Document Type : Original Article
Authors
- Amir Hossein Hashemian 1
- Behrouz Beiranvand 2
- Mansour Rezaei 3
- Abdolrasoul Bardideh 4
- Eghbal Zand-Karimi 2
1 Research Center for Environmental Determinants of Health (RCEDH), Kermanshah University of Medical Sciences, Kermanshah, Iran
2 MSc Student of Biostatics, Department of Biostatistics and Epidemiology, Kermanshah University of Medical Sciences, School of Public Health, Kermanshah, Iran
3 Assistant Professor, Department of Biostatistics and Epidemiology, Kermanshah University of Medical Sciences, School of Public Health, Kermanshah, Iran
4 Assistant Professor, Department of Kidney Transplantation, Kermanshah University of Medical Sciences, Kermanshah, Iran
Abstract
Cox regression model serves as a statistical method for analyzing the survival data, which requires some options such as hazard proportionality. In recent decades, artificial neural network model has been increasingly applied to predict survival data. This research was conducted to compare Cox regression and artificial neural network models in prediction of kidney transplant survival. The present multi-center retrospective study was conducted on the medical records of 756 kidney transplant recipients undergoing kidney operations at two treatment centers from 2001 through 2012. The data was randomly divided into two educational and experimental (validation) groups. Then, Kaplan-Meier, Cox proportional hazard, and three-layer artificial neural network models were used for analyzing the data. To compare the prediction of both models, the area under the curve in the characteristic function was applied. Post-operative creatinine and relative family are among the factors of influencing kidney transplant survival. Moreover, the survival estimates of the transplanted kidney for periods of six months, one year, three years, and five years were 89, 87.4, 80, and 75 percent, respectively. ROC areas under the curve, for multi-layer perceptron neural network model and Cox regression, were 81.3% and 71%, respectively.If a structure with high prediction ability is obtained in neural network, we may detect risk patients through the method and consider more treatment resources for them
Keywords
Main Subjects
BAKR, M. A. & GHONEIM, M. A. 2005. Living donor renal transplantation, 1976 - 2003: the mansoura experience. Saudi J Kidney Dis Transpl, 16, 573-83.
BIGLARIAN, A., HAJIZADEH, E. & KAZEMNEJAD, A. 2010. Comparison of artificial neural network and Cox regression models in survival prediction of gastric cancer patients. Koomesh, 11, Pe215-Pe220, En31.
COURTNEY, A. E., MCNAMEE, P. T. & MAXWELL, A. P. 2008. The evolution of renal transplantation in clinical practice: for better, for worse? QJM, 101, 967-78.
EL-HUSSEINI, A. A., FODA, M. A., SHOKEIR, A. A., SHEHAB EL-DIN, A. B., SOBH, M. A. & GHONEIM, M. A. 2005. Determinants of graft survival in pediatric and adolescent live donor kidney transplant recipients: a single center experience. Pediatr Transplant, 9, 763-9.
HASSANZADE , J., SALAHI , H., RAJAEEFARD , A., ZEIGHAMI , B. & ALMASI HASHIANI , A. 2011. 10-year Graft Survival Analysis of Renal Transplantation and Factors Affecting it in Patients Transplanted from Live Donor in Shiraz Transplant Research Center during 1999-2009. Journal of Kerman University of Medical Sciences, 18(1), 28-39.
KUTNER, M. H., NACHTSHEIM, C. & NETER, J. 2004. Applied linear regression models.
MAHDAVI-MAZDEH, M., HEIDARY ROUCHI, A., NOROUZI, S., AGHIGHI, M., RAJOLANI, H. & AHRABI, S. 2007. Renal replacement therapy in Iran. Urol J, 4, 66-70.
MEIER-KRIESCHE, H. U., PORT, F. K., OJO, A. O., RUDICH, S. M., HANSON, J. A., CIBRIK, D. M., LEICHTMAN, A. B. & KAPLAN, B. 2000. Effect of waiting time on renal transplant outcome. Kidney Int, 58, 1311-7.
QUCHANI, S. & TAHAMI, E. Comparison of MLP and Elman Neural Network for Blood Glucose Level Prediction in Type 1 Diabetics. 3rd Kuala Lumpur International Conference on Biomedical Engineering 2006, 2007. Springer, 54-58.
REZAEI, M., KAZEMNEZHAD, A. & RAESI, D. 2002. Survival of kidney transplant patients in Kermanshah. Journal Behbood, 24, 27-41.
SANTORI, G., FONTANA, I. & VALENTE, U. Application of an artificial neural network model to predict delayed decrease of serum creatinine in pediatric patients after kidney transplantation.
Transplantation proceedings, 2007. Elsevier, 1813-1819.
SHRESTHA, B. M. & HAYLOR, J. L. 2007. Factors influencing long-term outcomes following renal transplantation: a review. JNMA J Nepal Med Assoc, 46, 136-42.
TAN, S. Y., CHEN, T. P., LEE, S. H., TAN, P. S., CHUA, C. T., TEO, S. M., THIRUVENTHIRAN, T., WO, M., LOH, C. S., HASSAN, A., TAN, J. C. & KOH, S. N. 2000. Cadaveric renal transplantation at University Hospital Kuala Lumpur: a preliminary report. Transplant Proc, 32, 1811-2.
WARNER, B. & MISRA, M. 1996. Understanding neural networks as statistical tools. The American Statistician, 50, 284-293.
)