An Integrated Digital Health Care Platform for Diabetes Management With AI-Based Dietary Management: 48-Week Results From a Randomized Controlled Trial

OBJECTIVE We investigated the efficacy of an integrated digital health care platform with artificial intelligence (AI)–based dietary management in adults with type 2 diabetes (T2D). RESEARCH DESIGN AND METHODS In this 48-week, open-label, randomized, multicenter clinical trial, overweight or obese adults with T2D were randomly assigned to one of three groups in a 1:1:1 ratio: group A received routine diabetes care; group B used the digital integrated health care platform by themselves; and group C used the platform with feedback from medical staff and intermittently applied personal continuous glucose monitoring. The primary end point was the difference of change in HbA_1c from baseline to 24 weeks between groups A and B, while secondary end points included changes in HbA_1c from baseline to 48 weeks and changes in body weight during follow-up. RESULTS A total of 294 participants were randomly assigned to group A (n = 99), B (n = 97), or C (n = 98). The decreases in HbA_1c from baseline to 24 and 48 weeks in group B (20.32 ± 0.58% to 24 weeks and 20.28 ± 0.56% to 48 weeks) and group C (20.49 ± 0.57% to 24 weeks and 20.44 ± 0.62% to 48 weeks) were significantly larger than those in group A (20.06 ± 0.61% to 24 weeks and 0.07 ± 0.78% to 48 weeks). Groups B and C exhibited greater weight loss than group A from baseline to 24 weeks, and group C demonstrated more weight loss than group A from baseline to week 48. CONCLUSIONS Among adults with T2D, use of an integrated digital health care platform with AIdriven dietary management resulted in better glycemia and more weight loss.