Breast Cancer Detection in the Philippines Using Machine Learning Approaches
Maria Maura S. Tinao, Ruth B. Rodriguez, Eunelfa Regie F. Calibara · 2024
This study explores the prediction of breast cancer utilizing advanced machine learning techniques such as K-Nearest Neighbor (KNN), Decision Tree, Support Vector Machine (SVM), and Logistic Regression. The objective is to ascertain individuals who are at a heightened risk for the purpose of promptly identifying and providing therapy. This research employs a set of ten breast cancer features identified in Rabiel et al.'s (2022) study. The dataset utilized in this study consists of anonymised information collected from a sample of 112 women, selected by a random sampling method. The study's main findings indicate a notable occurrence of stress related to life events, family problems, and marital status. Additionally, a considerable proportion of participants reported having a family history of breast cancer. The K-nearest neighbors (KNN) model demonstrates the highest level of accuracy, reaching a rate of 0.8696. This indicates that the model successfully classifies 86.96% of the cases.