Methodology for analyzing censored correlated data: application of marginal and frailty approaches in human genetics

Background: Statistical analysis for correlated censored data allows to stu dy censored events in clustered structure designs. Considering a possible c orrelation among failure times of the same group, standard methodology is n o longer applicable, We investigated proposed models in this context to stu dy familial data about a genetic disease, Alport syndrome. Alport syndrome is a severe hereditary disease due to abnormal collagenous chains. Renal fa ilure is the main symptom of the disease. It progresses reward end-stage re nal failure (IRT) according to a high time variability As shown by genetic studies, mutations of COL4A5 gene are involved in the X-linked Alport Syndr ome. Due to the large range of the mutation types, the aim of this study wa s to search for a possible genetic origin of the heterogeneity of the disea se severity. Methods: Marginal survival models and mixed effects survival models (so-cal led frailty models) were proposed to take into account the possible non ind ependence of the observations. In this study, time until end-stage renal fa ilure is a rightly censored end point. Possible intra-familial correlations due to shared environmental and/or genetic factors could induce dependence among familial failure times, In this paper, we fit marginal and frailty p roportional hazards models to evaluate the effect of mutation type on the r isk of IRT and an interfamilial heterogeneity of failure times. Results: In this study, the use of these models allows to show the presence of an interfamilial heterogeneity, of the failure times to IRT. Moreover t he results suggest that some mutation types are linked to a higher risk of fast evolution to IRT, which explains partially the interfamilial heterogen eity of the failure times. Conclusions: This paper shows the interest of marginal and frailty models t o evaluate the heterogeneity of censored responses and to study relationshi ps between a censored criterion and covariables, This study puts forward th e importance of characterizing the mutation at a molecular level to underst and the relationship between genotype and phenotype.