ANALYZING NEW HIV INFECTIONS IN PREGNANT WOMEN AT GWERU DISTRICT HOSPITAL USING ARTIFICIAL NEURAL NETWORKS

Abstract

In this paper, the ANN model is applied to forecast the number of new HIV infections in pregnant women at Gweru District Hospital (GDH). The data employed in this research is taken from the GDH Health Information Department and ranges over the period January 2020 to December 2019. The out-of-sample forecasts will cover the period January 2020 to December 2021. The applied ANN (12, 12, 1) model is adequate as shown by its residuals and minimum forecast evaluation statistics. The results of the study basically reveal that new HIV infections in pregnant women will most likely decline over the period January 2020 to December 2021. This could be a positive towards an HIV/AIDS-free Zimbabwe. Therefore, in order to facilitate the realization of such projections, GDH has a role to play with regards to the following recommendations: [i] GDH should engage in community-based pre-pregnancy assessment and advice campaigns for all known HIV positive women who are of child-bearing age. In this regard, issues such as optimization of HIV treatment, safety of any treatment in pregnancy, model of birth as well as breastfeeding should be discussed. [ii] GDH should offer antenatal screening for HIV for all pregnant women in the first trimester bloods or when they present/book. [iii] GDH ought to engage in more HIV/AIDS awareness programmes, with special emphasis on HIV in pregnant women.