Using a machine learning analysis of socio-ecological and psychological factors to predict suicide risk among a nationally representative sample of Ghanaian adolescents

<i>Background.</i> Despite the growing recognition of adolescent suicide as a pressing concern, traditional methods for identifying suicide risk often fail to capture the complex interplay of socio-ecological and psychological factors. The advent of machine learning (ML) offers a transformative opportunity to improve suicide risk prediction and intervention strategies. <i>Objective.</i> This study aims to utilize ML techniques to analyze socio-ecological and psychological risk factors to predict suicide ideation, plans and attempts among a nationally representative sample of Ghanaian adolescents. <i>Methods.</i> A cross-sectional survey was conducted with 1,703 adolescents aged 12-18 years across Ghana measuring psychological factors (depression symptoms, anxiety symptoms etc) and socio-ecological factors (bullying, parental support etc) using validated measures. Descriptive statistics were conducted and random forest and logistic regression models were employed for suicide risk prediction, i.e., 'ideation, plans and attempts'. Model performance was evaluated using accuracy, sensitivity, specificity and feature importance analysis. <i>Results.</i> Psychological factors such as depression symptoms (<i>r</i> = .42, <i>p</i> < .01), anxiety (<i>r</i> = .38, <i>p</i> < .01) and perceived stress (<i>r</i> = .35, <i>p</i> < .01) were the strongest predictors of suicide ideation, plans and attempts, while parental support emerged as a significant protective factor (<i>r</i> = -.34, <i>p</i> < .01). The random forest model demonstrated good predictive performance (accuracy = 78.3%, AUC = 0.81). Gender differences were observed. <i>Conclusions.</i> This study is the first to apply ML techniques to a nationally representative dataset of Ghanaian adolescents for suicide risk prediction, i.e., 'ideation, plans and attempts'. The findings highlight the potential of ML to provide precise tools for early identification of at-risk individuals.