Exploratory brain-wide analyses predicting binge drinking: A machine learning and targeted causal inference pipeline in two adolescent cohorts
Abstract
BackgroundA sizeable literature has found that neuroanatomical differences predict alcohol use outcomes in adolescence. However, due possibly to small samples and inconsistent/limited methodologies, it is still unclear which specific morphometric features are most predictive and if they are also causally implicated in binge drinking onset.
MethodsTo differentially predict abstinence from binge drinking by age 16-17, a SuperLearner ensemble algorithm was fit to structural and diffusion MRI features at age 9-10 in the Adolescent Brain and Cognitive Development cohort (ABCD). A separate model was fit using the National Consortium on Alcohol and NeuroDevelopment in Adolescence (NCANDA), in which the MRI predictors were measured later (ages 12-17) but the developmental outcome (binge drinking by age 18) remained similar. The top ten predictors were extracted from each model, and the causal role of these features scrutinised using targeted maximum likelihood estimation (TMLE).
ResultsPredictive performance in ABCD was poor (AUC=.585) but was stronger in NCANDA (AUC=.695). There was little overlap in predictive feature rankings between the cohorts. TMLE did not reveal a causal effect of the top ten morphological predictors on binge drinking in either cohort.
ConclusionsNo evidence was found for causal contributions of any discrete macrostructural/microstructural brain feature in late childhood or adolescence to binge drinking. Using more sophisticated metrics of brain structure and function may yield better insights. Adding to previous evidence from youth cohorts, neuroanatomy may have greater predictive value for identifying those at risk of adolescent binge drinking when measured in adolescence, rather than late childhood.
Related
- Predicting the Timing of Adolescent Drinking Onset from Baseline Clinical Data: A Stacked-Encoder Survival Framework with Embedding-Derived Biotypes
- Predicting the Risk of Distal Junctional Kyphosis After Surgery for Adolescent Idiopathic Scoliosis Using Preoperative Radiographic Indicators and Machine Learning
- Thyroid-Stimulating hormone and metabolic cardiovascular risk markers from weighted two-wave analyses of india with an exploratory Chinese inpatient comparison
- mHealth-based lifestyle intervention for hypertension in community-dwelling adults: a cluster-randomized controlled trial with exploratory multi-omics analyses
- Exploratory Agreement of 3D Body Surface Analysis with Expert Manual Assessment of Pelvic Malalignment in Patients with Non-Acute Low Back Pain: A Prospective Pilot Study with Linked Post-Hoc Analyses
BibTeX
@misc{visontay2026exploratory,
title = {{Exploratory brain-wide analyses predicting binge drinking: A machine learning and targeted causal inference pipeline in two adolescent cohorts}},
author = {Rachel Visontay and Hollie R. Byrne and Emma K. Devine and Matthew Sunderland and Lei Fan and Wei Wen and Maria I. Perica and Susan Tapert and Duncan B. Clark and Kate Nooner and Kamran Afzali and Lindsay M. Squeglia and Louise Mewton},
howpublished = {medRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.18.26365855},
url = {https://www.medrxiv.org/content/10.64898/2026.10.18.26365855v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Exploratory brain-wide analyses predicting binge drinking: A machine learning and targeted causal inference pipeline in two adolescent cohorts
AU - Rachel Visontay
AU - Hollie R. Byrne
AU - Emma K. Devine
AU - Matthew Sunderland
AU - Lei Fan
AU - Wei Wen
AU - Maria I. Perica
AU - Susan Tapert
AU - Duncan B. Clark
AU - Kate Nooner
AU - Kamran Afzali
AU - Lindsay M. Squeglia
AU - Louise Mewton
PY - 2026
DA - 2026/10/18
PB - medRxiv
DO - 10.64898/2026.10.18.26365855
UR - https://www.medrxiv.org/content/10.64898/2026.10.18.26365855v1
AB - BackgroundA sizeable literature has found that neuroanatomical differences predict alcohol use outcomes in adolescence. However, due possibly to small samples and inconsistent/limited methodologies, it is still unclear which specific morphometric features are most predictive and if they are also causally implicated in binge drinking onset. MethodsTo differentially predict abstinence from binge drinking by age 16-17, a SuperLearner ensemble algorithm was fit to structural and diffusion MRI features at age 9-10 in the Adolescent Brain and Cognitive Development cohort (ABCD). A separate model was fit using the National Consortium on Alcohol and NeuroDevelopment in Adolescence (NCANDA), in which the MRI predictors were measured later (ages 12-17) but the developmental outcome (binge drinking by age 18) remained similar. The top ten predictors were extracted from each model, and the causal role of these features scrutinised using targeted maximum likelihood estimation (TMLE). ResultsPredictive performance in ABCD was poor (AUC=.585) but was stronger in NCANDA (AUC=.695). There was little overlap in predictive feature rankings between the cohorts. TMLE did not reveal a causal effect of the top ten morphological predictors on binge drinking in either cohort. ConclusionsNo evidence was found for causal contributions of any discrete macrostructural/microstructural brain feature in late childhood or adolescence to binge drinking. Using more sophisticated metrics of brain structure and function may yield better insights. Adding to previous evidence from youth cohorts, neuroanatomy may have greater predictive value for identifying those at risk of adolescent binge drinking when measured in adolescence, rather than late childhood.
ER -