Predicting HIV Status among Men Who Have Sex with Men in Bulawayo & Harare, Zimbabwe Using Bio-Behavioural Data, Recurrent Neural Networks, and Machine Learning Techniques

Abstract

HIV and AIDS continue to be major public health concerns globally. Despite significant progress in addressing their impact on the general population and achieving epidemic control, there is a need to improve HIV testing, particularly among men who have sex with men (MSM). This study applied deep and machine learning algorithms such as recurrent neural networks (RNNs), the bagging classifier, gradient boosting classifier, support vector machines, and Naïve Bayes classifier to predict HIV status among MSM using the dataset from the Zimbabwe Ministry of Health and Child Care. RNNs performed better than the bagging classifier, gradient boosting classifier, support vector machines, and Gaussian Naïve Bayes classifier in predicting HIV status. RNNs recorded a high prediction accuracy of 0.98 as compared to the Gaussian Naïve Bayes classifier (0.84), bagging classifier (0.91), support vector machine (0.91), and gradient boosting classifier (0.91). In addition, RNNs achieved a high precision of 0.98 for predicting both HIV-positive and -negative cases, a recall of 1.00 for HIV-negative cases and 0.94 for HIV-positive cases, and an F1-score of 0.99 for HIV-negative cases and 0.96 for positive cases. HIV status prediction models can significantly improve early HIV screening and assist healthcare professionals in effectively providing healthcare services to the MSM community. The results show that integrating HIV status prediction models into clinical software systems can complement indicator condition-guided HIV testing strategies and identify individuals that may require healthcare services, particularly for hard-to-reach vulnerable populations like MSM. Future studies are necessary to optimize machine learning models further to integrate them into primary care. The significance of this manuscript is that it presents results from a study population where very little information is available in Zimbabwe due to the criminalization of MSM activities in the country. For this reason, MSM tends to be a hidden sector of the population, frequently harassed and arrested. In almost all communities in Zimbabwe, MSM issues have remained taboo, and stigma exists in all sectors of society.

A Comparative Study of Cyberbullying Detection in Social Media for the Last Five Years

“…The SVM is a binary classification technique that classifies data and separates it into two groups by generating an operational separating hyperplane. The support vectors are the data points nearest to the hyperplane, and the hyperplane is a decision space separated into a set of objects of different classes [17,18].…”

Predicting HIV infection in the decade (2005–2015) pre-COVID-19 in Zimbabwe: A supervised classification-based machine learning approach

“…Three primary studies have been published that used machine learning methods to predict HIV status in Zimbabwe [ 2 , 19 , 20 ]. First, Mutai et al [ 2 ] predicted HIV status using Demographic Health Survey data from Sub-Saharan Africa.…”

“…The results obtained from the study by Mutai et al [ 2 ] were not specific to Zimbabwe but sub-Saharan Africa. Second, using data from the Zimbabwe Ministry of Health and Child Care, Chingombe et al [ 19 ] predicted HIV status among men who had sex with men in Zimbabwe’s two major cities, Bulawayo and Harare. The findings of this study were limited to men who had sex with men in Bulawayo and Harare and could not be generalised to other cities in Zimbabwe or the general population.…”

“…In contrast to Mutai et al’s [ 2 ] research, the findings of our study will be more applicable to Zimbabwe. In addition, unlike the two studies by Chingombe et al [ 19 , 20 ], we have access to a vast quantity of data from 2005–2015, i.e., ten years of DHS data. Therefore, the primary aim of this paper was to determine common risk factors of HIV positivity in Zimbabwe.…”

Conducting research among key populations in settings with discriminatory laws, policies, and practice: The case of men who have sex with men in Zimbabwe

“…In the context of HIV infection, key populations include men who have sex with men (MSM), transgender women, sex workers, intravenous drug users and people in prisons and other closed settings. Key populations remain the most crucial driver of the HIV pandemic, with the majority of incident cases occurring in this population [ [1] , [2] , [3] ]. Research has shown that men who have sex with men (MSM) living in sub-Saharan African countries where same-sex sexual conduct is criminalized have a five times higher risk of HIV infection than countries where it is not [ 4 ].…”