smartphone app is a very novel concept and gives us a glimpse into how health care might work in the future,” he said. “We are hopeful this technology will assist with early diabetes detection. A positive screening test would still require a physician to confirm the diabetes diagnosis and establish appropriate treatment.”
Given the study’s findings, Avram and his team are currently testing the app’s new use across two heart clinics to confirm its accuracy. Authors also plan to see how this technology performs in detecting whether someone has early or late stage diabetes and to validate it in different populations, such as African-Americans or Asians, that are underrepresented in this study but face increased risk for diabetes. Researchers said once the model is validated in these populations, it will be available to consumers via a smartphone application, likely within the next two years.