Predicting BMI Percentile in Hispanic/Latino Youth Using a Machine Learning Approach: Findings From the Study of Latino Youth
Authors' conclusion
Family-based approaches and focusing on dieting and body image satisfaction may be important for weight management in Hispanic/Latino youth.
Study context
- Population
- Hispanic/Latino 8- to 16-year-olds in the US, Study of Latino Youth (SOL Youth); mean age 12 years, 50% female, 44.2% Mexican heritageSOL Youth
- Participants
- 1,466 participants
- Outcome
- BMI percentile
Methodological detailsmachine learning (LASSO regression), 102 predictor variables
- Machine learning (LASSO regression)
- 102 predictor variables
Main finding
As reported in the abstract
Predictors of BMI percentile (10-variable LASSO model; 6 significant associations)
- Dieting 1-4 times/year: higher BMI percentile, β
- 8.69 (10.25 to 14.52) (95% CI)
- Dieting ≥ 5 times/year: higher BMI percentile, β
- 10.86 (13.14 to 18.33) (95% CI)
- Parent of Dominican heritage: higher BMI percentile, β
- 3.48 (4.05 to 9.90) (95% CI)
- Parent with obesity: higher BMI percentile, β
- 2.96 (2.99 to 6.85) (95% CI)
- Perceived smaller than "ideal" body size: lower BMI percentile, β
- −1.65 (−6.84 to −1.35) (95% CI)
- Food/activity parenting practice Control: lower BMI percentile, β
- −1.17 (−3.63 to −1.69) (95% CI)
Observational data: associations, not effects.
Further findings
Optimum mean squared error model (36-variable LASSO)
- R 2
- 0.42
Original publication
Predicting BMI Percentile in Hispanic/Latino Youth Using a Machine Learning Approach: Findings From the Study of Latino Youth. Obesity (Silver Spring). Published 16 December 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →