Improving Diabetic Retinopathy Prediction with Stacked Generalization and Out-of-Fold Learning

Diabetic retinopathy (DR) is a serious microvascular complication of diabetes that causes significantvision impairment worldwide. Because DR is usually asymptomatic in its early stages, frequent retinalscreening is essential to prevent permanent blindness. However, manual screening is time-consuming,labour-intensive, and difficult to scale in regions with limited expertise. These challenges have led to thedevelopment of automated computer-aided systems that enable effective, inexpensive monitoring ofretinal disease.This paper, motivated by advances in ensemble learning for medical decision support, proposes astacking-based classification system to predict retinal abnormalities using the Retinadataset. Thearchitecture consists of four base learners—Random Forest (RF), Extra Trees(ET), Histogram GradientBoosting, and Logistic Regression(LR)—whose out-of-fold predictions, produced via 10-fold stratifiedcross-validation, are combined to form a meta-level feature matrix. AnLR meta-learner generates thefinal predictions.The proposed system was evaluated against various single-base models, including LR,RF, SupportVector Machines(SVM), Naive Bayes(NB), Decision Trees(DT), and a blending ensemble.Experimental results demonstrate that the ensemble approach is more predictive, robust, and balancedin classification than individual learners. The Tuned Ensemble achieved the highest performance:77.15% accuracy, 70.87% sensitivity, 84.26% specificity, 83.59% precision, 76.71% F1-score, 54.58%Kappa, and an 84.09% area under the ROC curve (AUC). The Blending Ensemble achieved the bestAUC and a slightly higher sensitivity, while LR was the best-performing single classifier.These findings suggest that stacking-based ensemble learning provides a strong, interpretable frameworkfor the automated screening of retinal abnormalities and could supplement clinical risk assessment in theearly stages.