TY  - JOUR
PY  - 2023//
TI  - A practical risk calculator for suicidal behavior among transitioning U.S. Army soldiers: results from the Study to Assess Risk and Resilience in Servicemembers-Longitudinal Study (STARRS-LS)
JO  - Psychological medicine
A1  - Kearns, Jaclyn C.
A1  - Edwards, Emily R.
A1  - Finley, Erin P.
A1  - Geraci, Joseph C.
A1  - Gildea, Sarah M.
A1  - Goodman, Marianne
A1  - Hwang, Irving
A1  - Kennedy, Chris J.
A1  - King, Andrew J.
A1  - Luedtke, Alex
A1  - Marx, Brian P.
A1  - Petukhova, Maria V.
A1  - Sampson, Nancy A.
A1  - Seim, Richard W.
A1  - Stanley, Ian H.
A1  - Stein, Murray B.
A1  - Ursano, Robert J.
A1  - Kessler, Ronald C.
SP  - ePub
EP  - ePub
VL  - ePub
IS  - ePub
N2  - BACKGROUND: Risk of suicide-related behaviors is elevated among military personnel transitioning to civilian life. An earlier report showed that high-risk U.S. Army soldiers could be identified shortly before this transition with a machine learning model that included predictors from administrative systems, self-report surveys, and geospatial data. Based on this result, a Veterans Affairs and Army initiative was launched to evaluate a suicide-prevention intervention for high-risk transitioning soldiers. To make targeting practical, though, a streamlined model and risk calculator were needed that used only a short series of self-report survey questions. <br><br>METHODS: We revised the original model in a sample of n = 8335 observations from the Study to Assess Risk and Resilience in Servicemembers-Longitudinal Study (STARRS-LS) who participated in one of three Army STARRS 2011-2014 baseline surveys while in service and in one or more subsequent panel surveys (LS1: 2016-2018, LS2: 2018-2019) after leaving service. We trained ensemble machine learning models with constrained numbers of item-level survey predictors in a 70% training sample. The outcome was self-reported post-transition suicide attempts (SA). The models were validated in the 30% test sample. <br><br>RESULTS: Twelve-month post-transition SA prevalence was 1.0% (s.e. = 0.1). The best constrained model, with only 17 predictors, had a test sample ROC-AUC of 0.85 (s.e. = 0.03). The 10-30% of respondents with the highest predicted risk included 44.9-92.5% of 12-month SAs. <br><br>CONCLUSIONS: An accurate SA risk calculator based on a short self-report survey can target transitioning soldiers shortly before leaving service for intervention to prevent post-transition SA.<p />  <p>Language: en</p>
LA  - en
SN  - 0033-2917
UR  - http://dx.doi.org/10.1017/S0033291723000491
ID  - ref1
ER  -