# Enhancing-Breast-Tumor-Diagnosis-Leveraging-Support-Vector-Machine-Models
This project presents a comprehensive analysis of Support Vector Machines (SVM) in the classification of breast cancer tumors from fine-needle aspiration (FNA) test results. We explore the effectiveness of SVM in differentiating between malignant and benign tumors and identify the most significant features that contribute to classification accuracy. Our methodology encompasses a multi-phase process, including exploratory data analysis, model development, and optimization of the SVM classifier. Our results indicate that the SVM model with a linear kernel, achieved a classification accuracy of 97.06\% on the test dataset, with a sensitivity of 95.24\% and a specificity of 98.13\%. The model's precision is evidenced by positive and negative predictive values of 96.77\% and 97.22\%, respectively. Furthermore, the model's ability to discriminate between tumor classes is demonstrated by an Area Under the Curve (AUC) of 96.68\%, as determined by Receiver Operating Characteristic (ROC) curve analysis. The study's findings highlight the SVM model's potential as a diagnostic tool in the medical field, with the capacity to provide early and accurate diagnosis of breast cancer, leading to improved patient outcomes. The incorporation of this machine learning approach in clinical settings could revolutionize breast cancer diagnostics, offering a reliable, non-invasive diagnostic alternative.