Diagnosis of breast cancer using secured classifiers

Abstract

One of the most important tasks for variant approaches such as text categorization, voice recognition, image processing, proteins structure predictions, microarray gene expression and so on is classification. The majority of the current supervised classification techniques are based on traditional statistics, that can provide perfect results when the sample size is tending to infinity. However, samples can be acquired if only they are finite in practice. In this paper, we applied four different classifiers on the patients' data collected. The data consists of breast cancer parameters of 423 Egyptian females. This study aimed to early detect the existence of breast cancer in Egyptian society. After measuring the accuracy of each classifier across all classes, we concluded that ANN classifier can be considered as the nearly best classifier with 95% 72% and 81% accuracy to class 1, class 2 and class 3 respectively.