Use of machine learning techniques to identify HIV predictors for screening in sub-Saharan Africa

Abstract

Aim HIV prevention measures in sub-Saharan Africa are still short of attaining the UNAIDS 90–90-90 fast track targets set in 2014. Identifying predictors for HIV status may facilitate targeted screening interventions that improve health care. We aimed at identifying HIV predictors as well as predicting persons at high risk of the infection. Method We applied machine learning approaches for building models using population-based HIV Impact Assessment (PHIA) data for 41,939 male and 45,105 female respondents with 30 and 40 variables respectively from four countries in sub-Saharan countries. We trained and validated the algorithms on 80% of the data and tested on the remaining 20% where we rotated around the left-out country. An algorithm with the best mean f1 score was retained and trained on the most predictive variables. We used the model to identify people living with HIV and individuals with a higher likelihood of contracting the disease. Results Application of XGBoost algorithm appeared to significantly improve identification of HIV positivity over the other five algorithms by f1 scoring mean of 90% and 92% for males and females respectively. Amongst the eight most predictor features in both sexes were: age, relationship with family head, the highest level of education, highest grade at that school level, work for payment, avoiding pregnancy, age at the first experience of sex, and wealth quintile. Model performance using these variables increased significantly compared to having all the variables included. We identified five males and 19 females individuals that would require testing to find one HIV positive individual. We also predicted that 4·14% of males and 10.81% of females are at high risk of infection. Conclusion Our findings provide a potential use of the XGBoost algorithm with socio-behavioural-driven data at substantially identifying HIV predictors and predicting individuals at high risk of infection for targeted screening.

Machine learning approaches in the diagnosis of infectious diseases: a review

“…This does not provide a comprehensive and accurate analysis of the data. For example, for HIV [56], about 80 million people have been infected and are alive today. However, the data on their progression to acquired immunodeficiency syndrome (AIDS) and death is not available.…”

“…The traditional modeling methods are not suitable for data with missing values, irregular spacing, and high-dimensional features. The majority of the current ML models are developed and evaluated either on artificially generated data or are experimental [11], [22], [43], [45], [55], [56]. In many cases, these models perform better than existing methods based on evaluation metrics such as accuracy and precision.…”

Machine Learning Model for Prediction and Visualization of HIV Index Testing in Northern Tanzania

“…Machine learning in HIV/AIDS had applied as follows: Machine learning to identify HIV predictors for screening [13]. Machine learning in the prediction of patient-specific current CD 4 cell count to determine the progression of human immunodeficiency.…”

Linear and Machine Learning modelling for spatiotemporal disease predictions: Force-of-Infection of Chagas disease

“…These methods have previously been used in contexts in which those assumptions are challenged, such as spatial, temporal and spatiotemporal analyses of infectious diseases, e.g. mapping of human leptospirosis [10,11], severe fever with thrombocytopenia syndrome [12], lymphatic filariasis [13], or to identify individuals with a higher risk of HIV infection based on socio-behavioural-driven data [14].…”