M. Thangavel, A.M. Kalpana, S. Ananth 03 08 Diabetes and its complications particularly Diabetic Retinopathy DR and Diabetic Nephropathy DN pose significant challenges to global healthcare systems requiring accurate predictive models for early diagnosis and intervention Traditional approaches often underperform due to imbalanced datasets and complex feature interactions Publicly available datasets including structured diabetic clinical data and the APTOS 2019 retinal fundus images were utilized Preprocessing involved KNN imputer for missing values outlier detection and handling MinMax scaling and SMOTE oversampling to balance the data Multiple machine learning models were implemented for classification including variants of Logistic Regression Random Forest XGBoost LightGBM CatBoost MultiLayer Perceptron as well as hybrid ensemble approaches Advanced models were further developed comprising StackingClassifier EnsembleofEnsembles and image classification architectures including ResNet50 DenseNet121 Xception NasNetLarge and an ensemble of Xception DenseNet121 Evaluation metrics included Accuracy Precision Recall F1Score ROCAUC RMSE and LogLoss DenseNet121 achieved the highest classification performance with 996 Accuracy while StackingClassifier Oversampled reached 999 Accuracy for nephropathy and LightGBM OverSampled attained 996 Accuracy for retinopathy Explainable AI techniques including LIME SHAP and GradCAM provided model interpretability and a Flask frameworkbased interface enabled userfriendly prediction deployment ensuring accurate transparent and actionable clinical decision support Copyright (c) Journal of Science Engineering Technology and Management Science. All rights reserved 2026