Stage – Specific predictive models for main prognosis measures of breast cancer

Abstract

Breast cancer is a malignant tumor that starts in the cells of the breast. A malignant tumor is a group of cancer cells that can grow into near tissues or invading the distant areas of the body. The disease occurs almost entirely in women, but men can get it, too. Survival rate, recurrence detection and disease-free survival rate (DFS) are the main patient's outcome and prognosis measures. Breast cancer outcomes are vary among different stages of the disease. There are five stages of breast cancer named as 0, 1, 2, 3, and 4. Prognosis helps doctors to save patients' lives by estimating how patient will progress in the therapy plan by comparing the patient's results with another patient's has the same disease characteristics and completed his therapy plan. In Egypt breast cancer represented 21.6% of 33,000 women cancer deaths Ibrahim et al.,2014, with incidence rate (48.8/100,000) and mortality rate (19.2/100,000). We selected a sample about 1692 cases were diagnosed as breast cancer patients at the period from 2010 to 2012 taken from the cases recorded in the Tumors Hospital and Institute of First Settlement one of the National Cancer Institute “NCI” cancer hospitals in Egypt. NCI is the central cancer institute in Egypt. We select the main sufficient attributes to building a prognosis predictive model 0.1471 records have been selected form the whole sample. The data set we select is used to compute and predict the three main outcome of prognosis measure at two level, data level for the complete data set, stage level for every stage of breast cancer separately. The study uses efficient five prediction models with highest accuracy. Results shows that the 5-years survival rate and local recurrence was in continuous decreasing since 2010 to 2012. Metastatic as a type of breast cancer recurrence was 20.74% in 2010, 17.59% in 2011 and 22.35% in 2012.The DFS (Disease-Free Survival) have the worst rate ever in 2012 as 7.13% after it was 30.37% in 2010.Prognosis predictive models results shows that the SVM classifiers is the most accurate model to predict the three prognosis measures at the two data level.