Skip to main content

ORIGINAL RESEARCH article

Front. Public Health
Sec. Public Mental Health
Volume 12 - 2024 | doi: 10.3389/fpubh.2024.1504739
This article is part of the Research Topic Youth Mental Health, Particularly in Asian Populations View all 43 articles

Key risk factors of generalized anxiety disorder in adolescents: Machine learning study

Provisionally accepted
Yonghwan Moon Yonghwan Moon 1Hyekyung Woo Hyekyung Woo 1,2*
  • 1 Department of Health Administration, Kongju National University, Gong, Republic of Korea
  • 2 Institute of Health & Environment of Kongju National University, Republic of Korea, Kongju, Republic of Korea

The final, formatted version of the article will be published soon.

    This study utilized data from the Korea Youth Risk Behavior Web-based Survey (KYRBS) from 2020 to 2023 to analyze factors influencing Generalized Anxiety Disorder (GAD) in adolescents. Using machine learning techniques such as Lasso Regression, SelectKBest, and XGBoost, we identified key variables, including health behaviors such as sleep, smoking, and fast-food intake, as significant factors associated with GAD. Predictive models using Random Forest and Artificial Neural Networks demonstrated that the XGBoost feature selection method effectively identified key factors and showed strong performance. These findings emphasize the need for educational programs focusing on sleep management, smoking prevention, and balanced nutrition to reduce the risk of GAD in adolescents, providing crucial insights for early diagnosis and prevention strategies.

    Keywords: adolescent1, Mental health2, generalized anxiety disorder3, machine learning4, health behaviors5

    Received: 01 Oct 2024; Accepted: 18 Dec 2024.

    Copyright: © 2024 Moon and Woo. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Hyekyung Woo, Department of Health Administration, Kongju National University, Gong, Republic of Korea

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.