Breast Cancer Prediction Applying Different Classification Algorithm with Comparative Analysis using WEKA

Abstract

At present world, Breast cancer is a second main cause of cancer death in women after lung cancer. Breast cancer occurs when some breast cells begin to raise abnormally. It can arise in any portion of the Breast and it can be prevented if the treatment is started at the early stage of the Breast cancer. Breast cancer is a malignant tumour i.e. a collection of cancer cells arising from the cells of the breast Treatment of breast cancer relies on the cancer type and its stage (zero to fourth) and may include surgery, radiation, or chemotherapy. Mainly this paper focused on diagnosing the Breast cancer disease using various classification algorithm with the help of data mining tools. Data mining of the intelligent accumulated from previously disease detected patients opened up a new aspect of medical progression. In this paper, the capability of the classification of Naïve Bayes, Random Forest, Logistic Regression, Multilayer Perceptron, K-nearest neighbors in evaluating the Breast Cancer Disease dataset culled from UCI machine learning repository, was observed to predict the existence of Breast cancer. Data set has been explored in terms of Kappa Statistics, TP rate, FP Rate and precision.