Authors - Sanjida Karim Peuly, Sharmin Alam Mou, Tamanna Hossain Badhon Abstract - Diabetes diagnosis at the early stages is an important factor in avoiding long-term complications. The existing body of literature tends to be based on small, saturated datasets that are not very interpretable and externalized. This pa-per will suggest a powerful machine learning model to predict diseases at the first stage of diabetes on the basis of a symptom-based dataset of One thousand five hundred and sixty cases. Six classifiers, including Logistic Regression, Decision Tree, Random Forest, K-Nearest Neighbors, Naive Bayes, and XGBoost, were considered on the stratified cross-validation and independent test sets. Systematic hyperparameter optimization using GridSearchCV was used to prevent overfit-ting and improve the generalization. Additionally, a Stacking Ensemble model was provided; the Logistic Regression, Random Forest, and XGBoost were com-bined to obtain a high level of predictive stability. Experimental evidence has shown that ensemble-based methods are more effective than single classifiers, as XGBoost and Stacking Ensemble have the highest accuracy and ROC-AUC val-ues. The analysis of feature importance suggested polyuria and polydipsia as the most important clinical signs, which is consistent with medical knowledge. This study offers a practical and interpretable decision support model in screening early diabetes, which bridges the predictive performance and clinical utility gap.
Open Zoom