You’re reading the web edition of STAT’s Health Tech newsletter, our guide to how technology is transforming the life sciences. Sign up to get it delivered in your inbox every Tuesday and Thursday.
AI diabetes prevention app study shows promise
An automated app designed to deliver a diabetes prevention intervention achieved similar results to a standard human-led version of the program in a study. Diabetes prevention programs encourage lifestyle changes in people with prediabetes, and have been shown to reduce health risks of participants. However, many people do not receive the intervention for a variety of reasons.
The trial randomized half of the 368 participants to receive an app from Sweetch Health that offers prompts about weight management, physical activity, and nutrition. The app’s artificial intelligence personalizes messages to users based on information they log, for example about meals, and data collected from a wearable and digital scale. The app delivered both location- and goal-specific prompts, like encouraging a participant to pop into the gym when they are nearby. After 12 months, 31.7% of participants in this group hit the primary outcome of 5% weight loss, 4% weight loss plus 150 minutes of weekly physical activity, or a reduction in HbA1c of 0.2 percentage points. That’s nearly identical to the 31.9% who hit the primary outcome in a group that received a virtual version of the intervention that includes regular sessions with human coaches.
This article is exclusive to STAT+ subscribers
Unlock this article — plus in-depth analysis, newsletters, premium events, and news alerts.
Already have an account? Log in
