Application of Data Mining Techniques to Developing A Classification Model for Glaucoma Type Identification

Abstract

Data mining, also known as Knowledge Dis covery in Databas es (KDD),  is a proces s that entails extracting valuable, interpretable, and useful information from raw data. Glaucoma, characterized by an elevation in intraocular pres - sure (IOP), leads to glaucomatous optic neuropathy and subs equent loss of retinal ganglion cells and their axons, ultimately  resulting in blindness. Those tasked with treating  glaucoma patients may face challenges in accurately identifying the type of glaucoma and pres cribing appropriate treatment, often due to subjective decision-making, limited  knowledge, and reliance on instru-ment visualization. These challenges contribute to resource was tage  and time-consuming  processes . The primary goal of this res earch is not to com- pletely eliminate the problem but to alleviate bias ed decisions made by oph- thalmologis ts . This is accomplis hed by developing an easily accessible method for identifying  glaucoma types through the creation of an improved classification  model. In this study, data mining techniques are employed to unveil new knowledge based on the collected dataset. Among various data mining classification algorithms, this paper utilizes naïve Bayes, GRIP, J48, and PART algorithms, along with two test options involving complete and selected features. According to the empirical analys is conducted, the PART algorithm, with a 10-fold cross -validation test option using selected features, yielded the highest accuracy result, reaching 71.4%.