Estimation of a Machine Learning-Based Decision Rule to Reduce Hypoglycemia Among Older Adults With Type 1 Diabetes: A Post Hoc Analysis of Continuous Glucose Monitoring in the Wireless Innovation for Seniors with Diabetes Mellitus (WISDM) Study
Authors' conclusion
The decision rule underscores the benefits of CGM for older adults to reduce hypoglycemia. Diagnostic CGM and laboratory markers may inform decision-making surrounding therapeutic CGM and identify older adults for whom CGM may be a critical intervention to reduce hypoglycemia.
Study context
- Population
- Older adults with T1D in the WISDM trial with complete datacomplete data
- Participants
- 194 adults
- Comparison
- Continuous glucose monitoring (CGM) vs blood glucose monitoring (BGM)
- CGMn = 100
- BGMn = 94reference
- Primary endpoint
- CGM-measured % time in hypoglycaemic range (<70 mg/dL); decision rule assigned participants to the treatment estimated to minimise it
- Follow-up
- Across all visits
Methodological detailsprecision medicine analysis, policy tree and decision list algorithms, 14 baseline measures
- Precision medicine analysis
- Policy tree and decision list algorithms
- 14 baseline measures
Primary result
As reported in the abstract
Optimal decision rule assigning CGM vs BGM to minimise % time <70 mg/dL · all follow-up visits
Step 1: baseline time-below range >1.35% and no detectable C-peptide → CGM subgroup
n = 139
Remaining participants left in BGM subgroup
n = 37; 19%
Group for whom CGM minimized hypoglycemia
n = 157; 81%
Parts of this Brief are withheld: the automatic checks could not confirm them against the abstract.
Original publication
Estimation of a Machine Learning-Based Decision Rule to Reduce Hypoglycemia Among Older Adults With Type 1 Diabetes: A Post Hoc Analysis of Continuous Glucose Monitoring in the WISDM Study. J Diabetes Sci Technol. Published 11 January 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →