Machine learning-based prediction of suicidality in adolescents during the COVID-19 pandemic (2020–2021): Derivation and validation in two independent nationwide cohorts

• We developed a machine learning model, which exhibited a solid predictive performance for suicidality to capture the risk of suicidal attempts. • This study represents the first instance of predicting suicidality among adolescents through two Asian-based large-scale cohorts. • Our model has a potential to make a significant impact on suicide prevention effort by improving risk assessment for at-risk adolescents.