JAMA Netw Open

AI-assisted insulin titration improves glycemic control in type 2 diabetes

May 8, 2025

An artificial intelligence-based insulin clinical decision support system (iNCDSS) demonstrated noninferiority to senior endocrinologists in insulin titration for hospitalized patients with T2DM, suggesting it may be a viable tool for enhancing glycemic control with potential benefits in clinical efficiency and patient safety.

Study details: This multicenter, single-blind, parallel randomized trial (NCT04642378) was conducted from October 1, 2021, to September 8, 2022, in the endocrinology units of three medical centers. The study included 149 adults with T2DM, aged 18 years or older, with glycated hemoglobin levels between 7.0% and 11.0%. Participants were randomized to receive insulin dosage titration either by iNCDSS or by senior endocrinology physicians for five consecutive days.

Results: The proportion of time in the target glucose range (70-180 mg/dL; the primary outcome) was 76.4% in the iNCDSS group and 73.6% in the physician group, meeting the noninferiority margin of 6 percentage points (estimated treatment difference, 2.7%; 95% confidence interval [CI], -2.7% to 8.0%). Secondary outcomes, including other glycemic control measures and adverse events, showed no significant differences between the groups. Physicians reported high satisfaction with the iNCDSS for its clarity, time efficiency, effectiveness, and safety.

Source:

Ying Z, et al. (2025, May 1). JAMA Netw Open. Real-Time AI-Assisted Insulin Titration System for Glucose Control in Patients With Type 2 Diabetes: A Randomized Clinical Trial. https://pubmed.ncbi.nlm.nih.gov/40332936/