Global Trends and Exposure Profiling of Early‐Onset Type 2 Diabetes: An Ecological Analysis Using Machine Learning
Authors' conclusion
EOT2D incidence is rising globally. Population adiposity showed the most consistent association across analytical approaches, while the association with EOT2D incidence of low whole-grain intake was more context dependent.
Study context
- Population
- Individuals aged 15–39 years across 204 countries and territories from 1990 to 2021, GBD 2021 data
- Outcome
- EOT2D incidence trends
- Follow-up
- 1990 to 2021
Methodological detailstemporally separated training, validation and test periods, country-level bootstrap resampling, robust rank aggregation (RRA), SHapley Additive exPlanations (SHAP), year fixed-effects and two-way fixed-effects (TWFE) models
- Temporally separated training, validation and test periods
- Country-level bootstrap resampling
- Robust rank aggregation (RRA)
- SHapley Additive exPlanations (SHAP)
- Year fixed-effects and two-way fixed-effects (TWFE) models
Performance
As reported in the abstract
- EOT2D incidence increased globally, with persistently high rates in Pacific Island countries and rapid increases in Egypt, Greenland and Afghanistan
Further findings
Out-of-time predictive performance
- XGBoost showed the best out-of-time predictive performance
Cross-model consensus predictive exposures
- High body mass index and diet low in whole grains were the only cross-model consensus predictive exposures retained by RRA after multiple-testing correction and consistently ranked highest across models and temporal periods
Association of exposures with EOT2D incidence
- In the year fixed-effects model, both exposures were positively associated with EOT2D incidence
- After adjustment for country fixed effects, high body mass index remained significant
Composite exposure indices
- Composite exposure indices showed marked geographic heterogeneity but broadly similar patterns across weighting strategies
Original publication
Global Trends and Exposure Profiling of Early‐Onset Type 2 Diabetes: An Ecological Analysis Using Machine Learning. Diabetes Obes Metab. Published 9 November 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →