Breast Cancer Staging Prediction Based on Logistic Regression Model

Abstract

Breast cancer is one of the most common diseases in women. It is important to diagnose whether a patient’s breast cancer is benign or malignant as early as possible because there are different treatments for different stages. If the spread of cancer and tumors can be controlled early, patient’s suffering can be reduced and survival rates improved. In order to determine if a patient has benign or malignant breast cancer, this article will develop a breast cancer staging prediction model using a popular machine learning approach called logistic regression. The Wisconsin Breast Cancer Diagnosis (WBCD) dataset, provided by the University of Irvine Machine Learning, is the basis for the logistic regression model used in this study. A confusion matrix is utilized to assess the model’s accuracy as well as Type I and Type II errors. The Type I and Type II errors’ percentages are very small, the accuracy of the logistic regression model is 94.958%, which is not very high thus it may not be recommended for people to use and rely on this model to predict breast cancer, people can consider other prediction models. Furthermore, there may be several factors which may lead to the low logistic regression model’s accuracy, such as the size of the database, selection of samples, or the selection of variables.