Prediction of the axillary lymph node status in breast cancer using artificial neural network and logistic regression analysis methods

Today one of the prevalent cancer types we come across in women is breast cancer. Classification and staging of axillary lymph nodes are most important points in diagnose and treatment of breast cancers. Prognosis for these lymph nodes can only be clearified by surgical operation which it self has serious side effects. In this study aimed patients with breast cancer can easily follow up recent statues of axillary lymph nodes and information about whether cancer spread beyond breast or not with checking out clinic, pathological data results easily in any hospital by artificial neural network. Clinic and pathologic data of 270 breast cancer patients applied to Ankara Numune Educational and Research Hospital, Ankara Oncology Educational and Research Hospital are tested and classified according to back propagation multilayer perceptron, and logistic regression. For testing artificial neural network performance, Regression and ROC (Receiver Operating Characteristics) statistical analysis system used to find out specificity, sensitivity, and accuracy of this test.