Efficient Ensemble RAB-SVM Framework Using African Buffalo Algorithm for Accurate Glaucoma Detection and Classification

Glaucoma is a progressive eye disease that damages the optic nerve and can lead to irreversible blindness. Manual detection from medical images is complex and leads to errors. Machine learning (ML) algorithms offer significant advantages in automatically detecting glaucoma, with Fuzzy c-means clustering, Logistic Regression, Support Vector Machine (SVM), and Deep Learning (DL) being the most commonly used. While these models offer promising results, they often suffer from limitations such as limited generalization to new data and sensitivity to noise and feature imbalance. Hence, to overcome the limitations, this paper proposes an Ensemble Random Adaptive Support Vector based Random African Buffalo (ERAS-RAB) algorithm to detect and classify it. Evaluated using the Glaucoma Fundus Imaging dataset, the proposed system outperforms several baseline methods, achieving an Accuracy of 99.21%, a Precision of 99.09%, a Recall of 98.96%, and an F1-Score of 99.02%, demonstrating its efficacy in early glaucoma diagnosis. This work demonstrates the potential of hybrid ensemble models in medical image analysis, providing a reliable framework for integrating Artificial Intelligence (AI) into ophthalmic diagnostics.