Abstract
Diabetes can lead to a number of serious complications, in particular, diabetic retinopathy, which occurs in patients with diabetes and can lead to vision loss. In this regard, the development of an information system for the diagnosis of diabetic retinopathy is an important task in the medical field. Such a system can greatly facilitate the diagnostic process and help doctors detect and treat diabetic retinopathy in time. As a result of the conducted research, the urgent task of increasing the accuracy of diagnosis of fundus diseases was solved by using methods of pre-processing images to improve their informative characteristics, statistical analysis and differentiation of pathologies with the help of a decision support system based on neural network technologies. A comparative analysis of the existing methods of diagnosing diabetic retinopathy and other eye diseases was carried out, according to which it is clear that intellectual analysis and pre-processing of the received images of the fundus can significantly improve the results of diagnostics, especially early screening, which is important for preventing severe stages of the disease.