Identification of critical brain regions for young adults with obesity and their relationships with impulsivity using machine learning based on neuroanatomical features
Authors' conclusion
Distributed neuroanatomical features in prefrontal, medial temporal, cingulate, and parietal cortices discriminated obesity and showed convergent population-level associations with delay discounting impulsivity across group, correlational, and normative analyses.
Study context
- Population
- Young adults from the Human Connectome Project S1200 dataset
- Participants
- 243 vs 475
- Exposure
- Young adults with obesity vs healthy-weight controls
- Obesityn = 243
- Healthy weightn = 475reference
- Outcome
- Discrimination of obesity from healthy weight by SVM classifiers based on neuroanatomical features
Methodological detailsmachine learning, two-stage machine learning framework, surface-based morphometry, normative modeling
- Machine learning
- Two-stage machine learning framework
- Surface-based morphometry
- Normative modeling
Main finding
As reported in the abstract
Neuroanatomical-only support vector machine (SVM), ROC-AUC
0.648
SVM with demographic and cognitive covariates added, ROC-AUC
0.740
Observational data: associations, not effects.
Further findings
Associations of the top 15 SVM-selected features with AUC of delay discounting (partial correlations, full sample)
- Features significantly associated with AUC-DD, all in the expected direction (of top 15)
- 10
Normative modeling of AUC-DD from brain structure
- Obesity group showed systematically higher delay discounting (DD) impulsivity than predicted by brain structures alone
Original publication
Identification of critical brain regions for young adults with obesity and their relationships with impulsivity using machine learning based on neuroanatomical features. Int J Obes (Lond). Published 11 August 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →