Accepted for/Published in: Journal of Medical Internet Research
Date Submitted: Apr 2, 2024
Date Accepted: Jan 2, 2025
Predicting the Risk of HIV and Sexually Transmitted Diseases Among Men Who Have Sex with Men in Western China: A Cross-Sectional Study Using Multiple Machine Learning Approaches
ABSTRACT
Background:
Men who have sex with men (MSM) are at high risk for HIV and sexually transmitted diseases (STD) infection.
Objective:
The aim of this study was to develop web applications based on different machine learning methods for predicting and assessing the risk of HIV and STD among MSM.
Methods:
Our study was a cross-sectional study that collected individual characteristics of 1999 MSM with negative or unknown HIV serostatus in Western China during 2013-2023. MSM self-reported their STD history and were tested for HIV. We compared the accuracy of six machine learning methods in predicting HIV and STD risk using seven parameters for a comprehensive assessment and ranked the methods according to their performance in each parameters. We selected data from the Sichuan MSM for external validation.
Results:
Of the 1999 MSM, 3.60% (72/1999) tested positive for HIV and 7.30% (146/1999) self-reported a history of previous STD infection. XGBoost models performed optimally in predicting HIV and STD risk and demonstrated stability in both internal and external validation. Interpretability analysis showed that non-adherence to condom use, low HIV knowledge, multiple male partners, and internet dating were risk factors for HIV infection. Low degree of education, internet dating, multiple male and female partners were risk factors for STD infection. The risk stratification analysis indicated that the optimal model was able to distinguish well between high-risk and low-risk MSM individuals. The prediction results of the optimal model were displayed in the shiny web applications for online probability estimation and interactive computation.
Conclusions:
Machine learning methods have demonstrated strengths in predicting the risk of HIV and STD infection among MSM. Online web applications can facilitate clinicians to accurately assess the risk of infection in high-risk individuals, especially those with concealed MSM, and help them to self-monitor their risk status for further targeted and timely diagnosis and interventions to reduce the incidence of new infections.
Citation
Per the author's request the PDF is not available.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.