Apps & Software News

mHealth Wearables, AI Used to Detect Diabetes in One’s Heart Rate

A new study out of UCSF uses an AI platform integrated with popular mHealth wearables like the Apple Watch and Android Wear to detect diabetes in one's heart rate and step counts.

Source: ThinkStock

By Eric Wicklund

- A new study launched at the University of California in San Francisco has found that mHealth wearables integrated with an AI platform can detect early signs of diabetes.

UCSF researchers used a “deep neural network” developed by a Silicon Valley startup called Cardiogram to analyze a user’s heart rate and step counts through sensors commonly found in the Apple Watch, Android Wear and mHealth devices developed by Fitbit, Garmin and other companies. The researchers were reportedly 85 percent successful in identifying people with prediabetes.

“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,” Cardiogram co-founder Brandon Ballinger said in a press release. “By detecting diabetes earlier, we can help people live longer and healthier lives.”

The study aims to address the more than 100 million Americans now living with diabetes or trending toward that chronic condition, in particular the 25 percent of people with undiagnosed diabetes and the 88 percent of people with prediabetes who don’t realize they have it.

mHealth and telehealth advocates have long sought to use technology to identify those people and put them on a healthier path before they either develop diabetes or experience adverse health outcomes because of poor health management.

In this study, UCSF and Cardiogram researchers are looking to lay the groundwork for future mHealth wearables with more sophisticated sensors.

Cardiogram, which has worked with UCSF for several years in developing the DeepHeart platform to identify atrial fibrillation, sleep apnea and hypertension, presented the latest study during this week’s AAAi Conference on Artificial Intelligence in New Orleans.

For this study, people using the Cardiogram app on either the Apple Watch or Android Wear were invited to participate in UCSF’s Health eHeart study, which aims to collect heart health data from 1 million people. Researchers used data collected from those wearables to “train” Cardiogram’s AI platform to differentiate between people with diabetes and those without the chronic condition.

“Your heart is connected with your pancreas via the autonomic nervous system,” Cardiogram co-founder Johnson Hsieh pointed out in the release. “As people develop the early stages of diabetes, their pattern of heart rate variability shifts.”

“In 2015, the Framingham Heart Study showed that high resting heart rate and low heart rate variability predicts who will develop diabetes over a 12-year period,” he added. “In 2005, the ARIC study showed that heart rate variability declines faster in diabetics than non-diabetics over a 9-year period.”

Researchers conducted the study in several phases, in some cases pre-programming the neural network to identify certain signs and in other cases allowing the AI platform to develop its own protocols.

While the app isn’t designed to diagnose prediabetes or diabetes, it would alert a user to check in with his or her healthcare provider.

"Most people don't go to the doctor’s office as much as they should," Ballinger told Wareable. "So the future this promises is that if you're wearing an Apple Watch, Android Wear, Garmin, something with a heart rate sensor, and your heart rate variability starts to decline because you're getting diabetes, you may get a notification or an offer to get a blood test."

Do Not Sell or Share My Personal Information
©2012-2024 TechTarget, Inc. Xtelligent Healthcare Media is a division of TechTarget. All rights reserved. HealthITAnalytics.com is published by Xtelligent Healthcare Media a division of TechTarget.