Can Smartphones Detect Diabetes?

It’s almost impossible to walk anywhere these days without seeing a smartphone in nearly everyone’s hand. Smartphones are wildly popular, and their technology has advanced greatly in the last few years alone, so it makes sense to put them to good use. Researchers at UC San Francisco have done just that: they have developed a “digital biomarker” that uses a smartphone’s camera to detect diabetes. Diabetes is one of the world’s most prevalent diseases, making this is a potentially huge development. November is Diabetes Awareness Month, so let’s look at exactly how a smartphone can detect diabetes.

caucasian hand over the heart area.
People suffering from diabetes are twice as likely to die of heart disease, which is why a change is needed.

A Change Is Needed

Diabetes can lead to many other health problems. For example, those suffering from diabetes are twice as likely to die of heart disease than those who do not have diabetes. What’s worse is that half of all people with diabetes are unaware that they have it, and therefore are unaware of  the risks to their health. Finding a quicker and easier way to diagnose diabetes would make a huge difference when it comes to early detection and treatment. Finding the disease early is key: the sooner people know they have diabetes, the sooner they can begin controlling it – and possibly rid themselves of it altogether. Unfortunately, doctors have been struggling for a long time to find a better way to diagnose the disease. That is, until now.

“Diabetes can be asymptomatic for a long period of time, making it much harder to diagnose,” said Robert Avram, MD, MSc, clinical instructor in cardiology. “To date, noninvasive and widely-scalable tools to detect diabetes have been lacking, motivating us to develop this algorithm.”

Creating An Algorithm

Researchers have been studying how they can use existing smartphone technology to diagnose diabetes, and have found success with the Azumio Instant Heart Rate app. This app, using a smartphone’s camera and flashlight, can detect not only irregular heartbeats, but also changes in blood volume in a vessel, just by shining the flashlight on the user’s finger. Using this technique, known as photoplethysmography (PPG), the app can detect poor blood flow, which is common in diabetes. 

caucasian hand with the pointer finger pressing on a faded white box

To put this app to work for their study, researchers created an algorithm using nearly 3 million PPG recordings from 53,870 patients. The algorithm used was able to correctly identify the presence of diabetes in up to 81% of patients. Data also showed that the algorithm was able to accurately rule out diabetes in participants in the study around 92-97% of the time.

“We demonstrated that the algorithm’s performance is comparable to other commonly used tests, such as mammography for breast cancer or cervical cytology for cervical cancer, and its painlessness makes it attractive for repeated testing,” said study author Jeffrey Olgin, MD, a UCSF Health cardiologist, professor, and chief of the UCSF Division of Cardiology. “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.”

The Possibilities

This breakthrough opens the door to endless possibilities. If researchers can use an app to diagnose diabetes, then there is hope for using smartphones as a useful tool for our health in other ways.

“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 co-senior author Geoffrey H. Tison, MD, MPH, assistant professor in cardiology, of the Aug. 17, 2020, study in Nature Medicine. “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.”