County‐level socio‐environmental factors and obesity prevalence in the United States
Authors' conclusion
There is significant county-level geographical variation in obesity prevalence in the United States, which can in part be explained by complex SEDH factors. The use of machine-learning techniques to analyse these factors can provide valuable insights into the importance of these upstream determinants of obesity and, therefore, aid in the development of geo-specific strategic interventions and optimize resource allocation to help battle the obesity pandemic.
Study context
- Population
- US counties; county-level adult obesity prevalence (BMI ≥30 kg/m²), Diabetes Surveillance System 2017; 49 county-level sociodemographic and environmental determinants of health (SEDH) factors
- Participants
- 2,752 counties
- Outcome
- County-level adult obesity prevalence (BMI ≥30 kg/m²)
Methodological detailsmachine-learning, classification and regression trees (CART), hold-out validation, Random Forest variable importance
- Machine-learning
- Classification and regression trees (CART)
- Hold-out validation
- Random Forest variable importance
Main finding
As reported in the abstract
National median obesity prevalence (IQR)
34.1%
30.2%, 37.7%
Clusters identified by CART
11
Relative increase in prevalence across the cluster spectrum
60.8%
Key SEDH variables identified by CART: Physically Inactive (%), Diabetes (%), Severe Housing Problems (%), Food Insecurity (%), Uninsured (%), Population over 65 years (%), Non-Hispanic Black (%)
7
Observational data: associations, not effects.
Original publication
Composed by AI from the published abstract and checked against it. How Briefs are made →