Diabetes is one of the world’s top causes of disease and death, affecting more than 450 million people worldwide. While technology has come a long way in helping to detect and manage diabetes, it still typically involves blood draws and clinical tools. Moreover, around half of all people with diabetes aren’t even aware that they have the disease.
Researchers at UC San Francisco have now come up with a promising method of detecting diabetes using a smartphone camera and some deep learning, utilizing the publicly available Instant Heart Rate app from Azumio to capture photoplethysmography (PPG) measurements. When a user places his or her fingertip over the phone’s flashlight and camera, the app measures PPG’s by capturing color changes in the fingertip corresponding to each heartbeat. This data is reported back to the user as the instantaneous heart rate.
While heart rate measurement might be an impressive use of a smartphone in itself, the UCSF researchers found that the heart rate data, along with heart rate variability and certain features of the PPG waveform morphology, correlate with many physiological mechanisms affected by diabetes, such as endothelial aging and microvascular atherosclerosis. So, they undertook a study as part of UCSF’s massive Health eHeart study to see if PPG could be an accurate biomarker to detect diabetes.
The researchers developed and validated a deep-learning algorithm using nearly 3 million PPG recordings from 53,870 patients. The algorithm impressively managed to correctly identify the presence of diabetes in 82% of patients with diabetes, as well as the absence of diabetes in 97% of patients without diabetes. The algorithm’s performance improved even further when combined with patient data, such as age, gender, and BMI, as well as other co-occurring comorbidities. An additional analysis even showed a correlation between the algorithm’s score and the subjects’ A1c.
While more research is needed on how to best incorporate this new digital biomarker, the results could establish PPG as a new modality in diabetes care and smartphones as an even more useful tool for our health.
Journal article in Nature: A digital biomarker of diabetes from smartphone-based vascular signals
More info: PPG Diabetes project website @ UCSF
Anupam Ghose, a physician by training, was diagnosed with Type 2 Diabetes Mellitus (T2DM) in 2017. After the diagnosis of T2DM, he followed a low carbohydrate high fat diet and reversed his T2DM within a year. Now he has one main goal in life and that is to make people understand that the conventional method of treating T2DM is not beneficial. Type 2 diabetes is reversible and the best way to reverse T2DM is through diet and lifestyle modifications. He now decided to help people with type 2 diabetes by offering online coaching to reverse their diabetes.