Litcius/Paper detail

Enhanced Diabetes Diagnosis Using Ensemble Classifiers with Explainable AI and Oversampling for Imbalanced Data

Chennaiah Kate, G. Deepika, M Sravya, Raveendranadh Bokka, Sanjay Kumar, Sangeetha Ganesan

202522 citationsDOI

Abstract

Diabetes risk assessment is a key task in healthcare, aiming to identify individuals at risk and initiate early interventions to slow disease progression. Diabetes remains a critical global health concern, necessitating early and accurate diagnostic tools to mitigate long-term complications. This study proposes an enhanced diabetes prediction framework utilizing ensemble machine learning classifiers, explainable AI (XAI), and oversampling technique-SMOTE to address data imbalance. Leveraging the PIMA Indian Diabetes Dataset, the study conducts extensive preprocessing, including outlier handling, skewness correction using Box-Cox transformation, and feature selection via ANOVA F -score. Ensemble classifiers-Random Forest, Extra Trees, Voting, and Stacking were evaluated using evaluation metrics. Among these, the Extra Trees Classifier achieved the highest accuracy of 96.58%, while Random Forest demonstrated strong AUC-ROC performance. Explainable AI technique-SHAP was employed to interpret model predictions and identify key influencing features, such as glucose levels, BMI, and age. The results confirm that ensemble models, when integrated with robust preprocessing and interpretability techniques, significantly enhance the reliability and transparency of diabetes diagnosis. This research highlights that Ensemble classifiers are increasingly being used for diabetes diagnosis, employing machine learning methods to improve accuracy and enable early detection. The integration of oversampling (SMOTE), ensemble learning, and explainable AI significantly improved model performance and interpretability, demonstrating strong potential for clinical decision support systems in diabetes diagnosis.

Topics & Concepts

Random forestEnsemble learningInterpretabilityMachine learningArtificial intelligenceComputer scienceOversamplingRandom subspace methodPreprocessorFeature selectionClassifier (UML)Decision treeOutlierAdaBoostData miningStatistical classificationAnomaly detectionOverfittingSkewnessEnsemble forecastingData pre-processingBoosting (machine learning)Diabetes mellitusNaive Bayes classifierBootstrap aggregatingPattern recognition (psychology)Artificial Intelligence in HealthcareImbalanced Data Classification Techniques