Using Artificial Neural Networks for Predicting New Bilharzia Cases in Children Aged 15 Years and Below at Gweru Provincial Hospital in Zimbabwe

Bilharzia is an important, and yet neglected, infectious disease affecting at least 100 million people in Africa. Children in Zimbabwe, just like other children of Africa, continue to carry the heaviest burden of infection, with children as young as 12 months old showing signs of infection. This paper uses monthly time series data on bilharzia cases recorded and managed at Gweru Provincial Hospital (GPH) from Janaury 2010 to December 2019, in order to make predictions over the period January 2020 to December 2021. The study employed the famous ANN (12, 12, 1) model. Residual analysis of this model showed that the model is stable and thus suitable for predicting bilharzia cases at GPH over the out-of-sample period. The findings of this study indicate that bilharzia cases will continue on an upwards trajectory within the GPH catchment area. The study, amongst other policy directions; recommends prompt administration of antiparasite treatment (that is, praziquantel (PZQ)) to all infected children