A Malaria Fever Clinical Diagnostic System Driven by Reduced Error Pruning Tree (REP Tree)

The unending battle between man and malaria fever has necessitated the development of this new diagnostic model for malaria fever. It was evident from the literature search that malaria fever accounts for more than a million human deaths yearly as a result of lack of prompt diagnosis, poor diagnosis or no diagnosis due to shortages of medical experts and medical facilities, mostly in rural areas of developing countries of the world. The new diagnostic model was built by applying Reduced Error Pruning Tree (REP Tree) Algorithm on the malaria fever data sets collected from a reputable hospital. The model when tested, gave 100% detection rate on the training instances and 98.0392% success rate on the testing instances. It is hopeful that the full implementation of the model (rules generated from the REP Tree) as a mobile application will reduce the high death rate associated with malaria fever in the malaria belt of the world.