Prediction Model for the Risk of HIV Infection among MSM in China: Validation and Stability

Abstract

The impact of psychosocial factors on increasing the risk of HIV infection among men who have sex with men (MSM) has attracted increasing attention. We aimed to develop and validate an integrated prediction model, especially incorporating emerging psychosocial variables, for predicting the risk of HIV infection among MSM. We surveyed and collected sociodemographic, psychosocial, and behavioral information from 547 MSM in China. The participants were split into a training set and a testing set in a 3:1 theoretical ratio. The prediction model was constructed by introducing the important variables selected with the least absolute shrinkage and selection operator (LASSO) regression, applying multivariate logistic regression, and visually assessing the risk of HIV infection through the nomogram. Receiver operating characteristic curves (ROC), Kolmogorov–Smirnov test, calibration plots, Hosmer–Lemeshow test and population stability index (PSI) were performed to test validity and stability of the model. Four of the 15 selected variables—unprotected anal intercourse, multiple sexual partners, involuntary subordination and drug use before sex—were included in the prediction model. The results indicated that the comprehensive prediction model we developed had relatively good predictive performance and stability in identifying MSM at high-risk for HIV infection, thus providing targeted interventions for high-risk MSM.

Web-Based Risk Prediction Tool for an Individual's Risk of HIV and Sexually Transmitted Infections Using Machine Learning Algorithms: Development and External Validation Study

“…First, our predictive models were not limited to high-risk groups (such as MSM). HIV and STI risk prediction models have been published previously but mainly for high-risk individuals, such as MSM [20,21,24,29]. Our models could predict HIV and STI acquisition in both men and women, including homosexual and heterosexual individuals.…”

“…Despite the advantages of machine learning approaches, there is an absence of individual risk prediction tools for HIV and STI risk using machine learning models. Existing studies using machine learning algorithms to predict HIV and STI acquisition mainly focus on HIV [19][20][21][22][23][24][25][26][27][28][29][30], and few focus on STIs [19,21,31]. Of these HIV prediction studies, 4 studies focused on high-risk individuals (such as men who have sex with men [MSM] [20,21,24,29]), 2 studies used imaging or clinical text data [22,30], 4 studies used more than 40 predictors [23,[26][27][28], and 2 studies assessed future but not current HIV prediction [19,25].…”

“…Existing studies using machine learning algorithms to predict HIV and STI acquisition mainly focus on HIV [19][20][21][22][23][24][25][26][27][28][29][30], and few focus on STIs [19,21,31]. Of these HIV prediction studies, 4 studies focused on high-risk individuals (such as men who have sex with men [MSM] [20,21,24,29]), 2 studies used imaging or clinical text data [22,30], 4 studies used more than 40 predictors [23,[26][27][28], and 2 studies assessed future but not current HIV prediction [19,25]. Of the STI prediction studies, 1 study was conducted with MSM [21], and the other 2 studies focused on future STI prediction [19,31].…”

Internalized homophobia and sexual risk behavior in men who have sex with men: The mediational role of sexual self-concept

“…The main way of HIV transmission is sexual risk behaviors (SRB) (Martinez et al, 2016;Luz et al, 2019;Coelho et al, 2021;Mulaudzi et al, 2022;Wei et al, 2022). Understood as sexual situations or practices that generate harm to one's or others' sexual health, for example, (1) sexual activity with multiple partners (Sönmez et al, 2021;Dong et al, 2022), (2) absence or misuse of condoms (Closson et al, 2018;Chu and Huang, 2020), (3) sexual activity under the influence of alcohol and drugs (Palfai and Luehring-Jones, 2021;Bustamante et al, 2022).…”

Predicting the risk of HIV infection among internal migrant MSM in China: An optimal model based on three variable selection methods

“…Establishing appropriate prediction models to assess the risk of HIV infection in migrant MSM populations is beneficial for an individual to aware risk of infection and proactively avoid adverse factors, and is also in favor of the government to identify high-risk groups and integrate limited resources for targeted interventions specific to this population. While several HIV risk assessment tools have been targeted at MSM domestic and overseas ( 15 – 18 ), none has yet been developed for internal migrant MSM.…”