AI-Enabled Bundle of Sensors, Coaching Aids Type 2 Diabetes Outcomes

THURSDAY, Aug. 28, 2025 (HealthDay News) — An artificial intelligence (AI)-enabled bundled system of sensors and coaching facilitates significant improvements in glycemic outcomes and de-escalation of glucose-lowering pharmacotherapy, according to a study published online Aug. 20 in NEJM Catalyst.

Kevin M. Pantalone, D.O., from the Cleveland Clinic, and colleagues assessed whether or not the Twin Precision Treatment AI-enabled bundled system of sensors and coaching system could help individuals — with type 2 diabetes and managed in a primary care setting — to achieve glycemic targets while concurrently de-escalating glucose-lowering medications. The analysis included 150 adults with type 2 diabetes and a body mass index ≥27 assigned to the bundled intervention system (100 individuals) or usual care (50 individuals).

The researchers found that the primary end point (hemoglobin A1c [HbA1c] <6.5 percent without glucose-lowering medications, except metformin, at 12 months) was achieved by 71.0 percent of intervention participants versus 2.4 percent of usual care participants. Additionally, significantly more intervention participants achieved or sustained the target ≥90 days prior to 12 months without glucose-lowering medications, except metformin (52.5 versus 2.8 percent). Mean changes in HbA1c levels (−1.3 versus −0.3 percent) and body weight (−8.6 versus −4.6 percent) were significantly greater with the intervention versus usual care. In a post hoc analysis, overall use of glucose-lowering pharmacotherapy decreased substantially with the intervention, but not usual care. The intervention group also showed significant improvement in quality-of-life and treatment satisfaction scores in exploratory analyses.

“By leveraging personalized lifestyle modifications to understand each patient’s unique metabolic profile, the tool enabled individuals to make impactful lifestyle choices,” Pantalone said in a statement.

Several authors disclosed ties to the pharmaceutical industry.

Abstract/Full Text (subscription or payment may be required)