Machine Learning Assessment of Early Life Factors Predicting Suicide Attempt in Adolescence or Young Adulthood

Source:

Navarro MC, Ouellet-Morin I, Geoffroy M, et al. Machine Learning Assessment of Early Life Factors Predicting Suicide Attempt in Adolescence or Young Adulthood. JAMA Netw Open. 2021;4(3):e211450. doi:10.1001/jamanetworkopen.2021.1450

Key Points

Question  Can early life factors (ie, in-utero, perinatal, infancy) be used to predict suicide attempt in adolescence or young adulthood?

Findings  In this prognostic study of 1623 children from a representative longitudinal cohort study, random forest algorithms, including 150 potential factors, found that early life factors modestly contributed to the prediction of suicide attempt in adolescence or young adulthood, with 24% to 44% better prediction than chance. The most informative factors include birth-related characteristics, family and parents’ characteristics, parents’ mental health, and parenting practices.

Meaning  These findings suggest that although early-life factors may contribute to understanding the etiological processes of suicide, their utility in the long-term prediction of suicide attempt was limited.