A clinical diagnostic model based on supervised learning

Abstract

Shortages of medical practitioners, medical facilities and complexity of diseases among others have given rise to the need for the use of computer programs to give helping hands in the health sector. Supervised Learning as a method of developing predictive systems has been proved to be powerful on classification problems, mostly when dealing with diseases. It was used on malaria fever datasets collected from a reputable hospital in Ado-Ekiti, Ekiti State, Nigeria in this work to create a classification model using Partial Tree (PART) Technique. The developed model was tested on both the training and the testing sets with the detection rates of 100% and 98.04% respectively, and adjudged promising. The final implementation and deployment of the model will be carryout as a mobile application so as to have a wider coverage in terms of accessibility and usability. It is hopeful it will be of immense benefits in the health sector.