Optimizing Early Detection of Breast Cancer: A Cluster-Based Classification Approach

Breast cancer remains a significant health concern with rising global incidence, particularly among women. Despite advancements in detection and treatment, reducing mortality rates continues to be challenging. Early detection is crucial for improving survival rates, especially for small tumors. This study proposes a cluster-based classification approach using the K-means algorithm, Naive Bayes, and Decision Tree classifiers, enhanced by feature selection with a genetic algorithm and meta-learning through stacking. Evaluated on the Wisconsin Diagnostic Breast Cancer dataset, the framework achieved full accuracy in predictions. Future research could explore larger datasets, optimization techniques, and user-friendly interfaces for medical professionals.

Keywords:

Breast Cancer , Machine Learning , Classification , Clustering , Ensemble Learning , Feature Selection , Genetic Algorithm