Predicting mental health risk in adolescents using interpretable machine learning: Evidence from SHAP analysis
- 1College of Physical Education, Shanghai Normal University, Shanghai, China.
Abstract
Background/Objective: Adolescent mental health is a critical public health concern; however, the combined contribution of emotional, demographic, and behavioral factors to poor mental health remains incompletely understood. This study applied an interpretable machine learning framework to identify key predictors of elevated mental health risk among adolescents and characterize their relative and non-linear contributions. Methods: Data were drawn from the 2021 Youth Risk Behavior Survey (YRBS), comprising 16,946 U.S. high school students. Elevated mental health risk was defined using the YRBS current mental health item (Q85): reporting that mental health was not good most of the time or always during the past 30 days. The distinct 12-month sadness/hopelessness item (Q25) was retained as a predictor in the primary XGBoost model. The operating threshold was selected by maximizing the Youden index using five-fold out-of-fold predictions in the training set and was then locked before evaluation in the held-out test set. SHapley Additive exPlanations (SHAP) were used to assess feature importance and directional and non-linear patterns. Results: Overall, 28.0% of adolescents were classified as having elevated mental health risk, with higher prevalence among females (39.9% vs. 16.9%) and peak prevalence at ages 16–17. The primary XGBoost model achieved an AUC of 0.806 and PR-AUC of 0.603. At the training-derived threshold of 0.285, accuracy was 0.749, sensitivity 0.754, specificity 0.747, and balanced accuracy 0.750. SHAP analysis identified sadness/hopelessness as the dominant predictor, followed by sex, sleep duration, screen time, and breakfast frequency. In a sensitivity analysis excluding sadness/hopelessness, discrimination decreased (AUC 0.736; PR-AUC 0.510). Conclusion: The revised primary model achieved balanced sensitivity and specificity above 0.700 using a threshold selected entirely within the training data. Sadness/hopelessness was the strongest predictor, while demographic and behavioral factors provided additional predictive information. Because sadness/hopelessness is conceptually close to the current mental health outcome and the data are cross-sectional, the model should be interpreted as an auxiliary risk-stratification tool rather than a standalone clinical screening or diagnostic instrument.
Related
- Multiscale Nonlinear Risk Transmission in the Carbon–Fossil Energy–Clean Energy System from a Fractal-Market Perspective: Evidence from EMD–TVP-VAR and Interpretable Machine Learning
- Mastering Model Fit: Applications of the InterModel Vigorish for Interpretable Machine Learning
- Null importance: Disentangling relevance for interpretable machine learning
- Comparative Analysis of Machine Learning Algorithms for Predicting Difficulty Disengaging from Social Media Among Students
- Predicting Backup Non-Compliance Using KPI-Derived Labels and Machine Learning: A Proof-of-Concept Study
BibTeX
@article{he2026predicting,
title = {{Predicting mental health risk in adolescents using interpretable machine learning: Evidence from SHAP analysis}},
author = {Jinsheng He},
journal = {PLOS One},
year = {2026},
month = oct,
doi = {10.1371/journal.pone.0359233},
url = {https://doi.org/10.1371/journal.pone.0359233},
note = {CC BY},
}
RIS
TY - JOUR
TI - Predicting mental health risk in adolescents using interpretable machine learning: Evidence from SHAP analysis
AU - Jinsheng He
PY - 2026
DA - 2026/10/21
JO - PLOS One
DO - 10.1371/journal.pone.0359233
UR - https://doi.org/10.1371/journal.pone.0359233
AB - Background/Objective: Adolescent mental health is a critical public health concern; however, the combined contribution of emotional, demographic, and behavioral factors to poor mental health remains incompletely understood. This study applied an interpretable machine learning framework to identify key predictors of elevated mental health risk among adolescents and characterize their relative and non-linear contributions. Methods: Data were drawn from the 2021 Youth Risk Behavior Survey (YRBS), comprising 16,946 U.S. high school students. Elevated mental health risk was defined using the YRBS current mental health item (Q85): reporting that mental health was not good most of the time or always during the past 30 days. The distinct 12-month sadness/hopelessness item (Q25) was retained as a predictor in the primary XGBoost model. The operating threshold was selected by maximizing the Youden index using five-fold out-of-fold predictions in the training set and was then locked before evaluation in the held-out test set. SHapley Additive exPlanations (SHAP) were used to assess feature importance and directional and non-linear patterns. Results: Overall, 28.0% of adolescents were classified as having elevated mental health risk, with higher prevalence among females (39.9% vs. 16.9%) and peak prevalence at ages 16–17. The primary XGBoost model achieved an AUC of 0.806 and PR-AUC of 0.603. At the training-derived threshold of 0.285, accuracy was 0.749, sensitivity 0.754, specificity 0.747, and balanced accuracy 0.750. SHAP analysis identified sadness/hopelessness as the dominant predictor, followed by sex, sleep duration, screen time, and breakfast frequency. In a sensitivity analysis excluding sadness/hopelessness, discrimination decreased (AUC 0.736; PR-AUC 0.510). Conclusion: The revised primary model achieved balanced sensitivity and specificity above 0.700 using a threshold selected entirely within the training data. Sadness/hopelessness was the strongest predictor, while demographic and behavioral factors provided additional predictive information. Because sadness/hopelessness is conceptually close to the current mental health outcome and the data are cross-sectional, the model should be interpreted as an auxiliary risk-stratification tool rather than a standalone clinical screening or diagnostic instrument.
SN - 1932-6203
ER -