Editorial: Disrupting Pathways to Self-Harm in Adolescence: Machine Learning as an Opportunity

Abstract

Self-harm, hurting oneself with or without suicidal intent, is associated with poor mental health. Domains of risk known to be associated with self-harm include sociodemographic factors such as female gender, negative life events, family adversity, and psychiatric diagnoses.¹ However, the heterogeneous nature of self-harm makes predicting risk and prevention challenging. The behaviors can be occasional or repetitive, suicidal in nature or not. Only about half of youths with deliberate self-harm present significant suicide risk.¹ We are left with these remaining questions: What are the early signs of risk for self-harm? Who are the children and adolescents most at risk? Machine learning is the scientific discipline that focuses on how computers learn from data with efficient computing algorithms and prediction models.² If we can use this analytic tool wisely, it could help us to predict risk of self-injury and offer prevention and treatment with precision. However, we need to be careful not to replicate the human biases that already permeate our health care system by failing to include data from diverse populations or considering the ways they are marginalized in building prediction models.