The app uses logged food to predict a user’s blood glucose response. This app makes recommendations to users throughout the entire day. For example, it may suggest adjusting your portion sizes, trying a new combination of foods, or walking after meals. 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. Over time, the app adapts to users’ preferences using AI. The app allows users to chat with human health coaches for specific questions.
Buckley credits Twin Health with helping him to make better choices. For example, he swapped pre-packaged, frozen breakfast sandwich for homemade breakfast wraps made from low-carbohydrate and high-fiber wraps. He does not drink soda anymore and walks several miles each 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.
The app allows him to track his biometrics and receive instant feedback. He is able to see his blood pressure and body fat percentage are trending down.
“That’s where I get my motivation to keep walking and keep doing the work,” He says.
Buckley is around 275 pounds now, having reached his weight goal. His doctor suggested that he take a smaller dose of blood pressure medicine after being prescribed it for many years.
Kevin Pantalone, a staff endocrinologist with the Cleveland Clinic Health Plan, initially reacted skeptically when Twin Health proposed using their program. He conducted a research study on his own.
“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.” The majority of Americans have trouble adhering to healthy eating and exercising despite being told to do so by their parents.
Pantalone, his co-workers and 150 people with type 2 diabetics were recruited. 100 participants randomly assigned to Twin and the other half to control groups. The average age of the participants was 58, with an obesity rate and a blood sugar level (A1C) of 7.2 per cent. The level of diabetes is 6.5 or more percent. The trial’s goal was to test whether participants could achieve an A1C below 6.5 percent by using less medication.
In 12 months, the Twin app helped 71 percent achieve the same blood glucose level as the people in control, but only 2 percent did so. The people using Twin also lost more weight—8.6 percent of their body weight versus 4.6 percent in the control group.
Only 6 percent of Twin users were still taking GLP-1 medications at the end of this study. At the beginning of the trial, only 6 percent of those in the Twin group were on GLP-1 medication. By the end, this number increased to over 63 percent. Results were published Last year, the New England Journal of Medicine Catalyst published a review of this study.

