eng Oriental Scientific Publishing Company Biomedical and Pharmacology Journal 0974-6242 2026-03-20 19 1 386 397 /10.13005/bpj/3359 70407 article Usha Velusamy 1 Sathya Velusamy 2 Anitha Thambiayyan 3 Sathiya Priya Selvaraj 4 Vinodhini Kanakaraj 1 Madhumitha Chidambaram 1 Department of Computer Science and Engineering, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Chennai, India. Department of Information Technology, Velammal Engineering College, Surapet, Chennai. Department of Artificial Intelligence and Data Science, Vel Tech Multi Tech Dr.Rangarajan Dr.Sakunthala Engineering College, Chennai, India. Department of Information Technology, Vel Tech High Tech Dr.Rangarajan Dr.Sakunthala Engineering College, Chennai, India. 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. https://biomedpharmajournal.org/vol19no1/scorpi-xstack-improving-type-2-diabetes-prediction-via-feature-optimization-and-stacking/ Diabetes Prediction Metaheuristic Optimization ScorpiOpt Scorpi-XStack Stacked Ensemble Learning