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.

This study attempted to examine the role of institutions in boosting rural and agricultural development in the region of the Volcanic Highlands of Rwanda. Both qualitative and quantitative data were collected from a random sample of 401 small-scale farmers through a questionnaire. Data were analyzed using a weighted least-squares method to account for heteroscedasticity, a common issue in cross-sectional studies. Results from crop output function reveal a positive and significant effect of cooperative membership, a negative but significant effect of extension services, and a negative non-significant effect of land tenure, credit access, and market access on farm production, respectively. In terms of net farm income function, the results demonstrate that farmer cooperation, land tenure, extension services, and access to output markets have a positive, non-significant influence, but that access to finance has a negative non-significant effect. Results also point to a positive and significant effect of some household characteristics, namely family size, farming experience, land size, and farm yield, on farm production. As for net farm income, education of the head, family size, farm experience, land size, farm yield, selling price, and cattle proved to be among primary determinants. It was therefore suggested that agricultural sector programs and activities should be readapted and strengthened in order to leverage rural and agricultural development in Rwanda.

No abstract

Aim: HIV prevention measures at 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 six machine learning approaches for building models using population-based HIV Impact Assessment (PHIA) data for 41,939 male and 45,105 female respondents with 24 and 29 variables respectively from four countries in sub-Saharan countries. We trained and validated the six algorithms on 80% of 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 six algorithms by f1 scoring mean of 78.9% and 92.8% 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 seven 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 the infection.Conclusion: Our findings provide a potential use of XGBoost algorithm with socio-behavioural-driven data at substantially identifying HIV predictors and predicting individuals at high risk of infection for targeted screening.

No abstract