USING ARTIFICIAL NEURAL NETWORKS FOR PREDICTING MIGRAINE CASES AT KWEKWE GENERAL HOSPITAL IN ZIMBABWE

Abstract

Migraine is one of the most common neurological disorders. In Zimbabwe is not uncommon and yet migraine studies in the country are still scanty. The current study employed monthly time series data on migraine caseloads recorded and managed at Kwekwe General Hospital (KGH) from Janaury 2010 to December 2019, to forecast migraine cases over the period January 2020 to December 2021. The study applied the ANN (12, 12, 1) model. Residual analysis of this famous model indicates that the model is stable and thus suitable for forecasting migraine case volumes at KGH over the period January 2020 to December 2021. The findings of the indicated that migraine case-loads will, in general, slightly trend upwards over the out-of-sample period. Amongst other policy suggestions, we advise KGH to promptly treat all migraine cases and also disseminate information about migraine and the need for timely hospital visits.