Mahdi Hemmasian-Ettefagh - Faculty of Computer Engineering, Najafabad branch, Islamic Azad University, Najafabad, Iran
Mohammad-hossein Nadimi-Shahraki - Assistant professor, Department of Computer Engineering, Najafabad branch, Islamic AzadUniversity, Najafabad, Iran
Mahnaz Etehad-Tavakol - Medical Image and Signal Processing Research Center, Isfahan University of Medical Sciences,Isfahan, Iran
Maede Behbahani - superintendent of Breast Cancer Screening Unit in Askarieh Specialized Hospital, Isfahan, Iran

Breast Cancer is the second most common cancer among women and is the second largest cause of death in the world. Early detection can be very effective and can play an important role for treatment. Annually, approximately more than 1,700,000 women worldwide are detected to have thisdisease. There is an increase of around 2% in the breast cancer incidence rate yearly. There are several risk factors for Breast Cancer. Some of them have been proven, some are still having controversial reported results and some are almost rejected. Sometimes maternal age at first birth,age at marriage and number of children are considered as risk factors. However they sometimes are taken as protective measures. In this paper, we proposed a model which can predict the Percentage of Suffering for a person having breast cancer. Some of risk factors are modeled and some impact factors are chosen for them. In this study, the proposed algorithm is implemented and evaluated using data from Breast Cancer Surveillance Consortium (BCSC) in National Cancer Institute

Breast Cancer, Risk Factor, Data Mining, Screening, EM Algorithm