Predictors of depression among Chinese college students: a machine learning approach.

BACKGROUND

Depression is highly prevalent among college students, posing a significant public health challenge. Identifying key predictors of depression is essential for developing effective interventions. This study aimed to analyze potential depression risk factors among Chinese college students using the Random Forest Algorithm (RFA) and to explore gender differences in risk patterns.

METHODS

A cross-sectional study was conducted with 10,043 undergraduate students from Guizhou Normal University. Thirty-three variables were analyzed using RFA. Depressive symptoms were assessed using the Center for Epidemiologic Studies Depression Scale (CES-D), with a score of ≥ 16 indicating depression risk. The variables included sociodemographic characteristics, physical and psychological health indicators, behavioral and lifestyle factors, socioeconomic conditions, and family mental health history.

RESULTS

The RFA identified several factors associated with depression risk, with suicidal ideation, anxiety, and sleep quality exhibiting the strongest associations. Other significant predictors included academic stress, BMI, vital capacity, psychological resilience, physical fitness test scores, major satisfaction, and social network use. The model achieved an accuracy of 87.5% and an AUC of 0.927. Gender-stratified analysis suggested different patterns: physical fitness indicators showed stronger associations with depression risk among male students, while BMI was more strongly associated with depression risk among female students.

CONCLUSIONS

This cross-sectional study identified factors associated with depression risk among Chinese college students, with psychological factors showing the strongest associations. Gender-specific patterns were observed, suggesting the importance of considering gender differences when developing mental health interventions. However, longitudinal studies are required to establish causal relationships and validate these findings through intervention trials.