Classification Models to Predict Survival of Kidney Transplant Recipients Using Two Intelligent Techniques of Data Mining and Logistic Regression
Kidney transplantation is the treatment of choice for end-stage renal disease. The aim of this study was to determine the ten-year graft survival rate of renal transplantation in patients who have been transplanted from live donors. This is a historical cohort study designed to determine the organ survival rate after kidney transplantation from live donor during a 10-year period (from March 1999 to March 2009) on 843 patients receiving kidney transplant in the transplantation center of Namazi hospital in Shiraz, Iran. Kaplan-Meier method was used to determine the survival rate, log-rank test was used to compare survival curves, and Cox proportional hazard model was used to multivariate analysis. Mean follow-up was 53.07 ± 34.61 months. Allograft survival rates at 1, 3, 5, 7, and 10 years were 98.3, 96.4, 92.5, 90.8, and 89.2%, respectively. Using Cox proportional hazard model, the age and gender of the donors along with the creatinine level of the patients at discharge were shown to have a significant influence on survival. The 10-year graft survival rate of renal transplantation from living donor in this center is 89.2%, and graft survival rate in our cohort is satisfactory and comparable with reports from large centers in the world.