J Affect Disord. 2026 Sep 13:122495. doi: 10.1016/j.jad.2026.122495. Online ahead of print.
ABSTRACT
BACKGROUND: Internet Gaming Disorder (IGD) poses significant psychological and social risks for adolescents. Its development involves complex interactions among early adversity, negative life events, psychological symptoms, and regulatory emotional self-efficacy, yet relative importance of these factors and their interrelationships remain incompletely understood.
OBJECTIVE: To identify the key demographic and psychosocial factors associated with adolescent IGD, quantify their relative contributions to IGD risk, and characterize the interrelationships among these factors.
METHOD: Four machine learning algorithms were used to develop classification models among 6573 adolescents. Model performance was comprehensively evaluated using ROC-AUC, PR-AUC, threshold-based metrics, Brier score and DCA. SHAP analysis ranked feature contributions and their directional associations with IGD symptoms, followed by network analysis to examine their interrelationships and to identify central factors.
RESULT: The random forest model was selected as the final model for subsequent analyses. SHAP analysis ranked the selected features by their contribution as follows: gender, depression symptoms, insomnia, social anxiety, emotional abuse, health adaptation problems, anxiety symptoms, academic stress, punishment experiences, and regulating despondency/distress. Network analysis further revealed that anxiety, academic stress, and health adaptation functioned as the central nodes, with the strongest positive edges between health adaptation and punishment experiences, and between depression and anxiety.
CONCLUSION: The findings highlight the relevance of psychological distress, health adaptation problems, early-life adversity, and stress-related factors in adolescent IGD. Considering both the relative contribution of individual factors and their interrelationships may facilitate a more comprehensive understanding of psychosocial vulnerability to IGD and inform early risk identification.
PMID:42732833 | DOI:10.1016/j.jad.2026.122495
