Real-Time AI-Assisted Insulin Titration System for Glucose Control in Patients With Type 2 Diabetes: A Randomized Clinical Trial
Primary result · Time in target glucose range (70-180 mg/dL)Result — go to the resultEstimated treatment difference 2.7% 95% CI −2.7% to 8.0%Authors' conclusion
In this RCT of an iNCDSS, the system demonstrated noninferiority to senior endocrinology physicians in insulin titration in an inpatient setting, indicating its potential as a favorable tool for insulin titration in patients with T2D.
Study context
- Population
- Hospitalized adults (≥18 years) with T2D, HbA1c 7.0%–11.0%, antidiabetic treatment in previous 3 months; endocrinology wards of 3 medical centersrandomized 1:1
- Participants
- 149 adults
- Comparison
- AI-based insulin clinical decision support system (iNCDSS) vs senior endocrinology physicians for insulin titration
- iNCDSSn = 75
- Physiciann = 74reference
- Primary endpoint
- Proportion of time in target glucose range (70-180 mg/dL); noninferiority margin 6 percentage points
- Follow-up
- 5-day study period
Methodological detailsmulticenter, single-blind, parallel, noninferiority, Conducted October 1, 2021, to September 8, 2022
- Multicenter
- Single-blind
- Parallel
- Noninferiority
- Conducted October 1, 2021, to September 8, 2022
Primary result
Time in target glucose range (70-180 mg/dL)
Estimated treatment difference
2.7%
95% CI −2.7% to 8.0%
By group
iNCDSSvs Physician
estimated treatment difference 2.7% (95% CI −2.7% to 8.0%)
As reported in the abstract
Secondary outcomes
Physician satisfaction
- Most physicians were satisfied with the iNCDSS for its clear, time-saving, effective, and safe clinical support
Safety
- No significant differences in adverse events between the 2 groups
Original publication
Real-Time AI-Assisted Insulin Titration System for Glucose Control in Patients With Type 2 Diabetes: A Randomized Clinical Trial. JAMA Netw Open. Published 1 May 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →