Description/Abstract

The risk of suicide-related behaviors rises during the transition from military to civilian life. A prior study demonstrated the ability to identify high-risk U.S. Army soldiers pre-transition through a machine learning model considering administrative data, self-reports, and geospatial info. This led to a collaboration between Veterans Affairs and the Army to assess a tailored suicide prevention intervention. To streamline targeting, researchers aimed to develop a concise risk calculator using self-report surveys. The refined model was tested on 8335 individuals from the Study to Assess Risk and Resilience in Servicemembers-Longitudinal Study (STARRS-LS), including baseline and post-service surveys. Results showed around 1.0% prevalence of self-reported suicide attempts within a year post-transition. The effective constrained model, with 17 predictors, achieved a 0.85 test sample ROC-AUC. By targeting the top 10-30% at highest risk, the model encompassed 44.9% to 92.5% of individuals reporting suicide attempts within a year after transition. the study created an accurate risk calculator from succinct self-reports. This tool identifies high-risk transitioning soldiers before leaving, enabling timely intervention to prevent post-transition suicide attempts and highlights the need for targeted support for transitioning U.S. service members (TSMs) as most current support is universal and lacks focus on individuals with the greatest need.

Document Type

Brief

Disciplines

Military and Veterans Studies

Extent

2 pages

DCMI Type

Text

Keywords

Machine learning, Suicide attempt, Suicide prevention, Veterans

Publisher

Institute for Veterans and Military Families at Syracuse University

Date

8-2023

Language

English

Creative Commons License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.

Comments

Accessible document added 9/11/2023

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.