<![CDATA[Class imbalance remains a critical challenge in medical classification, particularly in breast cancer diagnosis, where misclassification of the minority class can have severe clinical consequences. This study investigates the impact of combining the Synthetic Minority Over-sampling Technique (SMOTE) and metaheuristic optimization on the performance of three traditional classifiers: Support Vector Machine (SVM), Naïve Bayes, and Random Forest, using the Wisconsin Diagnostic Breast Cancer (WDBC) dataset. Four experimental scenarios were evaluated, including baseline models, models with SMOTE, models with metaheuristic optimization, and a hybrid approach integrating both techniques. Performance was assessed using accuracy, precision, recall, F1-score, and Area Under the Curve (AUC). The results indicate that the effectiveness of the hybrid approach is highly model-dependent. SVM demonstrated the most consistent improvement, particularly when combined with SMOTE and Simulated Annealing, achieving a balanced performance across evaluation metrics with an AUC of 0.9960. In contrast, Random Forest exhibited stable performance across all scenarios with limited sensitivity to additional optimization, while Naïve Bayes showed performance degradation when combined with SMOTE, indicating potential disruption of the feature independence assumption due to synthetic data generation. These findings highlight that SMOTE and metaheuristic optimization are not universally beneficial but can enhance classification performance under specific conditions. This study provides empirical evidence to support the selective application of hybrid optimization strategies for imbalanced medical data and contributes to the advancement of intelligent classification methods in the field of artificial intelligence.]]>
Copyrights © 2026
