Classification of Adolescent Drinking via Behavioral, Biological and Environmental Variables: A Machine Learning Approach With Bias Control
Addiction Biology · 2026
DOI: 10.1111/adb.70188 ↗Kurz gefasst
Fachartikel in der Zeitschrift Addiction Biology, 2026. Verfasst von Ruobing Liu und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Neurological Sciences, University of Nebraska Medical Center, Omaha, Nebraska, USA. Hauptthemen laut MEDLINE: Underage Drinking, Machine Learning. Die Arbeit nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIH Office of the Director, NIAAA NIH HHS, NIGMS NIH HHS.
Abstract (Originalsprache)
In 2024, approximately 30% of US adolescents reported having consumed alcohol at least once in their lifetime, with about 25% of these individuals engaging in binge drinking. Adolescent alcohol use is associated with neurodevelopmental impairments, elevated risk of later alcohol use and mental health disorders. Therefore, it is important to identify the variables driving adolescent alcohol use and leverage them for early identification and targeted intervention. Previous studies have typically developed machine learning classification models that use neuroimaging data in combination with limited clinical measurements. Neuroimaging data are expensive and difficult to obtain at scale, whereas clinical measures are more practical for large‐scale screening due to their low cost and widespread accessibility. However, clinical‐only approaches for alcohol drinking classification remain largely underexplored. Furthermore, prior studies have often focused on adults, limiting generalizability to the broader adolescent population. Additionally, confounding factors such as age and substance use, which are strongly correlated with alcohol consumption, have often been inadequately addressed, potentially inflating classification performance. Finally, class imbalance remains a persistent challenge, with prior attempts yielding only limited improvements. To address these limitations, we propose FocalTab , a framework that integrates TabPFN with focal loss for robust generalization and effective mitigation of class imbalance. The approach also incorporates an initial preprocessing step to remove confounding factors to account for age and substance use. We compare FocalTab against state‐of‐the‐art methods across different variable selections and dataset settings. FocalTab achieves the highest accuracy (0.841 ± 0.011) and specificity (0.803 ± 0.055) in the most stringent setting, in which both age and substance use variables were excluded, whereas competing models drop to near‐chance specificity (12%–24%). We further applied SHapley Additive exPlanations (SHAP) analysis to identify key clinical predictors of drinker classification, supporting enhanced screening and early intervention.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Neurological Sciences, University of Nebraska Medical Center, Omaha, Nebraska, USA.
- Munroe-Meyer Institute for Genetics and Rehabilitation, University of Nebraska Medical Center, Omaha, Nebraska, USA.
- Department of Genetics, Cell Biology and Anatomy, University of Nebraska Medical Center, Omaha, Nebraska, USA.
ORCID-Profile: Ruobing Liu, Mohamed Azzam, Nicole L Zabik, Shibiao Wan, Jennifer Urbano Blackford, Jieqiong Wang
Förderung
- NIH Office of the Director
- NIAAA NIH HHS
- NIGMS NIH HHS
- NCI NIH HHS
- Child Health Research Institute at UNMC/Children's Nebraska
- National Science Foundation
- Nebraska EPSCoR FIRST Award
- NIH HHS
Zitieren
APA
Liu, R., Azzam, M., Zabik, N. L., Wan, S., Blackford, J. U., & Wang, J. (2026). Classification of Adolescent Drinking via Behavioral, Biological and Environmental Variables: A Machine Learning Approach With Bias Control. Addiction Biology. https://doi.org/10.1111/adb.70188
Vancouver
Liu R, Azzam M, Zabik NL, Wan S, Blackford JU, Wang J. Classification of Adolescent Drinking via Behavioral, Biological and Environmental Variables: A Machine Learning Approach With Bias Control. Addiction Biology. 2026. doi:10.1111/adb.70188
BibTeX
@article{Liu2026,
author = {Liu, Ruobing and Azzam, Mohamed and Zabik, Nicole L and Wan, Shibiao and Blackford, Jennifer Urbano and Wang, Jieqiong},
title = {Classification of Adolescent Drinking via Behavioral, Biological and Environmental Variables: A Machine Learning Approach With Bias Control},
journal = {Addiction Biology},
year = {2026},
doi = {10.1111/adb.70188}
}
EUVIMED