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

Abstract

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.

Classification and prediction of pulmonary tuberculosis infection in HIV/AIDS patients based on XGboost algorithm

“…Some studies have also used machine learning models to predict the spread of HIV in the AIDS pandemic, and the collected research factors are similar to those in this study, such as patient age, marital status, type of residence, occupation and route of HIV infection. The authors used these research factors to establish machine learning models to predict AIDS transmission, and the research results also showed that the XGboost model is the best algorithm to predict HIV status, which can help identify people who may need pre-exposure prophylaxis and is more helpful for the detection of socio-behavioral HIV [25] .…”

Predicting sexually transmitted infections among men who have sex with men in Zimbabwe using deep learning and ensemble machine learning models

“…The study reveals that MLP performed better in predicting STIs among MSM with a high accuracy of 87.54%, recall of 97.29%, precision of 89.64%, F1-Score of 93.31% and AUC of 66.78%. Other studies, including one by Birri Makota and Musengi [ 14 ] also applied different HIV prediction models and XGBoost outperformed other models. With such good performance, these models can be effectively used to develop pre-test STI infection screening tools to identify highly at-risk individuals within the MSM community [ 2 ] and prioritise resource allocation to improve the health outcomes of these hard-to-reach communities.…”

“…The findings of their study found that the Farrington models performed better than the catalytic models. Furthermore, Birri Makota and Musenge (2023) [ 14 ] also applied the XG Boost algorithm to predict HIV status in Zimbabwe using Demographic Health Survey data from 2005 to 2015. Their study revealed that XGBoost performed better than other models on original data and SMOTE-balanced data.…”