SAN FRANCISCO – Researchers at the University of California San Francisco have found that mHealth wearables integrated with digital health startup Cardiogram’s DeepHeart app can detect diabetes and other medical conditions.
“By detecting diabetes earlier, we can help people live longer and healthier lives,” said Brandon Ballinger, co-founder of Cardiogram, in a statement.
In a collaboration between UCSF’s Health eHeart Study and Cardiogram, researchers recruited more than 14,000 users of Cardiogram for Apple Watch and Android Wear for the study. Health sensor data was used to train a deep neural network, which uses machine learning to analyze large sets of data, by presenting it with samples from people with and without diabetes, hypertension, sleep apnea, atrial fibrillation and high cholesterol.
The study found that the app was 85% accurate in distinguishing between people with and without diabetes. It was also able to detect high blood pressure with 80% accuracy and sleep apnea with 83% accuracy.
“While there have been many attempts to build special-purpose glucose-sensing hardware to detect diabetes, this is the first large-scale study showing that ordinary heart rate sensors—when paired with an artificial intelligence-based algorithm—can identify early signs of diabetes,” said Ballinger. More than a quarter of a million people use Cardiogram actively, and 73% of them open the app on a daily basis, he said.
“While these research results are promising, ultimately, Cardiogram’s goal is to save lives in the real world,” said Ballinger.