Detecting breast cancer through blood analysis using decision tree (J48) classification algorithm

Abstract

Breast cancer is the second major cause of death in the world. Breast cancer accounts for 16% of all cancer deaths worldwide. Most of the methods of detecting breast cancer very expensive and difficult such as mammography. The objective of this research paper is detecting breast cancer through blood analysis using J48 algorithm which will serve as alternative to these expensive methods.

The J48 algorithm was used to classify 116 instances also,10-fold cross validation and holdout procedure were used coupled changing of random seed. Average accuracies of 84.65% and 89.99% were acquired for cross validation and holdout procedure. Although it was also discovered that Blood Glucose level is a major determinant in detecting breast cancer, it has to be combined with other attributes to make decision as a result of other health issues such as diabetes.