USING ARTIFICIAL NEURAL NETWORKS FOR PREDICTING NEW ESOPHAGEAL CANCER CASES AT GWERU PROVINCIAL HOSPITAL IN ZIMBABWE

Abstract

Cancer is a disease that affects large numbers of people from all walks of life.Diagnosis of cancer induces fear both in the individual and in families, and isfrequently viewed as death sentence (Ministry of Health & Child Care, 2014). Itsprevention, diagnosis and treatment poses a myriad of challenges particulary in developing countries such as Zimbabwe. This study employed monthly time series data on Esophageal Cancer (EC) cases at Gweru Provincial Hospital (GPH) from Janaury 2010 to December 2019, in order to predict EC cases over the period January 2020 to December 2021. The ANN (12, 12, 1) model was applied. Residual analysis of this model indicated that it was indeed stable and thus suitable for predicting EC cases at GPH over the out-of-sample period. The results of the study indicate that EC cases will generally rise over the out-ofsample period; characterised by possible seasonal peaks in the month of November each year. Amongst other recommendations, the study suggested the need for prioritizing proper diets and healthy lifestyles as a preventive measure against EC.