Machine Learning for Breast Cancer Detection

The increasing number of breast cancer-related deaths annually underscores the pressing need for improved prediction and diagnostic techniques. Machine learning offers a promising avenue for enhancing early detection and treatment planning. In this study, we applied various machine learning algorithms—such as K-Nearest Neighbors (KNN), Random Forest, Logistic Regression, Decision Tree (C4.5), and Support Vector Machine (SVM) o the Breast Cancer Wisconsin Diagnostic dataset. Through comprehensive evaluation and comparison of these classifiers, our primary objective was to determine the most effective method in terms of confusion matrix performance, accuracy, and precision. The results revealed that the Support Vector Machine achieved the highest accuracy at 97.2%, outperforming all other classifiers. The entire analysis was conducted using the Python programming language in Jupyter Notebook, leveraging various Python libraries including Scikit-learn, Pandas, and Numpy.