부산대학교 도서관

Breast cancer survival prediction can havean extreme effect on selection of best treatment protocols. Many approaches such as statistical or machine learning models have been employed to predictthe survival prospects of patients, but newer algorithms such as deep learning can be tested with theaim of improving the models and prediction accuracy. In this study, we used machine learning and deeplearning approaches to predict breast cancer survival in 4,902 patient records from the University ofMalaya Medical Centre Breast Cancer Registry. Theresults indicated that the multilayer perceptron (MLP),random forest (RF) and decision tree (DT) classifierscould predict survivorship, respectively, with 88.2 %,83.3 % and 82.5 % accuracy in the tested samples.Support vector machine (SVM) came out to be lowerwith 80.5 %. In this study, tumour size turned out tobe the most important feature for breast cancer survivability prediction. Both deep learning and machine learning methods produce desirable predictionaccuracy, but other factors such as parameter configurations and data transformations affect the accuracy of the predictive model.