BREAST CANCER PREDICTION USING MACHINE LEARNING MODELS

Abstract

Predictive modeling using machine learning techniques plays an important role in various fields. We can explore the use of machine learning algorithms to predict outcomes such as disease progression, stock prices, or customer behavior. Using large data sets and advanced algorithms, we aim to increase accuracy and provide useful information for decision makers. Worldwide, breast cancer is the most frequent cancer diagnosed in women, and its incidence is rising yearly. Early diagnosis and accurate detection of relapse are essential to improve prognosis. In this study, To determine which machine learning (ML) method was most effective in predicting the recurrence of breast cancer, we examined several models. Eleven machine learning algorithms can be used to create a prediction model: logistic regression (LR), random forest (RF), support vector classification (SVC), decision tree, multi layer perceptron (MLP), extreme gradient boosting (XGBoost), gradient boosting decision tree (GBDT), Adaptive Boosting (AdaBoost), Linear Discriminant Analysis (LDA), Gaussian Naive Bayes (GaussianNB), and Light Gradient Boosting Machine (LightGBM). Metrics like area under the curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and F1 score were used to assess each algorithm's performance.