Metabolic conditions like diabetes often show up as high blood sugar levels, or hyperglycemia, which happens when the body doesn't make enough insulin. If this goes unnoticed or untreated, it can cause serious damage to critical organs such as the eyes, kidneys, nerves, heart, and blood vessels. Recently, machine learning and other computational techniques have shown great potential for predicting who might develop diabetes. But there's still room to improve how accurate and reliable these models are. In this work introduce a step-by-step machine learning approach to predict and diagnose diabetes using three different datasets. First, used Hot Deck Imputation (HDeckImp) to fill in missing data and make the classifications more accurate. Next, we apply K-fold cross-validation to test how well the model holds up with different data splits, ensuring robustness. Then, we incorporate multiple classifiers like Random Forest, XGBoost, AdaBoost, and Bagging to strengthen predictions. Finally, we developed a new weighting method called Confidence-Calibrated Adaptive Weighting (CCAW). This method dynamically gives more weight to models that are both accurate and confident, measured through information entropy, so the best models have more influence on the final outcome. Experiments show that this approach, especially with CCAW, reaches a top accuracy of 98.9% on the Frankfurt dataset, beating previous ensemble methods such as ADR-W. This improvement not only enhances prediction accuracy but also makes the model stable, which is essential for practical clinical use.
20 March 2026 in Biomedical and Pharmacology Journal
Early detection of Type 2 Diabetes (T2D) is perilous for remediating patient consequences and dropping long-term complications. This study proposes Scorpi-XStack, a diagnostic framework that integrates a novel bio-inspired optimization algorithm, ScorpiOpt, with stacked ensemble learning to enhance predictive accuracy. ScorpiOpt identifies the most discriminative clinical features by reducing redundancy and improving feature robustness. These selected features are used to train a weighted collaborative classifier containing Random Forest and XGBoost as ignoble learners, for which Logistic Regression is the master learner. The framework was validated on three benchmark datasets—Pima Indian Diabetes (Kaggle), clinical records from Medical City Hospital, Iraq (Mendeley Data), and the Frankfurt Diabetes dataset (GitHub/ResearchGate)—after applying ETL processing, mean/mode imputation for missing values, and z-score normalization. Classical recital remained assessed via stratiform 5-fold cross-validation, springy an accurateness of 98.54%, F1-score of 98.50%, balanced accuracy of 98.52% and AUROC of 99.86%. Compared with existing methods (85–95% accuracy range), Scorpi-XStack demonstrated consistent improvements across multiple performance metrics. While results are promising, limitations such as dataset heterogeneity, potential overfitting, and computational overhead should be noted. Further validation on larger, independent, and multi-center cohorts is necessary to confirm clinical applicability and generalizability.