Bridging Traditional and AI Methods: A Novel Approach to Breast Cancer Prediction

Cancer ranks as the second leading cause of death worldwide, with 8.8 million fatalities attributed to it in 2015. Among women, breast cancer is the foremost cause of mortality. Numerous studies have been conducted to identify breast cancer at an early stage, which is critical for initiating treatment and improving survival rates. Breast cancer is a complex disease characterized by various types and forms. It uniquely affects women globally and can often result in death. The primary objective of this paper is to develop a predictive model for breast cancer using different machine learning techniques. It will also evaluate and compare the performance of various classifiers based on metrics such as recall, accuracy, precision, F1-score, and support. We propose employing a machine learning approach to identify patients with triple-negative breast cancer by analyzing their gene expression data. Researchers in machine learning have been experimenting with different methods to enhance outcomes, particularly focusing on accurately classifying samples from the larger population while giving less emphasis to those from smaller groups. Machine learning refers to the process of teaching computers to learn and perform tasks independently, without explicit programming or instructions. In this context, the data is utilized to estimate the likelihood of developing breast cancer. This article also includes the data used for the diagnosis and detection of breast cancer. The proposed model is capable of utilizing various types of information, including imaging and blood samples. The findings illustrate the potential of machine learning to effectively distinguish between triple-negative breast cancer and other cancer types.