Development of a Centralized Disease Database with Machine Learning Model for Forecasting Malaria in South Sudan

Malaria, a potentially fatal illness spread by female Anopheles mosquitoes, is still a major global health issue. The parasite penetrates the bloodstream, attaching itself to red blood cells and developing in the liver with common symptoms such as fever and chills caused by several Plasmodium parasites, the most important being Plasmodium vivax and Plasmodium falciparum. The most dangerous species on the continent is P. falciparum, but P. vivax is more common outside of sub-Saharan Africa. Over 619,000 people lost their lives to malaria in 2019, with 247 million cases reported globally. Children under the age of five accounted for 55% of all the deaths caused by malaria. Pregnant women in sub-Saharan Africa faced exposure to malaria throughout their pregnancies. Sub-Saharan Africa bore the brunt of malaria fatalities, with over 90% of deaths occurring in this region due to suitable climatic conditions for the malaria parasite and limited access to healthcare. Our project aimed to develop a centralized disease database with a machine learning model for forecasting malaria in South Sudan. We used qualitative and quantitative methods to gather requirements, employing extreme programming as our system development approach with four forecasting algorithms. Arima, Facebook Prophet, Neural Prophet, and Double Exponential Smoothing were trained using the dataset's temperature and number of malaria cases as the forecasting variables. Facebook Prophet, Neural Prophet, and Double Exponential Smoothing yielded the best results, with accuracy rates of 85.7%, 87.9%, 86.7% for the Juba region, 89.5%, 87.2%, and 80.4%, for Yei and accuracy rates of 88.9%, 90.7%, and 90.5% for Wau. Arima's accuracy of 81.1% in the Yei region was the only place where it performed well; accuracy of 77.4% and 68.5% were recorded in Juba and Wau, respectively. The system can forecast malaria incidence on a daily, monthly, and annual basis by using a machine learning model, which enhances the provision of healthcare services.