Kidney transplantation had been evaluated in some researches in our country mainly with a clinical approach. In this research we evaluated graft survival in kidney recipients and factors impacting on survival rates. Artificial neural networks have a good ability in modeling complex relationships, so we used this ability to demonstrate a model for prediction of 5yr graft survival after transplantation. This retrospective study was done on 316 kidney transplants from 1984 through 2006. Kaplan-meire method, Cox regression test, goodness of fit test and artificial neural networks were used in analysis. Body Mass Index (BMI) and type of transplantation (living/cadaver) had significant effects on graft survival. 1yr, 3yr and 5yr graft survival was 96%and 93% and 90% respectively. Suggested artificial neural network model had good accuracy (72%) and appropriate results in goodness of fit test. Sensitivity of model in identification of true positive situations was more than false negative situations (72% Vs 61%). Graft survival in living donors was more than cadaver donors. Graft survival decreased when the BMI increased at transplantation time. Artificial neural networks can be used in constructing models to prediction of graft survival in kidney transplantation.