Predicting Paediatric Malaria Occurrence Using Classification Algorithm in Data Mining

Abstract

This paper gives the current overview of the application of data mining techniques on the haematological and biochemical dataset to predict the occurrence of malaria in children between age zero (0) and five (5).  Malaria has been eradicated from the developed countries but still affecting a large part of the world negatively. A larger percentage of malaria is estimated to affect young children in sub-Sahara Africa.  In order to reduce mortality from paediatric malaria, there should be an efficient and effective prediction method.  In healthcare, data mining is one of the most vital and motivating areas of research with the objective of finding meaningful information from huge data sets and provides an efficient analytical approach for detecting unknown and valuable information in healthcare data.  In this study, a model was built to predict the occurrence of malaria in children between age zero (0) and five (5) years, using decision tree classification algorithms on WEKA workbench tool.  The classification algorithms used are LMT, REPTree, Hoeffding tree and J48. A J48 algorithm was used for building the decision tree model since it has higher accuracy for performance with least error margin.