Suicide is a leading cause of death that defies prediction and challenges prevention efforts worldwide. Artificial intelligence (AI) and machine learning (ML) have emerged as a means of investigating large datasets to enhance risk detection. A systematic review of ML investigations evaluating suicidal behaviors was conducted using PubMed/MEDLINE, PsychInfo, Web-of-Science, and EMBASE, employing search strings and MeSH terms relevant to suicide and AI. Databases were supplemented by hand-search techniques and Google Scholar. Inclusion criteria: (1) journal article, available in English, (2) original investigation, (3) employment of AI/ML, (4) evaluation of a suicide risk outcome. N = 594 records were identified based on abstract search, and 25 hand-searched reports. N = 461 reports remained after duplicates were removed, n = 316 were excluded after abstract screening. Of n = 149 full-text articles assessed for eligibility, n = 87 were included for quantitative synthesis, grouped according to suicide behavior outcome. Reports varied widely in methodology and outcomes. Results suggest high levels of risk classification accuracy (>90%) and Area Under the Curve (AUC) in the prediction of suicidal behaviors. We report key findings and central limitations in the use of AI/ML frameworks to guide additional research, which hold the potential to impact suicide on broad scale.

Family factors, such as poor family functioning and trauma, have been associated with negative outcomes for homeless adolescents. Further study is needed to better understand how family factors and trauma jointly relate to mental health problems and externalizing behaviors among homeless adolescents. Structural equation modeling was used to examine the influence of trauma (encompassing traumatic events experienced prior to, and after, becoming homeless) and family factors (poor family functioning and family conflict) on mental health problems and externalizing behaviors (substance use, delinquent behaviors, and sexual risk) among 201 homeless adolescents, ages 12 to 17 years. Trauma, poor family functioning, and family conflict significantly predicted greater mental health problems, delinquent behaviors, high-risk sexual behaviors and substance use. Overall, the findings suggest that family factors appear to be key to understanding mental health problems and externalizing behaviors among homeless adolescents. Implications, limitations and future directions are addressed.

No abstract