Abstract
Breast cancer is the leading cause of cancer-related mortality among women, presenting a significant health challenge. This study introduces a method that leverages dimensionality reduction, specifically Principal Component Analysis (PCA), to enhance the accuracy of existing breast cancer detection techniques. By applying PCA and Linear Discriminant Analysis (LDA), our research utilizes the Wisconsin breast cancer dataset to validate the improved performance of these methods. The findings indicate that incorporating PCA into the detection models significantly enhances prediction accuracy and model performance.