Control of nocturnal hypoglycemia by CGM-based AI-enabled nocturnal hypoglycemia prediction: A retrospective analysis of real-world data
Authors' conclusion
NLP use is associated with lower odds of nocturnal hypoglycemia in people with diabetes without raising odds of hyperglycemia, offering valuable self-management support.
Study context
- Population
- People with diabetes using the Accu-Chek SmartGuide Predict app, aged 20–84 years; users without nocturnal hypoglycemic events excluded159 for L2 analyses
- Participants
- 249 people
- Exposure
- Nights with Night Low Predict (NLP) predictions received vs nights without predictions generated
- Outcome
- Nocturnal hypoglycemia
- Follow-up
- Per night
Methodological detailsdeidentified, aggregated app-user data, within-user comparison of nights
- Deidentified, aggregated app-user data
- Within-user comparison of nights
Main finding
As reported in the abstract
Odds of hypoglycemic events of any severity (<70 mg/dL) in a given night, NLP vs no prediction
20.0 % lower
Odds of any TB70
31.2 % lower
Observational data: associations, not effects.
Further findings
L2 hypoglycemia (<54 mg/dL) · per night
- Odds of L2 events, NLP vs no prediction
- 31.0 % lower
- Odds of any TB54
- 39.2 % lower
- n = 159
Hyperglycemic events (>180 mg/dL) and TAR
- Hyperglycemic events and TAR were not affected by NLP use
Original publication
Control of nocturnal hypoglycemia by CGM-based AI-enabled nocturnal hypoglycemia prediction: A retrospective analysis of real-world data. Diabetes Res Clin Pract. Published 24 February 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →