BREAST CANCER DIAGNOSTIC SYSTEM USING DECISION TREE ALGORITHM AND SYNTHETIC SUPPORT VECTOR MACHINE.

Abstract

Breast cancer is the most common cancer among women in the Africa. Every thirteen minutes a woman dies of breast cancer. These facts have led researchers to continue studying how to diagnose and treat breast cancer in women, especially older women, who are at higher risk. Sonography (ultrasound) has become a great addition to mammography and magnetic resonance imaging (MRI) for imaging techniques dedicated to providing breast cancer screening. Identifying a high classifier algorithm that will help to proffer solutions to medical experts is crucial to the development of medical data expert systems for diagnosis of breast cancer in women. This paper focuses majorly on a study to improve the general low accuracy in classification algorithms by hybridizing Support Vectors Machine and Classification Regression Tree Decision Algorithm (CART) for breast cancer diagnosis. Two cases; Case A and Case B are mentioned, the result of Case B shows higher accuracy of 95.032400% with low mis-classification of 4.9676%, when synthetic support vector machine is used with Decision Tree compared to Case A when synthetic SVM is not applied.