AI Digital Twins Are Helping People Manage Diabetes and Obesity

Based on logged meals, the app predicts a person’s blood sugar response to those foods. It also makes personalized recommendations throughout the day, such as adjusting portion size, choosing a different food combination, 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 particular time of the day. The app uses AI to adapt to their preferences over time. Users can also chat with human coaches if they have specific health questions.

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

“When I first started the program, I could barely make it a mile before my back was hurting, my knee was hurting. Now I’m doing six and a half miles every morning,” he says.

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 have been trending downward.

“That’s where I get my motivation to keep walking and keep doing the work,” he says.

Buckley reached his initial weight goal of 300 pounds and is now around 275. After being on blood pressure medication for decades, his doctor recently suggested a lower dose.

When Twin Health approached the Cleveland Clinic’s health plan about using its program, staff endocrinologist Kevin Pantalone was initially skeptical. He decided to conduct a study himself.

“We have really struggled to implement lifestyle modification in a very effective manner. Patients often require numerous therapies to control their diabetes,” he said. “So I was certainly very interested.” Despite the age-old advice of simply exercising more and eating healthy, most Americans struggle to get the recommended amount of weekly physical activity and have difficulty sticking to a healthy diet.

Pantalone and his colleagues recruited 150 participants with type 2 diabetes, randomly assigning 100 people to the Twin program and the rest to a control group. On average, participants were 58 years old with obesity and had a blood glucose level, or A1C, of 7.2 percent. A level of 6.5 percent or higher indicates diabetes. The goal of the trial was to see if participants could reach an A1C of less than 6.5 percent with fewer medications.

After 12 months, 71 percent of the study participants using the Twin app achieved that blood sugar level with fewer medications, whereas only 2 percent of people in the control group did. The people using Twin also lost more weight—8.6 percent of their body weight versus 4.6 percent in the control group.

At the beginning of the study, 41 percent of those using Twin were on a GLP-1 medication, but by the end of the study, only 6 percent still were. In the control group, 52 percent of participants started off on a GLP-1, and at the end of the study that increased to 63 percent. The results were published in the New England Journal of Medicine Catalyst last year.