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

The burden of HIV and related diseases have been areas of great concern pre and post the emergence of COVID-19 in Zimbabwe. Machine learning models have been used to predict the risk of diseases, including HIV accurately. Therefore, this paper aimed to determine common risk factors of HIV positivity in Zimbabwe between the decade 2005 to 2015. The data were from three two staged population five-yearly surveys conducted between 2005 and 2015. The outcome variable was HIV status. The prediction model was fit by adopting 80% of the data for learning/training and 20% for testing/prediction. Resampling was done using the stratified 5-fold cross-validation procedure repeatedly. Feature selection was done using Lasso regression, and the best combination of selected features was determined using Sequential Forward Floating Selection. We compared six algorithms in both sexes based on the F1 score, which is the harmonic mean of precision and recall. The overall HIV prevalence for the combined dataset was 22.5% and 15.3% for females and males, respectively. The best-performing algorithm to identify individuals with a higher likelihood of HIV infection was XGBoost, with a high F1 score of 91.4% for males and 90.1% for females based on the combined surveys. The results from the prediction model identified six common features associated with HIV, with total number of lifetime sexual partners and cohabitation duration being the most influential variables for females and males, respectively. In addition to other risk reduction techniques, machine learning may aid in identifying those who might require Pre-exposure prophylaxis, particularly women who experience intimate partner violence. Furthermore, compared to traditional statistical approaches, machine learning uncovered patterns in predicting HIV infection with comparatively reduced uncertainty and, therefore, crucial for effective decision-making.Author summary: The Joint United Nations Programme (UNAIDS) set up fast-track targets to reach HIV epidemic control by 2030, where it is expected that 95% of people living with HIV know their status, and of those, 95% should be on treatment and of those on treatment 95% should have reached viral suppression. In Zimbabwe, by 2020, it was found that 86.8% of adults living with HIV were aware of their status and of those aware of their status, 97.0% were on antiretroviral treatment. Furthermore, among those on treatment, 90.3% achieved viral load suppression. In order to achieve these targets, modern predictive algorithms using machine learning have the power to enhance HIV prevention and prediction capability. Furthermore, studies have reported that machine learning could accurately predict future HIV infection. This paper, therefore, aims to use these machine learning tools to predict key HIV populations based on socio-behavioural characteristics obtained from survey data.