A knowledge-based system for breast cancer classification using fuzzy logic method

Breast cancer has become a common disease around the world. Expert systems are valuable tools that have been successful for the disease diagnosis. In this research, we accordingly develop a new knowledge-based system for classification of breast cancer disease using clustering, noise removal, and classification techniques. Expectation Maximization (EM) is used as a clustering method to cluster the data in similar groups. We then use Classification and Regression Trees (CART) to generate the fuzzy rules to be used for the classification of breast cancer disease in the knowledge-based system of fuzzy rule-based reasoning method. To overcome the multi-collinearity issue, we incorporate Principal Component Analysis (PCA) in the proposed knowledge-based system. Experimental results on Wisconsin Diagnostic Breast Cancer and Mammographic mass datasets show that proposed methods remarkably improves the prediction accuracy of breast cancer. The proposed knowledge-based system can be used as a clinical decision support system to assist medical practitioners in the healthcare practice.