Advancing Breast Cancer Prediction Using Logistic Regression and Machine Learning Techniques

The second leading cause of death global is cancer. In 2015, 8.8 million people lost their lives to cancer. The most common cause of mortality for women is breast cancer. Research on early identification of breast cancer to initiate therapy and improve survival rates has been conducted in a number of ways. Breast cancer is a diverse illness with several molecular kinds and forms. Breast cancer is the only kind of cancer that affects women worldwide, and it may be a common cause of death. This paper's main goal is to develop a model for predicting breast cancer utilizing several machines. Moreover, compare and assess the recall, accuracy, precision, f1-Score, and support performance of the different classifiers. This study proposes a machine learning (ML) approach to identify patients with triple negative breast cancer from those without it by using gene expression data. Among the many techniques machine learning researchers have been using to improve accuracy is precisely classifying samples that belong to the majority class while ignoring those that belong to the minority class. Teaching computers to learn and work without clear programming or instructions is known as machine learning. Then, the learned data is applied to predict the likelihood of breast cancer. Furthermore, the datasets used for breast cancer diagnosis and detection is used. Images and blood among other data kinds can be employed with the proposed model. The prediction outcomes show how well machine learning algorithms work and how they may be used to distinguish between triple negative and non-triple negative breast cancer.