In this paper, we aimed to investigate how sustainable development can be involved in educational contexts that use new trends in technology such as Artificial Intelligence (AI) and Data Science (DS). To achieve this goal, we conducted a documentary Systematic Review using PRISMA research to find and analyze applications of sustainable development in these aforementioned contexts. In the results, we explain how some applications of both AI and DS, including Big Data and Learning Analytics among others, offer alternatives to substantially improve the educational process by allowing either education to be personalized, learning to be predicted, or even possible school dropouts to be predicted. We found that the COVID emergency sped up the introduction of these technologies in educational environments. Nevertheless, the inclusion of new technologies to develop better processes in education is still in progress and will continue to grow. In conclusion, we identified and analyzed some of the main applications found in the literature regarding new computing technologies. AI and DS have introduced new learning and teaching methods to solve different context problems that promote sustainable development while making educational environments more dynamic. On the other hand, we observed that the divide in many countries will continue due to their economic and technological situations. We describe some of the challenges that the incorporation of these technologies will bring in the near future.

Background: Ocular diseases have been a severe problem worldwide, specifically in underdeveloped countries that do not have enough technology or economy to treat them. It would be beneficial to have software with low installation complexity and ease of use, allowing high efficacy in diagnosing eye diseases. This study aims to design and implement an algorithm based on deep learning to classify ocular diseases with high precision. Methods: This work describes digital image processing techniques for the easier handling of eye images; in particular, blur filters were used. The Canny filter was also applied to obtain the edges that allow the difference between the analyzed diseases. Once the images were pre-processed, a convolutional neural network of our own design was applied to perform the classification task. The validation algorithm used in this work was the hold-out algorithm (80–20). The metrics used to evaluate our proposal were the confusion matrix, accuracy, recall precision, and F1-score. Results: The dataset has five classes, namely, normal, cataract, diabetic retinopathy, glaucoma, and other retina diseases. The network architecture consists of 11 layers, including three convolutional layers, three max pooling layers, one batch normalization layer, one flattening layer, two hidden layers, and one output layer. This model resulted in 97% efficiency across all metrics. Conclusions: With the individual analysis of each metric, it can be observed that the proposed algorithm is capable of differentiating, first, images of healthy eyes from diseased ones and, second, adequately classifying eye diseases.

Background: Ocular diseases have been a severe problem worldwide, specifically in underdeveloped countries that do not have enough technology or economy to treat them. It would be beneficial to have software with low installation complexity and ease of use, allowing allowing the high efficacy in diagnosing eye diseases. This study aims to design and implement an algorithm based on Deep Learning to classify ocular diseases with high precision; (2) Methods: This work de-scribes digital image processing techniques for easier handling of eye images; in particular, Blur filters were used. The Canny filter was also applied to obtain the edges that allow the difference between the analyzed diseases. Once the images were pre-processed, a Convolutional Neural Network of our own design was applied to perform the classification task. The validation algorithm used in this work was the Hold-Out (80-20). The metrics used to evaluate our proposal were the confusion matrix, accuracy, recall precision, and F1-score; (3) Results: The dataset has five classes: Normal, Cataract, Diabetic Retinopathy, Glaucoma, and other Retina diseases. The network ar-chitecture consists of 11 layers, including three Convolutional layers, three Max Pooling layers, one Batch Normalization layer, one Flattening layer, two Hidden layers, and one output layer. This model resulted in 97% efficiency across all metrics; Conclusions: With the individual analysis of each metric, it can be observed that the proposed algorithm is capable of differentiating, first, normal images from diseased ones, and second, adequately classifying eye diseases.