Abstract: Diabetic retinopathy the most common diabetic eye disease, is caused by complications that occurs when blood vessels in the retina weakens or distracted. The correct diagnosis of proliferative diabetic retinopathy is essential; because it is a treatable disease and missing the diagnosis can lead to the patient becoming blind. We examined the ability of internists and ophthalmologists to diagnose proliferative retinopathy under optimal conditions. Several data mining technique serves different purposes depending on the modeling objective. I have used various data mining techniques to predict the early detection of eye disease diabetic retinopathy. Image enhancement, mass screening and monitoring of disease are the main methodologies of this work.

Keywords: Naïve bayes, Support Vector Machine, Daibetic Retinopathy.