Metabolic, demographic, and behavioral risk factors predict brain structural variability in the general population: an analysis of the human connectome project young adults
Clinical Snapshot
PICO Framework
| P — Population | 1082 neurologically healthy young adults aged 22-37 from the Human Connectome Project |
| I — Intervention | Machine learning regression models using metabolic, demographic, and behavioral predictors |
| C — Comparator | Different machine learning algorithms (XGBoost vs others) for predicting brain structural measures |
| O — Outcomes | Brain structural parameters from MRI including gray matter and white matter volumes, surface areas, and cortical thickness |
Bottom Line
This cross-sectional study demonstrates that machine learning models can predict brain structural variability in healthy young adults using readily available clinical parameters. XGBoost models achieved strong accuracy (R² > 0.80) for total brain volumes using age, gender, education, and blood pressure as key predictors. While methodologically sound and using high-quality HCP data, the findings are limited to healthy adults aged 22-37, restricting clinical generalizability. The approach shows promise as a complementary tool for brain health research but requires validation in broader populations and clinical settings. For Australian clinicians, the use of routine pathology markers makes this approach potentially feasible, though clinical utility remains to be established in real-world healthcare settings.
Key Findings
P Value: Not applicable for machine learning prediction models
Effect Size: XGBoost achieved R² > 0.80 for total brain volumes, R² < 0.60 for cortical surface measures
Primary Outcome: Brain structural parameter prediction accuracy using machine learning models
Nnt Or Sensitivity: NMAE < 0.35 for best-performing models (total brain segmentation)
Confidence Interval: Not reported for primary outcomes
Clinical Application
High - uses readily available clinical and demographic variables that are routinely collected Relevant for Australian healthcare as all predictor variables (BP, BMI, HbA1c, TSH) are standard pathology tests covered by Medicare and routinely monitored in primary care Healthy young adults aged 22-37 with normal neurological function
Abstract
BACKGROUND: Understanding whether commonly available metabolic, demographic, and behavioral factors can explain variability in brain structure may support the development of accessible predictive approaches. This study aims to evaluate the ability of machine learning regression models to predict brain structural measures in young, neurologically healthy adults using clinically accessible risk factors. METHODS: Data were drawn from the Human Connectome Project Young Adults dataset, including 1082 participants aged 22-37. Predictors comprised metabolic measures (systolic and diastolic blood pressure, hematocrit, body mass index, hemoglobin A1C, thyroid stimulating hormone) and demographic/behavioral variables (age, gender, race, education level, smoking history, alcohol use). Brain structural parameters from MRI included gray matter (GM) and white matter (WM) volumes, surface areas, and cortical thickness. Distance correlation (dcor) guided feature selection, followed by machine learning modeling. Model performance was evaluated using normalized mean absolute error (NMAE), normalized root-mean-squared error (NRMSE), and coefficient of determination (R²). SHAP values were used for feature interpretation. RESULTS: XGBoost consistently outperformed other algorithms, showing strong predictive accuracy for total brain segmentation, supratentorial, and total GM volumes (NMAE < 0.35, R² > 0.80). In contrast, cortical surface predictions (left superior frontal) showed moderate performance (NMAE > 0.50, R² < 0.60). SHAP analysis highlighted age, gender, education level, and diastolic and systolic blood pressure as the most influential predictors of brain structure. CONCLUSIONS: The findings highlight the methodological value of regression-based approaches for estimating brain structural variability and support their potential role as complementary tools for brain health research.
References
- 1.Soleymani, Y., Khalagi, K., Negarandeh, S., Negarandeh, N., Batouli, S. A. H., & Pourabbasi, A. (2026). Metabolic, demographic, and behavioral risk factors predict brain structural variability in the general population: an analysis of the human connectome project young adults. Neurological Sciences. https://doi.org/10.1002/hbm.26633
Related Research
Sleep medicine reviews
Machine and deep learning in REM sleep behavior disorder: a scoping review and analysis of reporting quality
3 Aug 2026
Neurological research
Federated deep learning model for epilepsy seizure detection using electroencephalogram (EEG) signal
2 Aug 2026
Journal of psychiatric research
Systematic review of machine learning and deep learning models for EEG-based detection of depression.
2 Aug 2026
This content is for educational purposes for healthcare professionals only and does not constitute clinical advice. Clinical decisions should be based on individual patient assessment, current guidelines, and appropriate specialist consultation. Editorial Standards · Privacy Policy · Terms of Service