Predicting type II diabetes mellitus in young and middle-aged adults: A machine learning approach using the Utah population database
Authors' conclusion
Application of machine learning models for T2DM prediction should be tailored to specific study designs and population characteristics, with considerations of environmental data relevant to the local context.
Study context
- Population
- Parents of individuals born in 1970–1990 who resided in Utah urban counties during 1990–2015 (Utah population database)
- Participants
- 240,163 vs 126,525
- Comparison
- Follow-back vs Age-based
- Follow-backn = 240,163
- Age-basedn = 126,525
- Outcome
- Performance of final CART decision rules for predicting T2D
Methodological detailsmachine learning, classification and regression tree (CART) methods, follow-back design, age-based design
- Machine learning
- Classification and regression tree (CART) methods
- Follow-back design
- Age-based design
Main finding
As reported in the abstract
Sensitivity of final CART decision rules
90-95%
Original publication
Predicting type II diabetes mellitus in young and middle-aged adults: A machine learning approach using the Utah population database. Diabetes Res Clin Pract. Published 16 May 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →