Integrated datamining with knowledge management framework for stroke disease

Stroke disease is a medical condition caused due to inadequate supply of blood to the brain cell that damages the cell and may result in death. In developing country like Ethiopia, the death of stroke patient increases from year to year due to the scarcity of specialists and health facilities. This lack of effort to address such a problem, this research study focuses to design and develop a prototype system by integrating data mining results with knowledge-based system that facilitate diagnosis and treatment for a patient and provides an advice and risk level for the patient. Mixed research design and an integrated knowledge acquisition method were used to acquire knowledge. Orange and WEKA tool were used as hybrid data mining tool to preprocess, analyze datasets and designing the prediction model. About six classification algorithms were comparatively analyzed and finally JRIP classification algorithm has been registered with the better accuracy of 94.16% under 10-fold cross-validation. Rule-based knowledge representation technique was used to represent knowledge in the knowledge base, SWI-Prolog was used to construct knowledge base, Java NetBeans was employed to design GUI for the KBS, JPL library was used as a middleware between knowledge base and designed GUI. Finally, after the system has scored 90% system performance and 89.9% user acceptance which is a promising result that achieves the objective of the study.