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

Amuki Joseph Kesi (), Loyani Loyani, Bonny Mgawe and Elizabeth Mkoba
Additional contact information
Amuki Joseph Kesi: Computational and Communication Science and Engineering (CoCSE), The Nelson Mandela African Institution of Science and Technology (NM-AIST)
Loyani Loyani: Computational and Communication Science and Engineering (CoCSE), The Nelson Mandela African Institution of Science and Technology (NM-AIST)
Bonny Mgawe: Computational and Communication Science and Engineering (CoCSE), The Nelson Mandela African Institution of Science and Technology (NM-AIST)
Elizabeth Mkoba: Computational and Communication Science and Engineering (CoCSE), The Nelson Mandela African Institution of Science and Technology (NM-AIST)

A chapter in Advancement in Embedded and Mobile Systems, 2026, pp 157-180 from Springer

Abstract: Abstract 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.

Keywords: Centralized disease database; Machine learning models; Extreme programming forecasting diseases (search for similar items in EconPapers)
Date: 2026
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:prochp:978-3-031-99219-3_12

Ordering information: This item can be ordered from
http://www.springer.com/9783031992193

DOI: 10.1007/978-3-031-99219-3_12

Access Statistics for this chapter

More chapters in Progress in IS from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().