Predicting Immunological Risk for Stage 1 and Stage 2 Diabetes Using a 1-Week Continuous Glucose Monitoring (CGM) Home Test, Nocturnal Glucose Increments, and Standardized Liquid Mixed Meal Breakfasts, with Classification Enhanced by Machine Learning
Authors' conclusion
A new technology combining machine learning with a potentially self-administered 1-week CGM home test can help improve T1D risk detection without the need to visit a hospital or use a medical laboratory.
Study context
- Population
- Healthy relatives of people with T1D; mean age 23.7 ± 10.7 years, HbA1c 5.3% ± 0.3%, BMI 23.8 ± 5.6 kg/m²
- Participants
- 60 relatives
- Exposure
- Glycemia across autoantibody groups (0, 1, ≥2 autoantibodies); autoantibody positive vs negative classification
- Zero autoantibodiesn = 21reference
- One autoantibodyn = 18
- ≥2 autoantibodiesn = 21
- Outcome
- CGM glycemia metrics across autoantibody groups
Methodological details1-week CGM home test, standardized liquid mixed meals, 10-fold cross-validation, supervised machine-learning classifiers
- 1-week CGM home test
- Standardized liquid mixed meals
- 10-fold cross-validation
- Supervised machine-learning classifiers
Main finding
As reported in the abstract
Linear support vector machine classifying autoantibody positive vs negative (overnight and post-SLMM features), AUC-ROC
≥0.81
Observational data: associations, not effects.
Original publication
Predicting Immunological Risk for Stage 1 and Stage 2 Diabetes Using a 1-Week CGM Home Test, Nocturnal Glucose Increments, and Standardized Liquid Mixed Meal Breakfasts, with Classification Enhanced by Machine Learning. Diabetes Technol Ther. Published 15 June 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →