EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Machine Learning Algorithms to Predict Heavy Episodic Drinking in the United States Using Survey Data

Laura Llamosas-Falcón iD, Charlotte Probst, Kevin Shield, Erik Spence, Jürgen Rehm iD

Drug and Alcohol Review · 2026

DOI: 10.1111/dar.70065 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Drug and Alcohol Review, 2026. Verfasst von Laura Llamosas-Falcón und 4 weiteren Autor:innen. Beteiligte Einrichtung: Institute for Mental Health Policy Research, Centre for Addiction and Mental Health, Toronto, Canada. Hauptthemen laut MEDLINE: Machine Learning, Binge Drinking, Algorithms. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIAAA NIH HHS, National Institute on Alcohol Abuse and Alcoholism.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Heavy episodic drinking (HED) is a major public health concern but is often missing from surveys or measured unreliably. Predictive models offer a method to estimate HED's likelihood at the individual level in such cases. While logistic regression is commonly used, other machine learning algorithms (MLA) may offer greater accuracy and robustness. This study compares various MLAs to identify the best predictive model of HED.

Methods

Data from the 1997–2018 National Health Interview Survey were used. Six MLAs were trained and cross‐validated: logistic regression, naïve bayes, k‐nearest neighbour, support vector machine, random forest and XGBoost. Model performance was compared, and the SHapley Additive exPlanations (SHAP) method assessed interpretability by ranking features based on their contribution to the model's prediction.

Results

The probability of correctly ranking a randomly selected HED instance higher than a non‐HED instance ranged from 0.85 to 0.97 (with values closer to 1 indicating better performance). XGBoost outperformed the other MLAs (sensitivity 0.80, precision 0.83, accuracy 0.92). Amongst the 11 features included in the models, average daily alcohol use and age were the most influential, as determined by SHAP values. Discussion and Conclusions The strong discriminative ability of our models shows that even a limited number of well‐chosen features can yield robust predictions, highlighting the potential of MLAs for modelling health behaviours. Integrating our models into simulation frameworks can help model HED and test scenarios, leading to effective policies. Future studies should incorporate objective sources for external validation and investigate systematic biases to improve predictive accuracy.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningBinge DrinkingAlgorithmsHumansUnited StatesMaleFemaleAdultMiddle AgedYoung AdultHealth SurveysAdolescentBayes Theorem

Stichwörter der Autor:innen

SHAPalcohol useheavy episodic drinkingmachine learningpublic health

Autor:innen und Institutionen

  • Institute for Mental Health Policy Research, Centre for Addiction and Mental Health, Toronto, Canada.
  • Institute of Medical Science, Faculty of Medicine, University of Toronto, Medical Sciences Building, Toronto, Canada.
  • Campbell Family Mental Health Research Institute, Centre for Addiction and Mental Health, Toronto, Canada.
  • Department of Psychiatry, Faculty of Medicine, University of Toronto, Toronto, Canada.
  • Dalla Lana School of Public Health, University of Toronto, Toronto, Canada.
  • SciNet Consortium, University of Toronto, Toronto, Canada.

ORCID-Profile: Laura Llamosas-Falcón, Jürgen Rehm

Förderung

  • NIAAA NIH HHS
  • National Institute on Alcohol Abuse and Alcoholism

Zitieren

APA

Llamosas-Falcón, L., Probst, C., Shield, K., Spence, E., & Rehm, J. (2026). Machine Learning Algorithms to Predict Heavy Episodic Drinking in the United States Using Survey Data. Drug and Alcohol Review. https://doi.org/10.1111/dar.70065

Vancouver

Llamosas-Falcón L, Probst C, Shield K, Spence E, Rehm J. Machine Learning Algorithms to Predict Heavy Episodic Drinking in the United States Using Survey Data. Drug and Alcohol Review. 2026. doi:10.1111/dar.70065

BibTeX
@article{LlamosasFalcn2026,
  author = {Llamosas-Falcón, Laura and Probst, Charlotte and Shield, Kevin and Spence, Erik and Rehm, Jürgen},
  title = {Machine Learning Algorithms to Predict Heavy Episodic Drinking in the United States Using Survey Data},
  journal = {Drug and Alcohol Review},
  year = {2026},
  doi = {10.1111/dar.70065}
}
Kostenlos starten →