Identification and validation of an explainable screening model of college students' mental health with therapeutic...

Mental health issues, especially depressive symptoms, among young adults represent a public health challenge. Conventional psychological assessment tools have limited sensitivity and specificity for identifying individuals at risk. This study aims to develop an explainable machine learning-based model to stratify concurrent depression risk in young adults. This study included 100,257 college students and collected mental health variables including depression, anxiety, resilience, parent-child relationship, and duration of mobile phone usage. The screening capabilities of 13 machine learning algorithms were systematically evaluated and compared. The SHapley Additive exPlanations (SHAP) framework was employed for the interpretability of the final model. The median scores for parent-child relationship, resilience, anxiety, and mobile phone usage time was 42.0, 28.0, 1.0 and 28.0, respectively. Among the 13 machine learning algorithms, the XGBoost model demonstrated superior performance. The final multivariate screening model achieved an area under the curve (AUC) of 0.887, a sensitivity of 0.787, a specificity of 0.830, and an accuracy of 0.816 in classifying young adults' concurrent depression risk. The SHAP analysis showed the importance of each variable: anxiety (2.303) > resilience (0.774) > parent-child relationship (0.708) > mobile phone usage time (0.411). The final multivariate model exhibited stable performance during cross-validation (AUC = 0.885 ± 0.032), significantly better than the single-variable model (P < 0.001) and better screening reliability (Brier score 0.153). The final multivariate XGBoost model provides a highly accurate and interpretable approach for young adults' depression risk stratification. As the model was developed using cross-sectional data collected during the COVID-19 campus lockdown, prospective validation is required before clinical deployment. Notably, anxiety level emerged as the most influential risk factor, and resilience demonstrated a significant protective effect.