ORIGINAL RESEARCH article
Front. Public Health
Sec. Infectious Diseases: Epidemiology and Prevention
Volume 13 - 2025 | doi: 10.3389/fpubh.2025.1596876
Predicting HIV Self-Testing Intentions Among Chinese College Students: A Dual-Model Analysis Integrating Health Belief Constructs and Machine Learning Prioritization
Provisionally accepted
- 1Jinan University, Guangzhou, China
- 2Guangzhou University of Chinese Medicine, Guangzhou, Guangdong Province, China
- 3Xiangnan University, Chenzhou, Hunan Province, China
- 4College of Humanities and Management, Hunan University of Chinese Medicine, Changsha, Anhui Province, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
As college students emerge as a key HIV-vulnerable population in China, HIV selftesting (HIVST) presents a critical strategy for enhancing detection rates and enabling timely intervention. While observational studies have identified multifactorial influences on HIVST willingness, few investigations integrate behavioral theory with machine learning approaches among high-risk subgroups. This cross-sectional study employed stratified cluster sampling to recruit 1,015 undergraduates from Xiangnan College (July-August 2022), synthesizing the Health Belief Model (HBM) with random forest analytics to elucidate determinants of HIVST willingness. Among participants, 69.3% (n = 703) expressed willingness to adopt HIVST within the next 6 months. 15.0% reported sexual activity (n = 152), with 12.0% (n = 122) of sexually active participants demonstrating concurrent engagement in unprotected intercourse and HIV testing willingness. HBM-based logistic regression revealed that self-efficacy (OR = 1.64, 95% CI: 1.21-2.21) and cues to action (OR = 1.34, 1.04-1.75) were significant facilitators, contrasting with the inhibitory effects of perceived barriers (OR = 0.69, 0.55-0.86).Random forest modeling prioritized these psychological constructs (mean decrease Gini >2.5), identifying male students and arts majors as critical subpopulations requiring targeted intervention. Our dual-method analysis establishes that campus HIV control necessitates: 1) Gender-specific prevention programs addressing male students' elevated risk exposure; 2) HBM-informed education strengthening self-efficacy and environmental cues; 3) Structural interventions reducing testing barriers through discreet service delivery. This theoretical-empirical integration advances predictive understanding of HIVST behaviors, providing actionable insights for developing precision public health strategies in academic settings.
Keywords: health belief model, College student, HIV self-testing, high-risk behaviors, Random Forest modeling
Received: 21 Mar 2025; Accepted: 08 Jul 2025.
Copyright: © 2025 Li, Lu, He, Hu, He, Huang, Li and Jiang. 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: Yan Jiang, Xiangnan University, Chenzhou, 423000, Hunan Province, China
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.