Type 1 diabetes

Predicting Hypoglycemia and Hyperglycemia Risk During and After Activity for Adolescents with Type 1 Diabetes

Diabetes Technol TherPublished Prediction modelling study

Authors' conclusion

Incorporating factors such as historical glucose and insulin can improve prediction modeling for the acute glucose responses to exercise.

Study context

Population
Adolescents with T1D wearing continuous glucose monitors (CGMs) in the T1DEXIP study (mean ± SD age 14 ± 2 years; HbA1c 7.1 ± 1.3%; T1D duration 5 ± 4 years; 56% using HCL), 3738 activities logged over 10 days3,738 activities
Participants
225 adolescents
Comparison
Repeated Measures Random Forest vs Repeated Measures Logistic Regression
Outcome
Composite:
  • Risk of hypoglycemia (<70 mg/dL)
  • Hyperglycemia (>250 mg/dL)
Follow-up
Within 2 h after starting exercise
Methodological detailsreal-world data, repeated measures random forest and logistic regression models
  • Real-world data
  • Repeated measures random forest and logistic regression models

Main finding

As reported in the abstract

Prediction of composite dysglycemia risk
GroupAUROC
Repeated Measures Random Forest (RMRF)0.737
Repeated Measures Logistic Regression (RMLR)0.661

AUROC

Repeated Measures Random Forest (RMRF)0.737
Repeated Measures Logistic Regression (RMLR)0.661
  • RMRF vs RMLR: P < 0.001 — RMRF more accurate

Further findings

Activity-start factors with minimal composite risk

Starting glucose
between 132 and 160 mg/dL
Glucose rate of change at activity start
between −0.4 and −1.9 mg/dL/min
Also predictive: time <70 mg/dL and >250 mg/dL in prior 24 h, HbA1c, insulin on board at activity start

Activity-end factors with minimal composite risk

Glucose
between 128 and 133 mg/dL
Glucose rate of change
between 0.4 and −0.6 mg/dL/min
  • Separate models

Original publication

Predicting Hypoglycemia and Hyperglycemia Risk During and After Activity for Adolescents with Type 1 Diabetes. Diabetes Technol Ther. Published 14 May 2024. doi:10.1089/dia.2024.0061

Composed by AI from the published abstract and checked against it. How Briefs are made →

Get them every week

New studies on this topic in My Week and in your Monday e-mail.

We e-mail you a sign-in link and a code. No password, no spam.