Bedtime Prediction of Nocturnal Hypoglycemia in Insulin-Treated Type 2 Diabetes Patients
Authors' conclusion
The model was able to predict nocturnal hypoglycemia with an acceptable accuracy and could therefore prevent such cases.
Study context
- Population
- Insulin-treated patients with T2D with continuous glucose monitoring (CGM), mealtime and insulin data30 in prediction model
- Participants
- 67 patients
- Outcome
- Prediction of nocturnal hypoglycemia (15 consecutive minutes below 3.0 mmol/L (54 mg/dL) during the following night)
Methodological detailsfive-fold cross-validation, logistic regression, forward feature selection
- Five-fold cross-validation
- Logistic regression
- Forward feature selection
Performance
As reported in the abstract
Prediction of nocturnal hypoglycemia
Mean AUC
0.82
Accuracy
0.79
Periods resulting in nocturnal hypoglycemia
60 of 496
Original publication
Bedtime Prediction of Nocturnal Hypoglycemia in Insulin-Treated Type 2 Diabetes Patients. J Diabetes Sci Technol. Published 13 December 2022. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →