Breast Cancer Detection: SVM and SMOTE Integration for Fine Needle Aspiration Feature Analysis

The paper presents an innovative approach for predicting breast cancer by employing fine-needle aspiration (FNA), the synthetic minority oversampling method (SMOTE), and a Cubic Support Vector Machine (c-SVM) to generate synthetic data and classify the obtained information, respectively. The dataset employed in our study reflects the intricacies of real-world scenarios, and our methodology addresses the inherent class imbalance by leveraging SMOTE to augment minority classes, thereby facilitating a more robust and balanced model. Subsequently, the classification task was undertaken by employing C-SVM, a powerful machine-learning algorithm known for its ability to capture complex decision boundaries. The proposed model achieved validation accuracy of 98.2% and AUC of 0.998, underscoring its efficacy in discriminating between benign and malignant breast lesions. The testing phase confirmed the reliability of our approach, with a 98.2% success rate and an AUC of 1.