Optimizing Breast Cancer Classification with Ensemble Methods: A Focus on Bagging Techniques

Among all the cancers that occur in women, breast cancer is the leading of them all. It is also placed on second place as the death cause in women. As per a study conducted in India every 1 out of 28 women suffered from breast cancer in their life. This ratio is even higher when surveyed in urban areas, where every 1 out of 22 are suffering from breast cancer. These all results show that breast cancer is getting a more common issues from the last decade. That is the reason there had been going on a lot of researchers for the classification of breast tumor. CAD systems are being extensively used for breast cancer identity and characterization. There had been a lot of researches going on for coming up with data mining techniques that can be used for detection of breast cancer. Also it is identified that ensemble classifiers are much more efficient as compared to single classifiers. In this paper, ensemble method is being used in order to determine if the patient has breast cancer or not. The purpose of data mining is to retrieve knowledge from large sets of information or data. There are many techniques of data mining and among them the one that is most extensively used in medical science is the classification. This classification technique is mainly used in effective decision making. In this study bagging algorithm has been studied and verified how it can be applied in detection of breast cancer.