Abstract:
The prevalence of eye disease is rapidly growing in Ethiopia and the scarcity of experts in the field
of ophthalmology is the major problem for early diagnosis and treatment for eye patients. Designing
KBS will simplify the medical diagnose processes by emulating human experts. In KBS
development case-based and rule-based reasoning are popular techniques of knowledge
representation for problem-solving and decision making. The main purpose of this research is to
integrate rule-based and case-based reasoning approaches for diagnosing and treatment of eye
diseases. The study followed the design science research approach with six steps process model. For
problem identification and formulate the objective of the solution, knowledge is acquired by using
document analysis, domain expert interviewing and previously solved patient cards form Jimma
University Specialized Hospital. The method of integration of rule-base with case-based reasoning is
done using a conditional combination model, which has a controller in between RBR and CBR. The
controller is developed by Java eclipse programming language. It forwards the query first for rulebased reasoning (RBR) which attempts to recommend a solution for the new query. If RBR doesn‘t
solve the problem, the query is automatically forwarded to the CBR system. The CBR system is
developed by JCOLIBRI programming language, where the case retrieval module identifies the most
related solution using case similarity measure. In this study, the four RE (Retrieval, Reuse, Revise
and retain) cycle are integrated with the CBR system. The knowledge-based system prototype is
demonstrated practically for users‘ acceptance evaluation. Experimental results show that the system
achieves 87.5% accuracy with an average Precision and Recall of 94.7% and 90% respectively. For
user acceptance testing the selected ten experts are involved for evaluation hereafter, the system
scores 85.6%. This shows the system has registered a promising result. However, knowledge
acquisition is performed manually which is challenging and incomplete. So, further study has to be
done for automatic knowledge acquisition using data mining or machine learning for simplifying
learning towards intelligent system design.
