Breast cancer  is  one  of  the  most  common  cancers,  and  also  it  is the  most  common type of malignancy in Iranian women that has been growing in recent years. In patients with this disease, there is usually the risk of recurrence. Many factors increase or decrease the risk of recurrence.  A  variety  of  models  that  can  be noted to  detect  and predict breast cancer recurrence and factors affecting it, classical statistical methods such as Cox  Regression and new  methods  such  as Artificial Neural Network  and Random Forest. In  this  study,  using these  three  techniques, recurrence  of  breast  cancer was predicted and  factors  affecting  relapse were detected.  Models and prediction Accuracy are compared using ROC curve. In this retrospective study, also called historic cohort study, 342 patients with breast cancer with 13 features from each patient were used. 

Data of patients in the Cancer Research Center of Shohada  Tajrish  hospital, have been recorded to track, and patients for at least 6 months after diagnosis were being monitored and follow-up was done for them.  To  develop  predictive  models  of breast  cancer  recurrence  and determination  of factors  affecting  recurrence, the  three-layer  Perceptron  Artificial Neural Network algorithms, Random Forest  classification  and  Cox Regression  models were fitted. Area  under  the  ROC  for  the  Artificial Neural Network, Random Forest and  Cox Regression obtained  87%,  76%  and  65%, respectively. Artificial Neural Network model classification accuracy is obtained 80%, against 60% for random forest model and 33% for cox regression model. So, ANN model predicted better than the two other models.