A Fuzzy Approach to Determining Critical Factors of Diabetic Retinopathy and Enhancing Data Classification Accuracy

Diabetic retinopathy (DR) is a chronic and progressive sight-threatening complication of retinal microvasculature associated with diabetes mellitus. These morphological subtle variations in the retina can result in visual impairment or eventual vision loss if not treated in time. The early detection and diagnosis of DR is mandatory to safeguard the patient's vision. To investigate and intervene at an earlier stage, we aim to systematically extract and analyze different DR factors, such as retinal condition of eyes, presence of microaneurysms (MAs), MAs with exudate, diameter of optical disk (OD), and Euclidian distance between macula and center of the OD. Considering the DR attributes, first we find out the important attributes of DR by applying fuzzy analytical network process to rank attributes from the most to the least related factors to DR. Then, a transformed fuzzy neural network is created to enhance the classification accuracy. Finally, we extract association rules among the selected attributes of DR to reveal their importance and degree of severity. Findings of this study reveal a new perspective on the treatment of DR at the early stage and prevention from any complications to improve the quality of life of all people.