5-year incidence of suicide-risk in youth: A gradient tree boosting and SHAP study

• Published in: Journal of affective disorders 2021-12, Vol.295, p.1049-1056
• Main Authors: Ballester, Pedro L., Cardoso, Taiane de A., Moreira, Fernanda Pedrotti, da Silva, Ricardo A., Mondin, Thaíse Campos, Araujo, Ricardo M., Kapczinski, Flavio, Frey, Benicio N., Jansen, Karen, de Mattos Souza, Luciano D.
• Format: Article
• Language: English
• Subjects: Machine learning; Prospective cohort; Suicide risk; Youth
• ISSN: 0165-0327; 1573-2517
• DOI: 10.1016/j.jad.2021.08.033

•Variables such as female sex, lower socioeconomic status, older age, not studying, common mental disorder symptoms, and poor quality of life were risk factors for suicide risk.•Clinicians may detect suicide risk early by looking at the signs of poor mental health and quality of life among individuals.•The interaction between sociodemographic status and overall health when modeling suicide risk is substantial as sociodemographic status shifts from a risk to a protective factor as overall health increases. Machine learning methods for suicidal behavior so far have failed to be implemented as a prediction tool. In order to use the capabilities of machine learning to model complex phenomenon, we assessed the predictors of suicide risk using state-of-the-art model explanation methods. Prospective cohort study including a community sample of 1,560 young adults aged between 18 and 24. The first wave took place between 2007 and 2009, and the second wave took place between 2012 and 2014. Sociodemographic and clinical characteristics were assessed at baseline. Incidence of suicide risk at five-years of follow-up was the main outcome. The outcome was assessed using the Mini Neuropsychiatric Interview (MINI) at both waves. The risk factors for the incidence of suicide risk at follow-up were: female sex, lower socioeconomic status, older age, not studying, presence of common mental disorder symptoms, and poor quality of life. The interaction between overall health and socioeconomic status in relation to suicide risk was also captured and shows a shift from protection to risk by socioeconomic status as overall health increases. Proximal factors associated with the incidence of suicide risk were not assessed. Our findings indicate that factors related to poor quality of life, not studying, and common mental disorder symptoms of young adults are already in place prior to suicide risk. Most factors present critical non-linear patterns that were identified. These findings are clinically relevant because they can help clinicians to early detect suicide risk.