Predictive Modeling of Breast Cancer Subtypes Using Machine Learning Algorithms

In this study, we aimed to classify breast cancer patients into four molecular subtypes: Luminal A, Luminal B, Her-2, and triple negative, using six machine learning techniques: logistic regression (LR), naive Bayes (NB), k-nearest neighbors (KNN), support vector machine (SVM), decision tree (DT), and random forest (RF). We evaluated the performance of each model using several evaluation metrics, including accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC). The dataset used in this study was obtained in real-time from breast cancer patients, and includes immunohistochemistry (IHC) marker reports. Our results show that all six models achieved high accuracy and AUC scores, indicating their effectiveness in classifying breast cancer patients into molecular subtypes. However, the random forest model outperformed the other models with an AUC score of + 0.95, followed by Logistic Regression with an AUC score of 0.91. These findings demonstrate the potential of machine learning techniques in accurately classifying breast cancer patients into molecular subtypes, which could inform clinical decision-making and personalized treatment strategies.