# From habit to high risk: The influence of multidimensional lifestyle changes on internet addiction risk among junior high school students and its predictive utility

## TL;DR

This study shows how lifestyle changes like poor sleep and less exercise increase the risk of internet addiction in junior high students, offering insights for prevention strategies.

## Contribution

The study identifies specific lifestyle changes as risk factors for internet addiction and proposes a predictive model for early intervention.

## Key findings

- Late sleep onset and late-night eating are significant risk factors for internet addiction.
- A predictive model with an AUC of 0.721 can identify students at risk based on lifestyle changes.
- Decreased exercise and poor dietary habits correlate with increased addiction risk.

## Abstract

To investigate how changes in the daily lifestyles of junior high school students influence the risk of Internet addiction, and to develop precise, lifestyle-based intervention strategies for preventing and reducing such addiction.

In April 2024, a follow-up survey was conducted on a cohort first assessed in September 2023. The relationship between various dynamic changes in daily lifestyle—encompassing four dimensions: exercise, smart device ownership, diet, sleep-wake patterns and the risk of Internet addiction was analyzed. The predictive performance of these factors was evaluated using Receiver Operating Characteristic (ROC) curves.

Of the 10,535 participants enrolled at baseline (T1), 9,750 were successfully followed up at T2, yielding a retention rate of 92.55% (9,750/10,535). Among these, 7,853 provided complete and valid questionnaire data, corresponding to a T2 effective data rate of 80.54% (7,853/9,750). The detected rate of Internet addiction risk increased from 10.62% at T1 to 13.35% at T2. Multivariate analysis identified the following behavioral changes as significant risk factors for Internet addiction: going to bed after 10:00 pm or having delayed sleep onset timing (OR = 2.859, 95% CI: 2.319–3.525); developing late-night eating habit (OR = 1.932, 95% CI: 1.494–2.499); becoming a smart device owner (OR = 1.773, 95% CI: 1.307–2.405); being a non-habitual napper (OR = 1.699, 95% CI: 1.408–2.049); decreased pursuit of dietary balance (OR = 1.654, 95% CI: 1.300–2.104); decreased active exercise (OR = 1.575, 95% CI: 1.222–2.031); and decrease in exercise duration per session (OR = 1.436, 95% CI: 1.117–1.846). A predictive model incorporating six key variables (excluding change in habitual late-night eating) demonstrated acceptable performance, with an area under the ROC curve (AUC) of 0.721 (95% CI: 0.701–0.741).

This six-month longitudinal study systematically reveals that adverse changes across four lifestyle dimensions significantly increase the risk of Internet addiction among junior high school students. These findings provide an empirical basis for developing targeted interventions to prevent and reduce this risk.