Search

Suicide rates among recent veterans have led to interest in risk identification. Evidence of gender-and trauma-specific predictors of suicidal ideation necessitates the use of advanced computational methods capable of elucidating these important and complex associations. In this study, we used machine learning to examine gender-specific associations between predeployment and military factors, traumatic deployment experiences, and psychopathology and suicidal ideation (SI) in a national sample of veterans deployed during the Iraq and Afghanistan conflicts (n = 2,244). Classification, regression tree analyses, and random forests were used to identify associations with SI and determine their classification accuracy. Findings converged on several associations for men that included depression, posttraumatic stress disorder (PTSD), and somatic complaints. Sexual harassment during deployment emerged as a key factor that interacted with PTSD and depression and demonstrated a stronger association with SI among women. Classification accuracy for SI presence or absence was good based on the receiver operating characteristic area under the curve, men = .91, women = .92. The risk for SI was classifiable with good accuracy, with associations that varied by gender. The use of machine learning analyses allowed for the discovery of rich, nuanced results that should be replicated in other samples and may eventually be a basis for the development of gender-specific actuarial tools to assess SI risk among veterans. [ABSTRACT FROM AUTHOR]

The 4-item Hurt/Insult/Threaten/Scream (HITS) tool accurately detects past-year intimate partner violence (IPV) among female Veterans Health Administration (VHA) patients; however, it lacks a sexual IPV item. This study evaluated the accuracy of an extended HITS (E-HITS), which adds a sexual IPV item, in female VHA patients. A sample of 80 female U.S. veteran VHA patients in New England completed a mail survey (50.0% response rate) that included the 5-item E-HITS and the Revised Conflict Tactics Scales (CTS-2). Women were included if they were in an intimate relationship in the past year. The women averaged 49 years of age and 86.0% of the sample was White. Accuracy of the 4-item HITS was compared to the 5-item E-HITS, using the CTS-2 as the reference. There were 20 women (25.0%) who reported past-year IPV on the CTS-2. The receiver operator characteristic curves demonstrated that the HITS and E-HITS performed nearly identically at their optimal cutoff scores of 6 and 7, respectively. At these cutoff scores, the sensitivity of both tools was .75, 95% CI [.55, .95]. The specificities were similar; .83 for the HITS, 95% CI [.73, .92], and .82 for the E-HITS, 95% CI [.72, .90]. Including a sexual IPV item may be clinically beneficial; it also attains the same accuracy of case identification as the HITS. [ABSTRACT FROM AUTHOR]