Comparison of Artificial Neural Networks and Cox Regression Models in Prediction of Kidney Transplant Survival

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.

Authors and Affiliations

Amir Hossein Hashemian| Research Center for Environmental Determinants of Health (RCEDH), Kermanshah University of Medical Sciences, Kermanshah, Iran, Assistant Professor, Department of Biostatistics and Epidemiology, Kermanshah University of Medical Sciences, School of Public Health, Kermanshah, Iran, Behrouz Beiranvand| MSc Student of Biostatics, Department of Biostatistics and Epidemiology, Kermanshah University of Medical Sciences, School of Public Health, Kermanshah, Iran, E-mail: behroz.beiran@yahoo.com, Mansour Rezaei| Assistant Professor, Department of Biostatistics and Epidemiology, Kermanshah University of Medical Sciences, School of Public Health, Kermanshah, Iran, Abdolrasoul Bardideh| Assistant Professor, Department of Kidney Transplantation, Kermanshah University of Medical Sciences, Kermanshah, Iran, Eghbal Zand-Karimi| MSc Student of Biostatics, Department of Biostatistics and Epidemiology, Kermanshah University of Medical Sciences, School of Public Health, Kermanshah, Iran

Keywords

Related Articles

The Chemical Composition and Antimicrobial Activity of Essential Oils of Vaccinium Arctostaphylos L.

Objective: The growing resistance of different bacteria to antibiotic chemical drugs have become the global issue. This investigation is the first study of the antimicrobial activity of the essential oil of flowering a...

Estimation of Lactate Dehydrogenase Activity in cerebrospinal fluid in different types of meningitis

Objective: Meningitis is life-threatening condition and examination of the Cerebrospinal fluid (CSF) may not give a precise diagnosis and prognosis of different types of meningitis. Bacterial meningitis is still a very...

Identify factors that effecting on wood and papers student’s entrepreneurial spirit (case study: college of agricultural and natural resources of Tehran university)

The purpose of this study was to identify factors that effecting on wood and papers student’s entrepreneurial spirit. Statistical population of this research consisted of whole wood and paper students in college of ag...

Studying the effect of kidney internal structure on beta absorbed dose of radiopharmaceuticals Hg-203, Ho-166 and Y-90 using Monte Carlo

Large quantities of radiopharmaceuticals prescribed for treatment and diagnosis are excreted through kidney. Therefore, radiation unwanted dose is created in kidney. As a result, exact calculation of prescribed radioph...

Evaluation of Crategus sp. spatial pattern in the Central Zagros Forest

Spatial pattern of trees can possibly indicate stand history, population dynamics, and species competition. This research was investigated in the Chahartagh forest reserve, Ardal region, chaharmehal and Bakhtiari Provi...

Download PDF file
  • EP ID EP12907
  • DOI -
  • Views 381
  • Downloads 16

How To Cite

Amir Hossein Hashemian, Behrouz Beiranvand, Mansour Rezaei, Abdolrasoul Bardideh, Eghbal Zand-Karimi (2013). Comparison of Artificial Neural Networks and Cox Regression Models in Prediction of Kidney Transplant Survival. International journal of Advanced Biological and Biomedical Research, 1(10), 1204-1212. https://europub.co.uk/articles/-A-12907