Abstract
In observational cohorts, longitudinal data are collected with repeated measurements at predetermined time points for many biomarkers, along with other variables measured at baseline. In these cohorts, time until a certain event of interest occurs is reported and very often, a relationship will be observed between some biomarker repeatedly measured over time and that event. Joint models were designed to efficiently estimate statistical parameters describing this relationship by combining a mixed model for the longitudinal biomarker trajectory and a survival model for the time until occurrence of the event, using a set of random effects to account for the relationship between the two types of data. In this paper, we discuss the implementation of joint models in genetic association studies. First, we check model consistency based on different simulation scenarios, by varying sample sizes, minor allele frequencies and number of repeated measurements. Second, using genotypes assayed with the Metabochip DNA arrays (Illumina) from about 4,500 individuals recruited in the French cohort D.E.S.I.R. (Data from an Epidemiological Study on the Insulin Resistance syndrome), we assess the feasibility of implementing the joint modelling approach in a real high-throughput genomic dataset. An alternative model approximating the joint model, called the Two-Step approach (TS), is also presented. Although the joint model shows more precise and less biased estimators than its alternative counterpart, the TS approach results in much reduced computational times, and could thus be used for testing millions of SNPs at the genome-wide scale.
Highlights
With the increased availability of longitudinal and survival data in large cohorts, joint models have emerged as an appropriate approach to account for both types of data, especially when dealing with informative/non-informative dropouts which commonly occur in such cohorts
With the ever-increasing availability of genomic data generated by genotyping arrays and generation sequencing, the need to develop and implement efficient models is important to ensure that statistical analysis will be achieved in a reasonable timeframe
We proposed a comparison of two approaches, namely the joint model (JM) and the two-step model
Summary
With the increased availability of longitudinal and survival data in large cohorts, joint models have emerged as an appropriate approach to account for both types of data, especially when dealing with informative/non-informative dropouts which commonly occur in such cohorts. Main applications of the joint model approach are: (i) to efficiently model the survival process with a time-varying covariate, accounting for missing data and measurement error; and (ii) to account for informative dropouts in the longitudinal data. Unlike the CoxPH model, in which the time-varying covariate is assumed to be exogenous, i.e., not modified by the occurrence of an event (Kalbfleisch and Prentice, 2002), the joint modelling framework allows to account for an endogenous timevarying covariate. An example of an endogenous covariate is the fasting blood plasma glucose which is irremediably modified due to glucose lowering medication, once T2D is diagnosed
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
