Breast cancer is a very dangerous disease. It is considered as one of the most serious threats to women's health. To treat breast cancer, surgery and chemotherapy are two common approaches. It is important to diagnose breast cancer early to minimize the severity and increase the chance of cure. This study aims to classify breast cancer diagnoses using Logistic Regression. The data used is secondary data downloaded from Kaggle.com totaling 569 records. The data is processed through encoding to change the data type into numeric. Data must also go through outlier handling to remove the same data or excess data that does not match the z-score requirements. Then the data that is ready to be processed is then divided into training and testing data with a ratio of 70%: 30%. This study produces an accuracy rate of 98% on the prediction of breast cancer patients after classification modeling and model testing using the confusion matrix method.
Copyrights © 2023