To develop and validate a risk prediction model for smartphone addiction among college students and identify key factors associated with this behavior.
Approach:
Survey Methodology: A cross-sectional survey was conducted among 2,761 college students using the XGBoost machine learning algorithm to analyze the dataset.
Data Analysis: The XGBoost model identified variables associated with smartphone addiction and ranked their contributions based on feature importance scores.
Key Findings:
The prevalence of smartphone addiction among college students was approximately 22.24%.
Key predictors of smartphone addiction included loneliness (0.437), monthly household income (0.067), age (0.056), and place of residence (0.056).
Interpretation:
Limitations:
The study relied on self-reported data, which may be subject to bias.
The cross-sectional design limits causal inferences.
Longer initial prescriptions, use of multiple benzodiazepines, and long-acting agents were associated with delayed discontinuation in a retrospective population-based cohort study.
