Identification and validation of an explainable screening model of college students’ mental health with therapeutic strategy implications
5 affiliations
- 1School of Chemistry and Biological Engineering, University of Science and Technology, Beijing
- 2School of Government, Beijing Normal University
- 3National Institute on Drug Dependence, Beijing Key Laboratory of Innovative Intervention Techniques and Translational Research for Mental Disorders Rehabilitation, Peking University
- 4School of Sociology, Beijing Normal University
- 5Hefei Fourth People’s Hospital, Anhui Mental Health Center, Affiliated Mental Health Center of Anhui Medical University
Abstract
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.
Related
- The application of explainable machine learning for the identification of MASLD in non-obese populations
- Biomechanical and movement-quality predictors of lower-limb load-related injury in collegiate athletes: a prospective cohort study using functional movement screening, wearable inertial sensing, and explainable machine learning
- Multicenter validation of an explainable machine-learning model for APL, AMoL, and ALL
- Development and internal temporal validation of an explainable XGBoost model for predicting clinical pregnancy after frozen embryo transfer
- Development and validation of an explainable machine learning-based risk prediction model for macrosomia in han Chinese women with singleton cephalic pregnancies
BibTeX
@article{liu2026identification,
title = {{Identification and validation of an explainable screening model of college students’ mental health with therapeutic strategy implications}},
author = {Ke Liu and Zhe Li and Yu-Yu Zhao and Xin Li and Zi-Chun Guan and Dong-Hua Tian and Su-Xia Li and Xiang-Yang Zhang},
journal = {Scientific Reports},
year = {2026},
month = jul,
doi = {10.1038/s41598-026-63087-w},
url = {https://doi.org/10.1038/s41598-026-63087-w},
note = {CC BY},
}
RIS
TY - JOUR
TI - Identification and validation of an explainable screening model of college students’ mental health with therapeutic strategy implications
AU - Ke Liu
AU - Zhe Li
AU - Yu-Yu Zhao
AU - Xin Li
AU - Zi-Chun Guan
AU - Dong-Hua Tian
AU - Su-Xia Li
AU - Xiang-Yang Zhang
PY - 2026
DA - 2026/07/01
JO - Scientific Reports
DO - 10.1038/s41598-026-63087-w
UR - https://doi.org/10.1038/s41598-026-63087-w
AB - 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.
SN - 2045-2322
ER -