Predicting the severity of breast masses using Bayesian networks

Mammography is the most effective and available tool for breast cancer screening. However, the low positive predictive value of breast biopsy resulting from mammogram interpretation leads to approximately 70% unnecessary biopsies with benign outcomes. Data mining algorithms could be used to help physicians in their decisions to perform a breast biopsy on a suspicious lesion seen in a mammogram image or to perform a short term follow-up examination instead. This study evaluates two Bayesian network classifiers; tree augmented Naïve Bayes and the Markov blanket estimation on the prediction of the severity of breast masses. Bayesian networks are selected as they are able to produce probability estimates rather than predictions. These estimates allow predictions to be ranked, and their expected costs to be minimized. The prediction accuracies of Bayesian networks are benchmarked against the multilayer perceptron neural network. The experimental results show that Bayesian networks are competitive techniques for prediction of the severity of breast masses.