Expert systems for self-diagnosing of eye diseases using Naïve Bayes

Abstract

The best defense against eye diseases is to have regular checkups. However, in reality, poverty stops people outside the developing world from seeing an eye doctor regularly. Thus, many patients did not get appropriate treatment for their eye disease until it is too late. This paper presents an expert system for diagnosing eye disease based on Naive Bayes. The developed expert system applies Case-Based Reasoning (CBR), which is a paradigm for reasoning from experience while the Naive Bayes is used as a method for classifying eye diseases by applying Bayes' theorem. The outputs of the expert system are classification of an eye disease and information on the best treatment. The result of this study is obtained by comparing the expert system diagnostic results with an expert diagnostic result. Based on the experimental results, the Naive Bayes based expert system has been able to obtained 82% accuracy. Thus, it can be concluded that an expert system with Naive Bayes has the potential to be used effectively by the people but still has plenty room for improvement.