Development and Internal Validation of a Model for Predicting Internet Gaming Disorder Risk in Adolescents and...

Area of Science:

• Psychiatry
• Public Health
• Digital Health

Background:

• Internet gaming disorder (IGD) poses a significant public health concern due to its high prevalence and severe consequences in children and adolescents.
• There is an urgent need for efficient and cost-effective early detection methods for IGD.

Purpose of the Study:

• To develop and internally validate a nomogram model for predicting Internet gaming disorder risk in Chinese children and adolescents.
• To provide reliable tools for early screening and personalized treatment planning.

Main Methods:

• An online survey collected data from 780 adolescents aged 7-18 years.
• Least absolute shrinkage and selection operator regression identified key predictors, followed by multivariate logistic regression to build prediction models.
• Model performance was evaluated using ROC curves, calibration plots, and decision curve analysis, with bootstrapping for internal validation.

Main Results:

• Male sex and prior game consumption experience were identified as significant predictors of IGD.
• Both developed models demonstrated strong predictive discrimination (Area Under Curve >0.80) and good calibration.
• Decision curve analysis indicated clinical utility for both nomograms within a 5-75% intervention probability range.

Conclusions:

• Two nomogram-based prediction models serve as effective tools for screening Internet gaming disorder in young populations.
• Model 2 is recommended as a more simplified and cost-effective option for clinical application.
• These models can aid clinicians in personalizing treatment strategies for adolescents with IGD.