Effective Analysis of Machine Learning Algorithms for Breast Cancer Prediction

Early prognosis of Breast Cancer (BC) is significantly important to cure the disease easily so it is essential to develop methods that is able to aid doctors to get precise prognosis. Hence, a BC prognosis methodology is proposed utilizing Machine Learning (ML) approaches. The target of this paper is to utilize classification techniques to classify tumor types, or benign and malignant cells, using 569 samples from Wisconsin Diagnostic Breast Cancer (WDBC) database. Initially, preprocessing is employed to enhance the data’s quality, which includes data cleaning and min-max normalization. It improves the input breast cancer data's quality, accuracy, and suitability for further analysis. Followed by preprocessing, the ML approaches such as K-Nearest Neighbour (KNN), Random Forest (RF) and Support Vector Machine (SVM) methods are analyzed for the classification of BC data. Each algorithm offers a distinct approach to classification by capturing local patterns in data and handles high-dimensional spaces along with nonlinear boundaries through kernel tricks. The developed work is implemented in python software and comparative analysis is done with traditional methods. The outcomes demonstrates that the proposed KNN classifier shows better performance interms of precision, recall, F1-score with an accuracy of 96.49%, ensuring the earliest diagnosis of breast cancer compared with SVM and RF. This comparative approach enhances the reliability of the proposed methodology and supports the selection of the best-performing algorithm offering valuable insights for real-world clinical decision support systems.