Interpretable machine learning to identify problematic alcohol use in peacekeepers

Addictive Behaviors Reports, pp. 100763

Abstract

Introduction United Nations peacekeeping missions expose military personnel to significant psychological stress, impacting mental health and operational readiness. Despite predeployment screening efforts, problematic alcohol use remains a concern. Objectives This study aimed to evaluate whether supervised machine learning combined with interpretable artificial intelligence can identify and interpret factors associated with problematic alcohol use in Brazilian peacekeepers assessed prior to deployment. Materials and methods We performed a cross-sectional analysis of predeployment data from 771 Brazilian male military personnel assessed before deployment to the United Nations mission in Haiti. Problematic alcohol use was defined by a positive CAGE questionnaire result administered before deployment. Six supervised machine learning models were trained and evaluated using traditional metrics. Interpretability was addressed with Shapley values and feature importance, to clarify variable contributions. Results The best model, LightGBM, achieved an ROC-AUC of 0.80, with 75% sensitivity and 70% specificity on the test set. Interpretability analyses consistently identified lifetime trauma exposure and posttraumatic stress symptoms as the main predictors. Discussion These results highlight the value of interpretable machine learning in predeployment screening, enabling interpretable risk stratification from routine data. The importance of trauma exposure and posttraumatic stress aligns with evidence linking cumulative trauma to alcohol problems in military populations. Conclusions Interpretable machine learning may complement traditional methods in identifying multivariable patterns of problematic alcohol use in predeployment data. It also helps mitigate concerns about model opacity in clinical and operational contexts. External validation, calibration, and clinical utility assessment are required before operational use.

Authors 15

1. Erito Marques de Souza Filho corresponding
2. Liliane Maria Pereira Vilete
   Affiliation as printed

   Department of Psychiatry and Legal Medicine, Institute of Psychiatry, Rio de Janeiro, Brazil

3. Wanderson Fernandes de Souza
4. Eliane Volchan

   Universidade Federal do Rio de Janeiro · Instituto de Biofísica Carlos Chagas Filho

   Affiliation as printed

   Institute of Biophysics, Carlos Chagas Filho, Universidade Federal do Rio de Janeiro, Rio de Janeiro, Brazil

5. Antônio Fernando Araújo Duarte

   Exército Brasileiro

   Affiliation as printed

   Brazilian Army Physical Training Center, CCFEx, Rio de Janeiro, Brazil

6. Roberta Benitez Freitas Passos

   Universidade Federal do Estado do Rio de Janeiro

   Affiliation as printed

   Department of Internal Medicine, Universidade Federal do Estado do Rio de Janeiro, Rio de Janeiro, Brazil

7. Mariana Pires Luz
   Affiliation as printed

   Department of Psychiatry and Legal Medicine, Institute of Psychiatry, Rio de Janeiro, Brazil

8. Thaís Pereira Mendes
   Affiliation as printed

   Department of Psychiatry and Legal Medicine, Institute of Psychiatry, Rio de Janeiro, Brazil

9. Gabriel Ribeiro Cesario da Silva
10. Sergio Baxter Andreoli

    Universidade Federal de São Paulo

    Affiliation as printed

    Department of Psychiatry, Universidade Federal de São Paulo, São Paulo, Brazil

11. Jair de Jesus Mari
12. Eric Vermetten Aachen

    Leiden University

    Affiliation as printed

    Leiden University, Leiden, the Netherlands

13. Mauro Vitor Mendlowicz
    Affiliation as printed

    Department of Psychiatry and Legal Medicine, Institute of Psychiatry, Rio de Janeiro, Brazil

14. Jorge Amaral

    Universidade do Estado do Rio de Janeiro

    Affiliation as printed

    Department of Electronic and Telecommunications Engineering, Universidade do Estado do Rio de Janeiro, Rio de Janeiro, Brazil

15. William L. Berger
    Affiliation as printed

    Department of Psychiatry and Legal Medicine, Institute of Psychiatry, Rio de Janeiro, Brazil