A Scalable Application of Artificial Intelligence-Driven Insulin Titration Program to Transform Type 2 Diabetes Management
Authors' conclusion
The use of d-Nav allowed for improvement in overall diabetes management with appropriate use of both insulin and noninsulin pharmacologic agents in a scalable way.
Study context
- Population
- Patients with long-term T2D on insulin in a community-based endocrinology center; age 67.1 ± 11.5 years, diabetes duration 19.8 ± 11.0 years82% retention
- Participants
- 600 patients
- Outcome
- HbA1c
- Follow-up
- D-Nav use 8.2 ± 3.0 months
Methodological detailscommunity-based endocrinology center, AI-based autonomous insulin titration (d-Nav)
- Community-based endocrinology center
- AI-based autonomous insulin titration (d-Nav)
Main finding
As reported in the abstract
| Group | Value | HbA1c at program start | HbA1c >9% at start | HbA1c >9% with d-Nav |
|---|---|---|---|---|
| d-Nav | 7.3% ± 1.2% | 8.6% ± 2.1% | 29.3% | 5.7% |
d-Nav
Value7.3% ± 1.2%
HbA1c at program start8.6% ± 2.1%
HbA1c >9% at start29.3%
HbA1c >9% with d-Nav5.7%
Observational data: associations, not effects.
Further findings
Cardiorenal-risk reduction pharmacotherapy
- GLP-1 RA or dual GLP-1/GIP receptor agonists prescribed
- about a half of the patients
- SGLT2i prescribed
- a third
Insulin dose reduction due to relatively low glucose · first 3 months
- Total daily insulin dose reduced
- one of every five patients
Safety
Hypoglycaemia
- Frequency of hypoglycaemia (<54 mg/dL)
- 0.4 ± 0.6/month
- Severe hypoglycaemia
- 1.7/100-patient-years
Insulin dose reduction for low glucose · first 3 months
- Total daily insulin dose reduced due to relatively low glucose levels to minimize hypoglycaemia risk
- one of every five patients
Original publication
A Scalable Application of Artificial Intelligence-Driven Insulin Titration Program to Transform Type 2 Diabetes Management. Diabetes Technol Ther. Published 31 May 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →