IABCP: an Integrated Approach for Breast Cancer Prediction

Breast cancer detection and prognosis may result in better medication being provided early, lowering the number of deaths caused by the illness each year and presenting a potentially significant danger to human health. Even though many academics have developed Additional research is also being undertaken in this field by other researchers employing Machine Learning (ML) approaches for the prognostication of chronic illnesses such as diabetes, heart disease, and cancer using both manually generated datasets and publicly available datasets. Based on the support vector machine (SVM) classifier, principal component analysis (PCA), and recursive feature elimination (RFE), this study suggested an Integrated Approach for Breast Cancer Prediction (IABCP) for predicting this chronic disease. Several experiments were carried out using the UCI-ML warehouse-based dataset WBCD, i.e., the Wisconsin breast cancer dataset (WBCD), and Python coding in a Jupyter notebook. Various experiments are taken place and results are obtained as accuracy, precision, recall, and f-measures of 97.87%, 98.55%, 98.77%, and 97.14% respectively. The results revealed that the recommended technique outperforms other typical approaches and is effective in the context of this research.