Kernel-based naïve bayes classifier for breast cancer prediction

The classification of breast cancer patients is of great importance in cancer diagnosis. Most classical cancer classification method are clinical-based and have limited diagnostic ability. The recent advent of machine learning technique has made an revolution in cancer diagnosis. In this research we develop a new algorithm: Kernel-Based Naive Bayes (KBNB) to classify breast cancer tumor based on memography data. Proposed algorithm performance is compared with classical navie bayes algorithm and another kerne- based decision tree algorithm C4.5. The proposed algorithm is found to outperform in the both cases. We recommend the proposed algorithm could be used as a tool to classify the breast patient for early cancer diagnosis.