Comparative study of logistic regression and artificial neural networks on predicting breast cancer cytology

<p>Currently, breast cancer is one of the most common cancers and a main reason women death worldwide particularly in<strong> </strong>developing countries such as Iraq. our work aims to predict type tumor whether benign or malignant through models that were built using logistic regression neural networks we hope it will help doctors in detecting tumor. Four set binary two different types artificial namely multilayer perceptron MLP radial basis function RBF. Evaluation validated trained was done several performance metrics like accuracy, sensitivity, specificity, AUC (area under receiver operating characteristic ROC). Dataset downloaded from UCI ml repository; composed 9 attributes 699 samples. The findings are clearly showing RBF NN classifier best prediction tumors since had recorded highest terms correct classification rate (accuracy), Receiver Operating Characteristic ROC) among all other models.</p>