关键词: 自杀预测, 机器学习, 自杀叙事-危机模型, 大学生

Abstract: Suicide among college students has emerged as an increasingly urgent public health issue. Traditional statistical methods are often limited in handling high-dimensional predictors and complex interactions proposed by contemporary suicide theories, whereas existing machine learning studies frequently lack theoretical grounding and often focus on a single suicide-related outcome. To address these gaps, this study adopted the Narrative-Crisis Model of Suicide as a theoretical framework and developed separate predictive models for suicidal ideation, suicide plans, and suicide attempts, with the aim of comparing the predictive contributions of risk factors across these three concurrent suicide-related outcomes. Following feature importance analysis, simplified models were constructed and further evaluated in a same-school temporal validation sample. This study drew on two large-scale survey datasets collected from Chinese university students. In Dataset 1 (n = 5,296), baseline models were developed using 74 features primarily derived from the Narrative-Crisis Model of Suicide, supplemented by variables informed by related theoretical frameworks. Random Forest and Extreme Gradient Boosting were used for model training, with Random Forest selected for subsequent feature contribution analyses. To address class imbalance, the Synthetic Minority Over-sampling Technique (SMOTE) was applied. Model performance was evaluated across repeated runs using AUC, AUPRC, accuracy, precision, recall, specificity, and F1 score. Based on feature importance rankings, 16 variables were retained to construct simplified models, which were evaluated on both the internal hold-out test set and a same-school temporal validation sample collected at a later time point. The three suicide-related outcomes were assessed retrospectively over the same six-month period; therefore, the analyses were intended to compare concurrent outcome-specific predictive patterns rather than temporal transitions between suicidal ideation, planning, and attempts. The results showed distinct predictive patterns across the three suicide-related outcomes. Tobacco and alcohol use showed relatively greater predictive contributions in the suicide plan and suicide attempt models than in the suicidal ideation model, whereas interpersonal trauma, including verbal and relational bullying, emotional abuse, and domestic violence, showed relatively greater contributions in the suicidal ideation model. Variables related to suicide crisis syndrome, suicidal narratives, and self-harm behavior also ranked highly across the models. Despite a substantial reduction in the number of predictors, the simplified models maintained good discrimination and showed generally stable performance in the same-school temporal validation sample. Supplementary analyses further indicated that calibration remained imperfect and that decision-analytic performance varied across risk thresholds. Overall, the findings suggest that combining theory-informed variable selection with data-driven machine learning may help identify outcome-specific predictive patterns across suicidal ideation, suicide plans, and suicide attempts. The simplified feature set may provide a useful basis for further validation and refinement of suicide risk assessment models in college populations.

Key words: suicide prediction, machine learning, Narrative-Crisis Model of Suicide, college students