Early Medical Diagnosis of Breast Cancer in Women Using Support Vector Machine Algorithm in Comparison with CNN Algorithm

Breast cancer remains a major health challenge, and improving detection methods is crucial for better outcomes. This study aims to enhance breast cancer detection by comparing two advanced algorithms. Using a trained dataset, we evaluate how well each algorithm predicts breast cancer risk. Both algorithms were tested with 10 samples each. The SVM algorithm, a supervised learning technique grounded in statistical learning theory, showed impressive accuracy in detecting breast cancer, achieving <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{9 5. 7 0 \%}$</tex>. On the other hand, the CNN algorithm, known for its powerful classification and prediction capabilities, achieved an accuracy of <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{9 0. 8 1 \%}$</tex>. For both algorithms, we set the significance level to <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$(p&lt;0.05)$</tex> to ensure robust results. Our findings suggest that the SVM algorithm outperforms the CNN algorithm in breast cancer prediction.