Author/Authors :
Pourhoseingholi، Mohamad Amin نويسنده Research Center for Gastroenterology and Liver Disease, Shahid Beheshti University of Medical Sciences, Tehran, Iran , , Pourhoseingholi ، A نويسنده 1. Research Center for Gastroenterology and Liver Disease, Shahid Beheshti University of Medical Sciences, Tehran, Iran , , Vahedi ، M نويسنده 1. Research Center for Gastroenterology and Liver Disease, Shahid Beheshti University of Medical Sciences, Tehran, Iran , , Moghimi Dehkordi ، B نويسنده 1. Research Center for Gastroenterology and Liver Disease, Shahid Beheshti University of Medical Sciences, Tehran, Iran , , Safaee ، A نويسنده 1. Research Center for Gastroenterology and Liver Disease, Shahid Beheshti University of Medical Sciences, Tehran, Iran , , Ashtari ، S نويسنده . Research Center for Gastroenterology and Liver Disease, Shahid Beheshti University of Medical Sciences, Tehran, Iran , , Zali، MR نويسنده ,
Abstract :
Background: Although Cox proportional hazard regression is the most popular model to analysis the prognostic factors on survival of cancer patients, under certain circumstances, parametric models estimate the parameter more efficient than Cox. The objective of this study was to compare Cox regression and parametric models in patients with gastric cancer who registered at Taleghani hospital, Tehran, Iran.
Methods: In a retrospective cohort study the 746 patients with gastric cancer studied from February 2003 through January 2007. Gender, age at diagnosis, distant metastasis, extent of wall penetration, tumor size, histology type, tumor grade, lymph node metastasis and Pathologic stage were selected as prognosis and entered to the models. Lognormal, Exponential, Gompertz, Weibull, Log-logistic and Gamma regression were performed as parametric models and Akaike Information Criterion (AIC) was used to compare the efficiency of models.
Results: Based on AIC, Log logistic is the efficient model. Log logistic analysis indicated that wall penetration and presence of pathologic distant metastasis as potential risk of death in full and final model analysis.
Conclusion: In multivariate analysis all parametric models fit better than Cox with respect to AIC and the log logistic regression among them was the best one. So when the proportional hazard assumption dose not holds, these modes would be the alternative and lead to acceptable conclusions.
