Breast Cancer Diagnosis: A Multi-Model Machine Learning Approach

Breast cancer occurs when irregular breast cells multiply uncontrollably, forming tumors that can become fatal if left untreated and spread throughout the body. Timely detection plays a vital role in enhancing survival rates and securing successful treatment outcomes. Artificial intelligence (AI) is essential in breast cancer prediction, making it an important area of study for medical experts and researchers alike. This work evaluates several machine learning (ML) techniques for detecting breast cancer using the Wisconsin Breast Cancer dataset, which consists of 32 features and 569 observations. In our approach, XGBoost outperformed six other machine learning techniques: Logistic Regression (LR), Support Vector Machines (SVM), Random Forest (RF), K-Nearest Neighbors (KNN), Decision Trees (DT), and Gradient Boosting(GB). Performance metrics, including accuracy, sensitivity, precision, F1 score, and AUC-ROC, were used to compare the effectiveness of each technique. The xGBoost outperformed all other classifiers, as research outcomes show it has the accuracy, sensitivity, precision, and F1 score of 98.86%, 99.28%, 97%, and 98% with an AUC-ROC of 0.99, respectively.