Skip to main content
ABCT 2025 59th Annual Convention Main banner
Psychology Tools Ad
Final Program


Icon Legend
This session is not in your schedule.
This session is in your schedule. Click again to remove it.
Presentation Icons
Recorded Session
Recorded Session
Ticketed Session
Ticketed Session
ViewAttendees 3

Symposia

Suicide and Self-Injury

Advancing Suicide Risk Assessment for Veterans: Leveraging AI, Assessing Novel Risks, and Developing New Strategies for Risk Management of Veteran Suicide

1 - (SYM 30) Suicide Risk Prediction Modeling in Veterans Experiencing Homelessness And/or Criminal-legal Involvement

Saturday, November 22, 2025
10:03 AM - 10:22 AM CST
Location: Celestin G, Level 3
Keywords: Suicide, Risk / Vulnerability Factors, Assessment
Recommended Readings: Litschi, M. A., Lancaster, S. L., Linkh, D. J., Renno, S., Neal‐Walden, T. A., Lawless, C. E., & Breetz, A. A. (2024). Evaluating suicide risk stratification in outpatient settings: A vignette‐based approach. Clinical Psychology & Psychotherapy, 31(2), e2965. https://doi.org/10.1002/cpp.2965,   Edwards, E. R., Fortuna, A., Holliday, R., Addison, H., & Tsai, J. (2024). Prevalence of mental health conditions, substance use disorders, suicidal ideation and attempts, and experiences of homelessness among Veterans with criminal-legal involvement: A meta-analysis. Clinical Psychology Review, 102533. https://doi.org/10.1016/j.cpr.2024.102533,   Matarazzo, B. B., Eagan, A., Landes, S. J., Mina, L. K., Clark, K., Gerard, G. R., ... & Reger, M. A. (2023). The Veterans Health Administration REACH VET program: suicide predictive modeling in practice. Psychiatric services, 74(2), 206-209. https://doi.org/10.1176/appi.ps.2021006,   ,  
Abstract Body
In 2021, the suicide rate for US military Veterans was approximately 34 per 100,000, more than double that of US civilian adults. To better address this suicide crisis, high-risk Veteran subgroups have been identified to guide targeted suicide-prevention efforts, including Veterans experiencing criminal-legal involvement (150 per 100,000) and/or homelessness (112 per 100,000; H/CLI). About 30% of US suicide deaths occur within two years of incarceration, and 1% occur during a period of homelessness.
Despite their exceptionally elevated risk, little is known about the phenomenology of suicide among Veterans experiencing H/CLI. A recent meta-analysis on Veterans with criminal-legal involvement identified only 11 samples examining suicide-related outcomes. Similarly, a systematic review of studies on self-directed violence among Veterans experiencing homelessness identified only 19 relevant studies. This limited literature is also largely redundant, routinely documenting elevated rates of suicidal ideation and attempts, though offering minimal insight or direction to guide suicide prevention.
Advancements in machine learning allow for increased nuance and precision in suicide risk prediction. However, prediction models commonly have disparate accuracy across population subgroups with accuracy typically highest when applied to subgroups similar to samples used in model development. Despite various efforts to build risk prediction models to identify risk for suicide in the broader Veteran population, applicability of these models to Veterans experiencing H/CLI is unexplored.
This presentation will review results of a currently ongoing analysis using machine learning and VA medical record system data to develop and compare statistical risk prediction models for suicide attempts and deaths occurring within six months of a VA suicide risk assessment among Veterans experiencing and not experiencing H/CLI. Results promise to provide pivotal insights into potentially unique suicide risk management needs of this population and will be used to guide development, refinement, and dissemination of suicide prevention efforts within and outside the VA.