An Evidence-Based Integrated Framework for College Student Mental Health Monitoring and Precision Intervention Using Multi-Source Big Data

Abstract

College student mental health issues are rising, but traditional assessments lack timeliness and objectivity. Leveraging campus digitalization, this study proposed an end-to-end “prediction–interpretation–intervention” framework addressing multisource data heterogeneity, poor interpretability, and ethical concerns. A macro–micro dual-scale pipeline integrated psychological, behavioral, and physiological data. An evidence-based model combining causal inference and attention mechanisms boosted prediction accuracy and explainability; t-distributed stochastic neighbor embedding and clustering revealed three risk subgroups, enabling tiered interventions. The model achieved 0.812 average precision, remained robust under data perturbations, and pilot interventions significantly reduced depressive symptoms and improved health behaviors in high-risk students. This framework bridged data-driven prediction and actionable support, offering a scalable, ethical solution for campus mental health management.