Machine learning-based diagnosis of eye-diseases

Abstract

Over the last several years, artificial intelligence (AI) has been substantially utilized in image processing and classification. Several tools are accessible for visualizing, training, and pre-processing image data. One such tool is orange, which has several pre-processing modules and a particular add-on for image processing methods in addition to excellent data visualization. The tool (version 3.32.0) was used in the suggested study to give a comparative and predictive analysis using several classification models. Three main models have been used to train and predict the three groups image eye diseases. The results were compared based on some criteria, including area-under-a-curve (AUC), the accuracy of classification (CA), F1 score, precision, and recall. These models include K-nearest neighbour (KNN), logistic regression (LR), artificial neural networks (ANN) and stacking model. The stacking model, which is a novel model, is also presented in this work by concatenating the output of the parallel form of ANN and KNN models with the LR model. The best performance belonged to the Stacking model, which offers the best detection and prediction results.