Development Of A Bayesian Based Approach To Malaria Fever Diagnosis

ABSTRACT

Malaria is a deadly disease killing millions of people every year. Different countries of the

world, governmental and non-governmental organizations including World Health

Organization have taken it as a challenge to address the issue of deaths associated with

malaria. Prompt and accurate diagnosis is a major key in medical field. This prompts for the

need to develop a Bayesian base approach to malaria fever diagnosis. A machine learning

technique Bayesian was used on labelled sets of malaria fever symptoms collected in malaria

dataset. The labelled database was divided into five cases of malaria and the classification

model for malaria fever diagnosis was developed using WEKA software.

The developed model has been tested and gives a classification accuracy of 66% on training

dataset while that of testing data set gives classification accuracy of 84%.

The result shows that the Bayesian is a promising approach and the system hereby recommended for use in areas where cases of malaria fever are prevalence.