Deep Neural Network–Based Automated Detection and Classification of Diabetic Retinopathy

Diabetic Retinopathy (DR) is a severe complication of diabetes that affects the retina and can lead to vision loss if not detected early. Automated DR classification using artificial intelligence has gained significant attention due to the limitations of manual diagnosis. Traditional machine learning approaches, such as the K-Nearest Neighbour (KNN) algorithm, have been widely used for DR classification, leveraging distance-based similarity measures for image classification. However, KNN struggles with high-dimensional medical image data, leading to suboptimal accuracy, longer computational time, and sensitivity to noise. To overcome these limitations, this study proposes a Deep Neural Network (DNN)-based framework for the automated detection and classification of Diabetic Retinopathy using retinal images. The model integrates Convolutional Neural Networks (CNNs) for feature extraction and a fully connected DNN for classification, ensuring efficient learning of spatial features and robust decision making. The proposed method is evaluated on publicly available DR datasets, achieving higher accuracy, sensitivity, and specificity compared to traditional KNN-based approaches. Results demonstrate that DNN outperforms KNN in handling complex retinal features, reducing false positive rates, and enhancing early-stage DR detection. This study highlights the potential of deep learning in enhancing clinical decision support systems, providing an accurate and scalable solution for automated DR screening. Future work may involve hybrid models combining deep learning with explainable AI techniques to improve interpretability and clinical adoption.