Using machine learning to predict suicide risk among veterans: variation by race and ethnicity

AIMS: Suicide is a leading cause of preventable death among U.S. veterans. Machine learning (ML) prediction is promising, yet most ML models for suicide rely on predominantly non-Hispanic White samples and rarely assess racial/ethnic status. METHODS: We analysed baseline data from the Behavioural Research and Analysis of Veterans' Outcomes (BRAVO) cohort, a national sample of post-9/11 veterans. A total of 2,083 veterans (37% female; mean age = 38.5 years) completed a survey assessing demographics, military history, behavioural health, discrimination, neighbourhood context and treatment access; 40.7% met the cut-score (≥7 on the Suicide Behaviours Questionnaire-Revised [SBQ-R]) for elevated suicide-related thoughts/behaviours. Using 90 variables assessed from self-report and census tract linking, we fit random-forest classifiers with multiple imputation and race-stratified models. Permutation importance and Shapley Additive Explanations (SHAP) identified influential predictors and their directional contributions; performance was summarised with area-under-the-curve (AUC). RESULTS: Overall model performance was adequate (AUC = 0.77) and similar across racial/ethnic groups (AUCs = 0.72-0.77). Across the full sample and race/ethnicity-stratified models, suicide risk was dominated by shared transdiagnostic and non-transdiagnostic phenotypes. The rank order of variable importance was higher neuroticism, emotion-regulation difficulties, irritability/anger, trauma-related shame and moral injury, internalizing symptoms, adverse childhood experiences and difficulty transitioning out of the military. Group-specific predictors (e.g. neighbourhood disadvantage, substance use patterns and minority-stress exposures) added meaningful signal. CONCLUSION: Interpretable ML in an intentionally diverse veteran cohort identifies a robust, shared suicide-risk profile with contextually distinct amplifiers across race/ethnicity.

Authors

Institutions

Publication Details

Journal
Epidemiology and Psychiatric Sciences
Published
2026-11-20
DOI
https://doi.org/10.1017/s2045796026101176
Primary Topic
Suicide and Self-Harm Studies
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Using machine learning to predict suicide risk among veterans: variation by race and ethnicity

Whitney S. Livingston, Jordan P. Davis, Daniel Leightley, Angeles Sedano et al.
4 links
Epidemiology and Psychiatric Sciences
Suicide and Self-Harm Studies
article

Using machine learning to predict suicide risk among veterans: variation by race and ethnicity

Whitney S. Livingston, Jordan P. Davis, Daniel Leightley, Angeles Sedano, John Prindle, Eric R. Pedersen, Liv Canning, Carl A. Castro, Kathryn Bouskill, Ricky N. Bluthenthal
article en

Abstract

AIMS: Suicide is a leading cause of preventable death among U.S. veterans. Machine learning (ML) prediction is promising, yet most ML models for suicide rely on predominantly non-Hispanic White samples and rarely assess racial/ethnic status. METHODS: We analysed baseline data from the Behavioural Research and Analysis of Veterans' Outcomes (BRAVO) cohort, a national sample of post-9/11 veterans. A total of 2,083 veterans (37% female; mean age = 38.5 years) completed a survey assessing demographics, military history, behavioural health, discrimination, neighbourhood context and treatment access; 40.7% met the cut-score (≥7 on the Suicide Behaviours Questionnaire-Revised [SBQ-R]) for elevated suicide-related thoughts/behaviours. Using 90 variables assessed from self-report and census tract linking, we fit random-forest classifiers with multiple imputation and race-stratified models. Permutation importance and Shapley Additive Explanations (SHAP) identified influential predictors and their directional contributions; performance was summarised with area-under-the-curve (AUC). RESULTS: Overall model performance was adequate (AUC = 0.77) and similar across racial/ethnic groups (AUCs = 0.72-0.77). Across the full sample and race/ethnicity-stratified models, suicide risk was dominated by shared transdiagnostic and non-transdiagnostic phenotypes. The rank order of variable importance was higher neuroticism, emotion-regulation difficulties, irritability/anger, trauma-related shame and moral injury, internalizing symptoms, adverse childhood experiences and difficulty transitioning out of the military. Group-specific predictors (e.g. neighbourhood disadvantage, substance use patterns and minority-stress exposures) added meaningful signal. CONCLUSION: Interpretable ML in an intentionally diverse veteran cohort identifies a robust, shared suicide-risk profile with contextually distinct amplifiers across race/ethnicity.

Epidemiology and Psychiatric SciencesVol. 35
University of Southern California (US), RAND Corporation (US), King's College London (GB), Washington University in St. Louis (US)
National Institute on Alcohol Abuse and Alcoholism
Good health and well-being, Reduced inequalities
Suicide and Self-Harm Studies
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon