Somalia Struggling To Control the TB Epidemic: Insight from Artificial Neural Networks

Somalia is among the African countries which have been ravaged by political instability and poverty. The country recorded high TB incidence between 2000-2013. Modeling and forecasting of TB incidence is now critical in order to understand the future evolution of the TB epidemic and assess the impact of mitigatory and control measures in the fight against TB. In this research article, the ANN approach was applied to analyze TB incidence in Somalia. The employed annual data covers the period 2000-2018 and the out-of-sample period ranges over the period 2019-2023. The residuals and forecast evaluation criteria (Error, MSE and MAE) of the applied model indicate that the model is stable in forecasting TB incidence in Somalia. The results of the study indicate that TB incidence is likely to be high around 287 cases /100 000/year and TB program gains will be reversed over the period 2019-2023.Therefore the government of Somalia is encouraged to intensify TB surveillance and control programs and to channel more resources towards TB/HIV programs.