Integration of DHIS2 and Climatic Data for Disease Prediction: A Case of Malaria occurrence in Gulu District, Uganda

Prediction models are important tools that can assist public health in evidence-based decision-making. Disease burden estimates for Uganda are currently based on only reported cases and rough estimates from seasonal weather changes. This paper incorporates other variables including weather factors with their time lags to predict future estimates of malaria cases in Gulu District. We used data on malaria cases from an electronic Health Management Information System powered by DHIS2 of the Ministry of Health and daily reported weather data from Uganda National Meteorological Authority for a time span of five years (2013 to 2017) to provide both machine learning and statistical predictive models. Results show that the integration of malaria cases data with two weeks' historical weather data leads to better prediction of future malaria cases compared to using only currently reported cases.