Robert Avram, MD, postdoctoral fellow at UCSF Medical Center and his colleagues conducted a study on a smartphone app that tracks a person’s heart rate to detect diabetes using a photoplethysmography signal, which is easily measured using a smartphone’s light and camera. They presented this study at the American College of Cardiology Scientific Session.

The study ‘Health eHeart’ included data from nearly 55,000 participants among which 53% were men and 7% had self-reported diabetes and the mean age of the participants in the study was 45 years. Randomly the researchers split the participants into separate data sets for preparation, development, and testing. The prototype data set was used for model tuning, and model discrimination was measured using area within the test data set under the receiver-operating characteristic curves. Avram and colleagues designed and implemented a deep learning algorithm using the photoplethysmography signal recordings based on the smartphone to classify which patients had diabetes based on this signal alone.

In 72 percent of cases using photoplethysmography alone, the model correctly identified diabetes, with a negative predictive value of 97 percent, according to the findings reported here.

“While analyzing the heart rate data as collected using smartphone apps in the Health eHeart study, we noticed that patients with diabetes had, on average, a higher ‘free-living’ heart rate than patients without diabetes when adjusted for multiple factors,” Avram told Cardiology Today. In 72 percent of cases using photoplethysmography alone, the model correctly identified diabetes, with a negative predictive value of 97 percent, according to the findings reported here.

Given the positive results of this app that tracks a person’s heart rate to detect diabetes found in this research, knowledge gaps remain and some areas need further study, according to Avram.