Machine learning identifies prominent risk factors for depressive symptoms among Chinese children and adolescents

¹Department of Psychiatry, Key Laboratory of Major Brain Disease and Aging Research (Ministry of Education), The First Affiliated Hospital of Chongqing Medical University, Chongqing, China.

Related Experiment Videos

View abstract on PubMed

Summary

Depressive symptoms affect nearly 30% of Chinese youth. Key prevention factors include psychological resilience, sleep, and family relationships.

Area of Science:

Background:

Identifying risk factors for child and adolescent depressive symptoms is critical for effective prevention strategies.
Limited research has comprehensively explored these risk factors in diverse populations.
This study addresses this gap by examining depressive symptom prevalence and ranking risk factors in Chinese children and adolescents.

Purpose of the Study:

To determine the prevalence of depressive symptoms in a large cohort of Chinese children and adolescents.
To identify and rank significant risk factors associated with depressive symptoms.
To establish a predictive model for depressive symptoms using machine learning techniques.

Main Methods:

A large-scale cross-sectional study involving 198,062 children and adolescents from Chongqing, China.
Assessment of depressive symptoms using the Center for Epidemiological Studies Depression Scale for Children.
Application of logistic regression and three machine learning methods (Random Forest, Random Ferns, Extreme Gradient Boosting) for risk factor identification and ranking.

Main Results:

The prevalence of depressive symptoms was found to be 29.6% in the study population.
Machine learning analysis identified nine key risk factors: psychological resilience, age, sleep satisfaction, self-expectations, gender, relationship with father, academic performance, relationship with classmates, and breakfast frequency.
A predictive model achieved a high Area Under the Curve (AUC) of 0.844, indicating strong predictive performance.

Conclusions:

Psychological resilience, age, sleep satisfaction, self-expectations, gender, father relationship, academic performance, peer relationships, and breakfast frequency are prominent risk factors for depressive symptoms in Chinese youth.
These identified factors should be prioritized in developing targeted prevention programs for child and adolescent depression.
The findings provide valuable insights for public health initiatives aimed at mitigating depressive symptoms in young populations.