Mental Health Issues and 24-Hour Movement Guidelines-Based Intervention Strategies for University Students With High-Risk Social Network Addiction: Cross-Sectional Study Using a Machine Learning Approach.

Background: The exponential growth of digital technologies and the ubiquity of social media platforms have led to unprecedented mental health challenges among college students, highlighting the critical need for effective intervention approaches.

Objective: This study aimed to explore the relationship between meeting the 24-hour movement guidelines (24-HMG) health behavior combinations and the risk of social network addiction (SNA) as well as mental health issues among university students. It further sought to compare differences in mental health indicators and SNA levels across various risk groups and adherence patterns, and to identify the optimal 24-HMG health behavior intervention strategies for students at high risk of SNA.

Methods: This cross-sectional study recruited a total of 12,541 university students from the university town of Guizhou Province as participants. Data were collected through standardized questionnaires, including the Chinese version of Social Network Addiction Scale for College Students (SNAS-C), the adult attention-deficit/hyperactivity disorder (ADHD) self-report scale (ASRS), and the Chinese version of the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition (DSM-5) Self-Report Level 1 Cross-Cutting Symptom Measure for Adults (DSM-5 CCSM), among others. The primary analytical method used was the random forest model, which was used to explore the relationship between different 24-HMG behavior combinations and mental health variables among student at high-risk of SNA. In addition, the study aimed to identify the optimal 24-HMG health behavior intervention strategies for this high-risk group.

Results: Participants in the meeting none group exhibited the highest SNA scores (57.98), which declined progressively with greater adherence. Among single-guideline groups, meeting physical activity (PA; 53.07) and meeting sedentary time (ST; 52.72) showed similar scores. Further reductions were seen in meeting PA+ST (49.68), meeting sleep (48.44), and meeting ST+sleep (44.75), with the lowest in meeting PA+ST+sleep. Approximately 6% of the variance in SNA was attributable to differences in adherence patterns (η²=0.06). Students meeting all three 24-HMG components-PA, sleep, and ST-demonstrated the strongest protection against attention deficit, depression, and anxiety. All 24-HMG behaviors were inversely associated with mental health symptoms, except academic satisfaction, which was positively correlated. Random forest modeling identified meeting sleep+ST as the most impactful for mania (0.4491), sleep disturbance (0.4032), personality (0.3924), and dissociation (0.3832). Meeting ST alone showed the strongest effects on substance (0.6176) and alcohol use (0.6597). Depression was influenced by meeting sleep+ST (0.2053), meeting PA+ST+sleep (0.1650), and meeting PA+ST (0.1634). The model achieved high accuracy for ASRS (0.912; F1-score=0.927), with robust predictions for substance use (F1-score=0.873) and mania (F1-score=0.836).

Conclusions: Adherence to the health behaviors recommended by the 24-HMG can significantly improve the mental health outcomes of university students at high risk for SNA. The findings of this study support the development of mental health intervention strategies for students at high-risk of SNA based on the 24-HMG framework.