Using K-Means Clustering Technique to Study of Breast Cancer

Breast cancer is one of the most common cancers worldwide. In developed countries, among one in eight women develop breast cancer at some stage of their life. Early diagnosis of breast cancer plays a very important role in treatment of the disease. With the goal of identifying genes that are more correlated with the prognosis of breast cancer, we use data mining techniques to study the gene expression values of breast cancer patients with known clinical outcome. K-means clustering is used to compare the result based on test data. As a result, a set of genes are identified that are potential bio marks for breast cancer prognosis which can categorize the patients based on the certain attributes. A comparison is made on gene expression levels that are discovered with gene subsets identified from similar studies using clustering techniques.