USING ARTIFICIAL NEURAL NETWORKS FOR PREDICTING NEW DOG BITE CASES AT GWERU PROVINCIAL HOSPITAL IN ZIMBABWE

Abstract

Believe it or not, any dog is capable of biting. Dog bites can cause serious injuries and even death, especially to humans. This piece of work uses monthly time series data on dog bite cases recorded and managed at Gweru Provincial Hospital (GPH) from Janaury 2010 to December 2019, to predict dysentery cases over the period January 2019 to December 2020. The study applied the ANN (12, 12, 1) model. Residual analysis of this model indicates that the model is stable and adequate and therefore suitable for predicting dog bite cases at GPH over the out-of-sample period. The results of the study reveal that dog bite cases may slightly rise over the out-of-sample period. The study, amongst other policy directions, recommends Mass Dog Vaccination (MDV) as well as educating people about dogs in the GPH catchment area in order to reduce the numbers of dog bites as well as the negative heath impacts of this preventable public health concern.