Research progress on machine learning-based risk assessment for HIV and sexually trans-mitted infections
WANG Jinshen
LI Haiyi
LIANG Peng
Alikesi Muheyati
HUANG Shujie
ZHAO Peizhen
WANG Cheng
Abstract：HIV and sexually transmitted infections(STIs)are critical global public health is-sues.In resource-constrained settings,the accurate identification of high-risk populations is criti-cal for the effective prevention of HIV/STI transmission.As a pivotal subset of artificial intelli-gence,machine learning offers advanced capabilities in data processing and pattern recognition,providing novel approaches for risk assessment in HIV/STIs,and is an emerging focus of research in this field.This review summarizes recent advances in machine learning for assessing the risk of HIV/STI infections,with a focus on comparing the strengths and limitations of different algo-rithms.It provides an in-depth analysis of the main risk factors among various high-risk popula-tions and discusses the shortcomings and challenges of current research regarding sample represen-tativeness,model interpretability,and integration with intervention strategies.The aim is to pro-vide rational and practical guidance for future research.
Keywords：sexually transmitted infectionsHIVmachine learningrisk assessment
Publication Date：2025-09-28
Online Publishing Date：2025-10-29(First online date of this platform, not the publication date of the document)
Pages：6( 673-678 )