Comparison between Parametric and Semi-parametric Cox Models in Modeling Transition Rates of a Multi-state Model: Application in Patients with Gastric Cancer Undergoing Surgery at the Iran Cancer Institute

Abstract

<b>Background:</b> Research on cancers with a high rate of mortality such as those occurring in the stomachrequires using models which can provide a closer examination of disease processes and provide researcherswith more accurate data. Various models have been designed based on this issue and the present study aimedat evaluating such models. Materials and <br/><b>Methods</b>: Data from 330 patients with gastric cancer undergoingsurgery at Iran Cancer Institute from 1995 to 1999 were analyzed. Cox-Snell Residuals and Akaike InformationCriterion were used to compare parametric and semi-parametric Cox models in modeling transition ratesamong different states of a multi-state model. R 2.15.1 software was used for all data analyses. <br/><b>Results</b>: Analysisof Cox-Snell Residuals and Akaike Information Criterion for all probable transitions among different statesrevealed that parametric models represented a better fitness. Log-logistic, Gompertz and Log-normal modelswere good choices for modeling transition rate for relapse hazard (state 1"state 2), death hazard without arelapse (state 1"state 3) and death hazard with a relapse (state 2"state 3), respectively. <br/><b>Conclusions</b>: Althoughthe semi-parametric Cox model is often used by most cancer researchers in modeling transition rates of multistatemodels, parametric models in similar situations- as they do not need proportional hazards assumptionand consider a specific statistical distribution for time to occurrence of next state in case this assumption is notmade - are more credible alternatives.