AI-Powered Lifestyle System Reduces HbA1C and Medication dependence in Type 2 Diabetes: Study

Secondary endpoints were:

• Maintenance of HbA1c <6.5% off medications for ≥90 days before 12 months

• Reaching HbA1c <6.5% off any glucose-lowering medications at 12 months and maintained ≥90 days

• HbA1c and weight change at 12 months

• Post hoc analyses of medication usage and quality-of-life scores.

Key Findings

Primary endpoint:

• Attained by 71.0% of INT participants (95% CI, 60.1–80.0)

• Attained by just 2.4% of UC participants (95% CI, 0.5–11.6)

• P<0.001

Glycemic target sustained ≥90 days before 12 months (except metformin):

• 52.5% in INT vs. 2.8% in UC (P<0.001)

Reduction in HbA1c at 12 months:

• INT: −1.3%

• UC: −0.3%

• P<0.001

Weight loss at 12 months:

• INT: −8.6%

• UC: −4.6%

• P<0.001

Medication use:

• Significant reduction in glucose-lowering pharmacotherapy in INT group

• No change of significance in UC group

• Quality of life and treatment satisfaction

• Mean improvement in INT group (exploratory analysis)

• No improvement in UC group

In this randomized trial of 150 adults with T2D, an AI-supported bundled system of sensors and coaching resulted in much more improved glycemic control, weight loss, and quality of life compared to standard care. Most importantly, it enabled huge de-escalation of glucose-lowering drugs, with 71% attaining HbA1c <6.5% off all medications except metformin versus 2.4% in controls. These findings demonstrate the revolutionary potential of precision medicine based on AI in type 2 diabetes treatment.

Reference: