Breast Cancer Risk Analysis using Machine Learning

Abstract

When cells in and around breast are affected and damaged due to cancer, we call it Breast Cancer. It is commonlyfound among women and a very few men. Breast Cancer poses major health hazard and best way to handle itis to identify the symptoms as early as possible. Recently, Machine Learning techniques have been aggressivelyused by many researchers for different types of analysis and predictions in medical domain. In literature, BreastCancer classification and prediction through Machine Learning techniques, based on Breast Cancer WisconsinData Set, has come into picture many times. Typical attributes like radius, perimeter, tumour size (often fetchthrough X-Rays) apart from others, provides comprehensive inputs for the prediction process, often at a laterstage. However, till date, work on evaluation of the Risk of Breast Cancer is quite limited. We have worked onthe problem of risk prediction of breast cancer on the basis of self-assessed parameters, to find if the patient islikely to get the disease, at a very early stage. Risk evaluation / prediction tries to identify if a person is at riskof getting infected with disease. Risk analysis can not only save money but also enable the patient to undertakecourse correction in terms of food intake and medication, before it is too late. In this paper we present our analysisbased on well-defined parameters, discuss our results and then compare those results with one other similar work.