Machine Learning Classification of Smoking Behaviours—From Social Environment to the Prefrontal Cortex

Reinhardt P, Zacharias N, Fislage M, Böhmer J, Hollunder B, Reppmann Z, Wiehe A, Rajwich R, Dominick N, Ritter K, Bajbouj M, Wienker T, Gallinat J, Thürauf N, Kornhuber J, Kiefer F, Wagner M, Tüscher O, Walter H, Winterer G (2025)

Publication Type: Journal article

Publication year: 2025

Journal

Addiction Biology Wiley-Blackwell

Book Volume: 30

Article Number: e70056

Journal Issue: 8

DOI: 10.1111/adb.70056

Abstract

The pronounced heterogeneity in smoking trajectories—ranging from occasional or heavy use to successful quitting —highlights substantial interindividual variation within the smoking population. Machine learning is particularly well suited to capture these complex patterns that may be challenging for traditional inferential statistics to uncover. In this study, we applied machine learning to data from a population-based cohort to identify multimodal markers that distinguish smokers from never smokers at baseline and predict long-term cessation success at a 10-year follow-up. We employed 10 times repeated nested cross-validation (10 outer folds, 5 inner folds) to analyse baseline data (T1) from 707 smokers—including 222 heavy smokers (FTND ≥ 4)—and 864 never smokers for smoking status classification. At the 10-year follow-up (T2), we further classified 60 successful quitters (≥ 1 year abstinent) versus 81 non-quitters. Feature importance was assessed using averaged SHAP values derived from test set predictions. Classification models achieved the following performance, expressed by the area under the receiver operating characteristic curve (AUROC; mean ± SD): smokers versus never smokers, 0.85 ± 0.03; heavy smokers versus never smokers, 0.92 ± 0.03; and quitters versus non-quitters, 0.68 ± 0.13. SHAP analysis identified markers of frontal functioning, cognitive control and smoking behaviour within the social environment among the most influential predictors of both smoking status and cessation success. In conclusion, our machine learning analyses support a multifactorial model of smoking behaviour and cessation success, which may inform nuanced risk stratification to advance the development of personalized cessation strategies.

Authors with CRIS profile

Norbert Thürauf Department of Psychiatry and Psychotherapy Johannes Kornhuber Lehrstuhl für Psychiatrie und Psychotherapie

Involved external institutions

Charité - Universitätsmedizin Berlin DE Germany (DE) Max-Planck-Institut für molekulare Genetik / Max Planck Institute for Molecular Genetics DE Germany (DE) Universitätsklinikum Hamburg-Eppendorf (UKE) DE Germany (DE) Universitätsklinikum Mannheim DE Germany (DE) Universitätsklinikum Bonn DE Germany (DE) Universitätsmedizin der Johannes Gutenberg-Universität Mainz DE Germany (DE)

How to cite

APA:

Reinhardt, P., Zacharias, N., Fislage, M., Böhmer, J., Hollunder, B., Reppmann, Z.,... Winterer, G. (2025). Machine Learning Classification of Smoking Behaviours—From Social Environment to the Prefrontal Cortex. Addiction Biology, 30(8). https://doi.org/10.1111/adb.70056

MLA:

Reinhardt, Pablo, et al. "Machine Learning Classification of Smoking Behaviours—From Social Environment to the Prefrontal Cortex." Addiction Biology 30.8 (2025).

BibTeX: Download