Use of machine learning to identify characteristics associated with severe hypoglycemia in older adults with type 1 diabetes: a post-hoc analysis of a case–control study
Authors' conclusion
Machine learning may augment risk stratification for OAs by identifying key characteristics associated with SH. Prospective studies are needed to identify the predictive performance of these risk characteristics.
Study context
- Population
- Older adults with T1D recruited from the T1D Exchange Clinical Network; 47.1% female, 92.1% non-Hispanic white
- Participants
- 191 adults
- Comparison
- Older adults (OAs) with vs without recent severe hypoglycemia (SH)
- Primary endpoint
- Characteristics associated with case vs control status (SH history) and their relative importance
Methodological detailsmachine learning (random forest), T1D Exchange Clinical Network
- Machine learning (random forest)
- T1D Exchange Clinical Network
Primary result
As reported in the abstract
Characteristics associated with SH history
- Across models, hypoglycemia unawareness was the top characteristic associated with SH history
- Richest model, most important characteristics in descending order: hypoglycemia unawareness, hypoglycemia fear, CV from continuous glucose monitoring (CGM), % time blood glucose below 70 mg/dL, trail making test B score
Parts of this Brief are withheld: the automatic checks could not confirm them against the abstract.
Original publication
Use of machine learning to identify characteristics associated with severe hypoglycemia in older adults with type 1 diabetes: a post-hoc analysis of a case–control study. BMJ Open Diabetes Res Care. Published 27 February 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →