Optimizing Breast Cancer Prediction by Implementing Feature Selection with Principal Component Analysis

Breast cancer is a major global health concern, where early detection plays a pivotal role in improving patient outcomes. Advances in machine learning (ML) offer significant potential in enhancing the accuracy of cancer diagnosis, leading to more effective treatment strategies. This study explores the application of machine learning techniques for breast cancer prediction, utilizing a dataset collected from cancer hospitals in Pune, Maharashtra, India. The data includes clinical and diagnostic variables, such as lifestyle factors, hereditary background, and cancer stages. The primary focus of this research work is to evaluate the impact of dimensionality reduction using Principal Component Analysis (PCA) on the performance of several machine learning classifiers. By reducing the dimensionality of the dataset, the study aims to improve model interpretability, computational efficiency, and predictive accuracy. The classifiers are evaluated both with and without PCA to determine the optimal approach for breast cancer classification. The results indicate that PCA significantly enhances model performance in terms of accuracy, efficiency, and generalizability, offering a more streamlined approach to breast cancer prediction. This research work suggests that incorporating dimensionality reduction into machine learning workflows can provide valuable support for early diagnosis and personalized treatment in breast cancer care.