AI-powered digital twins help people manage diabetes and obesity

Based on recorded meals, the app predicts a person’s blood sugar response to those foods. It also provides personalized recommendations throughout the day, such as adjusting portion size, choosing a different food group, or taking a walk after eating. Users can accept or ignore these suggestions – maybe broccoli isn’t their favorite food, or they prefer to exercise during a certain time of the day. The app uses artificial intelligence to adapt to their preferences over time. Users can also chat with human trainers if they have specific health questions.

For Buckley, Twin Health has helped him make healthier choices, like swapping pre-packaged frozen breakfast sandwiches for homemade breakfast burritos with low-carb, high-fiber wraps. He no longer drinks soda, and walks several miles a day.

“When I first started the program, I could barely get a mile before my back hurt, and my knees hurt,” he says. “Now I walk six and a half miles every morning.”

He likes getting instant feedback from the app and also tracking his biometrics over time. He can see that his body fat percentage and blood pressure are trending downward.

“This is where I get my motivation to keep walking and keep doing the work,” he says.

Buckley reached his initial goal of 300 pounds, and now weighs about 275 pounds. After taking blood pressure medications for decades, his doctor recently suggested a lower dose.

When Twin Health approached Cleveland Clinic Health Plan about using its software, endocrinologist Kevin Pantalone was initially skeptical. He decided to conduct the study himself.

“We have really struggled to implement lifestyle modification in a very effective way,” he said. “Patients often need multiple treatments to control their diabetes.” “So I was definitely very interested.” Despite the age-old advice to exercise more and eat healthier, most Americans struggle to get the recommended amount of weekly physical activity and have difficulty sticking to a healthy diet.

Pantalone and colleagues recruited 150 participants with type 2 diabetes, with 100 randomly assigned to the Twin program and the rest to a control group. On average, participants were 58 years old and obese and had a blood sugar level, or A1C, of ​​7.2%. A level of 6.5 percent or higher indicates diabetes. The goal of the trial was to see if participants could reach an A1C level below 6.5 percent using fewer medications.

After 12 months, 71% of study participants who used the Twin app achieved their blood sugar level using fewer medications, while only 2% of people in the control group did so. People using Twin also lost more weight — 8.6 percent of their body weight versus 4.6 percent in the control group.

At the start of the study, 41% of those using Twin were taking GLP-1, but by the end of the study, only 6% were still using it. In the control group, 52% of participants started using GLP-1, and by the end of the study that number had risen to 63%. The results were published in the New England Journal of Medicine Catalyst last year.