GlucoseGo: a simple tool to predict hypoglycaemia during exercise in type 1 diabetes
Authors' conclusion
The GlucoseGo heatmap provides a practical, accessible tool for predicting hypoglycaemia risk immediately before exercise. It may empower individuals with type 1 diabetes to exercise more safely, reduce hypoglycaemic episodes, and increase engagement in physical activity.
Study context
- Population
- People with T1D aged 12–80 years using various insulin delivery methods; 16,430 exercise sessions16,430 exercise sessions
- Participants
- 834 people
- Comparison
- Comprehensive model vs simplified model
- Outcome
- Prediction of hypoglycaemia during exercise
Methodological detailsmachine learning (XGBoost), pooled data from four studies
- Machine learning (XGBoost)
- Pooled data from four studies
Main finding
As reported in the abstract
| Group | Mean ROC AUC | ROC AUC |
|---|---|---|
| Comprehensive model | 0.89 | — not stated in the abstract |
| Simplified model | — not stated in the abstract | 0.87 |
Mean ROC AUC
Comprehensive model0.89
Simplified model— not stated in the abstract
ROC AUC
Comprehensive model— not stated in the abstract
Simplified model0.87
— not stated in the abstract
Further findings
Translation into tool
- Simplified model translated, with individuals with T1D, into GlucoseGo, a traffic-light heatmap of hypoglycaemia risk based on the three variables
Original publication
GlucoseGo: a simple tool to predict hypoglycaemia during exercise in type 1 diabetes. Diabetologia. Published 25 February 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →