Improving the Algorithm: The Inclusion of a Socioeconomic Status Measure in Predicting Type 2 Diabetes Development in Youth With Prediabetes
Authors' conclusion
The addition of ADI to the model resulted in the best performance in predicting youth-onset type 2 diabetes development.
Study context
- Population
- Youth with prediabetes; patient encounters from an electronic medical record
- Participants
- 665 patient encounters
- Comparison
- HbA1c + Area Deprivation Index (ADI) model vs HbA1c-only model
- Outcome
- Prediction of T2D development
- Follow-up
- Within 1 year of prediabetes diagnosis
Methodological detailssupervised machine learning, logistic regression, electronic medical record data
- Supervised machine learning
- Logistic regression
- Electronic medical record data
Main finding
As reported in the abstract
Prediction of T2D development (AUC) · within 1 year
| Group | AUC |
|---|---|
| HbA1c + ADI | 0.73 |
| HbA1c only | 0.68 |
AUC
HbA1c + ADI0.73
HbA1c only0.68
Further findings
Developed T2D · within 1 year
- Patient encounters that developed T2D
- 181 (27.2%)
Original publication
Improving the Algorithm: The Inclusion of a Socioeconomic Status Measure in Predicting Type 2 Diabetes Development in Youth With Prediabetes. Diabetes Care. Published 16 March 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →