Neuroanatomical profile of BMI implicates impulsive delay discounting and general cognitive ability
Authors' conclusion
Taken together, these findings reveal a robust machine learning-derived neuroanatomical profile of BMI, one that comprises nodes in motivational brain networks and suggests the functional links to obesity are via self-regulatory capacity and cognitive function.
Study context
- Population
- Young adults from the Human Connectome Project Young Adult project; 22% BMI > 3022% BMI > 30 242
- Participants
- 1,100 adults
- Outcome
- Neuroanatomical morphometry profile associated with BMI (variance in BMI explained)
Methodological detailsmachine learning elastic net regression, five-fold cross-validation, held-out test set
- Machine learning elastic net regression
- Five-fold cross-validation
- Held-out test set
Main finding
As reported in the abstract
Prediction of BMI by multiregion neuroanatomical profile
R2, five-fold cross-validation
10.05%
R2, held-out test set
8.87%
Observational data: associations, not effects.
Further findings
Regional composition of the profile
- Profile enriched for nodes in the default mode, executive control and salience networks
Mediation of profile–BMI relationship
- Partially mediated by impulsive delay discounting and general cognitive ability
Original publication
Neuroanatomical profile of BMI implicates impulsive delay discounting and general cognitive ability. Obesity (Silver Spring). Published 19 October 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →