International Journal of Engineering Research and Applications (IJERA) ISSN: 2248-9622 National Conference on Emerging Trends in Engineering & Technology (VNCET-30 Mar’12) Vidyavardhini’s College of Engineering and Technology, Vasai Page 470 Classifying Chief Complaint in Eye Diseases using Data Mining Techniques Archana L. Rane 1 , P. D. Mahajan 2 1,2 Department of MCA, K K Wagh Institute of Engineering Education & Research Hirabai Haridas Vidyanagar, Panchvati, Nashik - 422 003, Maharashtra E-mail: rane_nehete_archana@yahoo.com 1 , 2 punamgf@yahoo.co.in Abstract— Eyes are the important organ for the vision system. The system itself is very complicated. The clinicians attempt to determine the correct diagnosis using signs, symptoms and test results to formulate the hypothesis of the diagnosis before providing treatments. Most patients in this study have severe illness. Therefore, the clinicians decide to take the treatment by surgery rather than treating the patients with medicine. The result of the classification is very critical for the clinicians to support their diagnosis before giving the surgery to the patients. This study endeavors on using intelligent capability of data mining to discover hidden patterns in the data. Here, Artificial Neural Networks (ANN) and Naïve Bayes are utilized as techniques to classify patients with chief complaints in eye diseases. The results of classifying the eye diseases are very encouraging with the percentage accuracy of 100% for both techniques. Keywords- classifier, data mining techniques, Artificial Neural Network, Naïve Bayes, eye disease I. INTRODUCTION Eyes are organs that detect light and convert it into electro- chemical impulses in neurons. The simplest photoreceptors in conscious vision connect light to movement. In higher organisms the eye is a complex optical system which collects light from the surrounding environment, regulates its intensity through a diaphragm, focuses it through an adjustable assembly of lenses to form an image, converts this image into a set of electrical signals, and transmits these signals to the brain through complex neural pathways that connect the eye via the optic nerve to the visual cortex and other areas of the brain [1]. Human vision is a highly complex activity with a range of physical and perceptual limitations, yet it is the primary source of information for the average person. Figure 1: Human Eye Anatomy Eye disease is referred to as any abnormal thing that III. METHODOLOGY A general approach for solving classification can be shown as in Figure 2. Eye disease is referred to as any abnormal thing that happens tothe blind system. The blind system by itself is very complicated. Figure1 shows the anatomy of the eye. The eye has a number of importance components The cornea and lens at front of the eye focus the light into a sharp image on the back of the eye, the retina is light sensitive and contains two types of photoreceptors: rods and cones. Rods are highly sensitive to light and therefore allow us to see under a low level of illumination. The eye has approximately 12 millions rods per eye. Cones are less sensitive to light than rods and can therefore tolerate more light. The eye has approximately 6 millions cons and mainly concentrated on fovea which is small area of the retina on which image are fixated. In general, diagnosis of the eye [1] requires special knowledge and skill in addition to common physical examinations. Special inspections and tools are required for diagnosis the eye diseases. Patients will servere eye diseases, who do not get the proper treatment or delay for treatment can lose their vision sense permanently. The objective of this study is to assist medical providers in screening and diagnosis of eye disease patients using patient history. In addition, the symptoms can be identified for diagnosis, treatment planning, including referral to medical specialist accurately and quickly. Artificial neural network (ANN) and Naïve Bayes (NB) illustrate the potential for medical diagnosis [2][3]. The study has the main focus on using them as classifiers for patients with eye diseases. The result can be assist a clinician’s decision in giving the right treatments to patients. This paper is structured as follows: section II provides the literature review. Section III describes the methodologies. Experimental results are discussed in Section IV. Finally, discussion, conclusion and future works are given in Section.