A machine learning algorithm-based model for predicting the risk of non-suicidal self-injury among adolescents in western China: A multicentre cross-sectional study

Abstract

The prevalence of non-suicidal self-injurious (NSSI) in adolescents is high. However, few studies exist to predict NSSI in this population. This study employed a machine learning algorithm to develop a predictive model, aiming to more accurately assess the risk of NSSI in Chinese adolescents. Sociodemographic, psychological data were collected in 50 schools in western China. We constructed eXtreme Gradient Boosting (XGBoost) model and multivariate logistic regression model to predict the risk of NSSI and nomograms are plotted. Data from 13,304 adolescents were used for model development, with an average age of 13.00 ± 2.17 years; 617 individuals (4.6 %) reported non-suicidal self-injury (NSSI) behaviors. The results of the XGBoost model showed that depression and anxiety were the top two predictors of NSSI in adolescents. The results of the multivariate logistic regression model showed that the risk factors for adolescent NSSI behaviors include: gender (being female), Age, Living with whom (father), History of psychiatric consultation, Stress, Depression, Anxiety, Tolerance, Emotion abreaction. The XGBoost prediction and multivariate logistic regression model showed good predictive ability. Nomograms can serve as clinical tools to assist in intervention measures, helping adolescents reduce NSSI behaviors and improve their mental and physical well-being.

Keywords: Adolescence; Machine learning; Non suicidal self injury; Predictive models; eXtreme gradient boosting.