Effects of Digital Health Interventions on the Physical and Mental Health of Middle School Students

Overview

1\. Study Population 1. Sample Size: 20 classes, about 800-1000 children. 2. Randomization: This study will adopt a cluster-randomized controlled intervention design. 20 Classes will be randomly assigned in a 1:1:1:1 ratio to one of four groups: the graphic-text intervention group, the video intervention group, the AI dialogue intervention group, and the control group. The randomization process will be centralized and conducted by personnel not involved in the project. 3. Inclusion Criteria (all of the following must be met for inclusion): Both children/adolescents and their parents are willing to participate and demonstrate good compliance. Children/adolescents have a weight classified as normal, overweight, or obese. Age range: 11 to 13 years. Informed consent is obtained from both the child and the parent. 4. Exclusion Criteria (meeting any one of the following will result in exclusion): Clinically diagnosed severe mental illness or psychiatric disorders. Clinically diagnosed eating disorders (e.g., binge eating disorder). Physical developmental abnormalities or disabilities that prevent normal physical activity.

Intervention Content Control Group: The students did not receive any additional intervention and continued with their regular school activities. After the intervention, a complete set of video and graphic materials was provided to the control group students to ensure ethical fairness. Graphic-text Intervention Group: The students read the electronic version of the instruction manual on the computer screen in the computer room for about 10 minutes each week. Video Intervention Group: Students watch AI-produced videos on the computer screens in the computer room for about 10 minutes each week. The playback progress of the videos is uniformly controlled by the teacher end, and the student end cannot operate it independently. AI Dialogue Intervention Group: Students conducted text-based conversations with a "health partner" based on a large language model using computers in the computer room, for approximately 10-15 minutes each week. In this group, about half of the students were randomly assigned to the motivational interview dialogue group, while the other half were assigned to the non-motivational interview dialogue group. The content of the conversations (all focusing on topics related to physical activity) and the duration of the conversations were the same for both groups, but the communication methods were different. Follow-up Survey This study will conduct assessments at baseline (1 week before the intervention), 1 week after the end of the intervention, and 8 weeks after the end of the intervention. Baseline assessment will include all outcome measures, demographic information, and baseline physical activity level. The assessment at 1 week after the intervention will include all outcome measures, process indicators, and satisfaction evaluation (for intervention groups only). The assessment at 8 weeks after the intervention will include all outcome measures and behavioral maintenance. In addition, for the AI dialogue group, an immediate post-test will be conducted after the first dialogue session, and an additional follow-up assessment will be conducted during the mid-intervention period (approximately 1-2 weeks after baseline).