Retinal disease needs to be anticipated because the retina is an essential organ. In this instance, the goal of the paper is to forecast retinal disease using deep learning approaches, particularly the deployment of convolutional neural networks (CNNs) with an emphasis on the VGG16 architecture. The principal aim of this research is to provide a reliable and precise framework for the segmentation of blood vessels and subsequent classification, which would facilitate the early identification and diagnosis of retinal disorders. The use of VGG16, a well-known CNN architecture with a reputation for performance and depth, emphasizes the dedication to reaching higher accuracy in disease classification and blood vessel segmentation. Nonetheless, the outcomes show a promising 80.65% training accuracy and 67.18% validation accuracy in predicting retinal diseases, which showcases the potential of proposed methodology.