Exploring causality mechanism in the joint analysis of longitudinal and survival data

Liu, Lei; Zheng, Cheng; Kang, Joseph

doi:10.1002/sim.7838

Cited by 13 publications

(18 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Application of the proposed joint model approach in longitudinal studies of disease progression, such as in the DCCT Genetics Study, improves classification of direct and/or indirect SNP association which can help to elucidate the genetic architecture of complex traits. In the context of mediation analysis, Liu et al 47 discussed various formulations and interpretations of joint models, with shared-random-effects accounting for potential unmeasured baseline confounding factors between one longitudinal and one time-to-event traits. Using applications in datasets from two clinical trials, they illustrate interpretation of sensitivity analysis to unmeasured baseline confounders.…”

Section: Discussionmentioning

confidence: 99%

Characterization of direct and/or indirect genetic associations for multiple traits in longitudinal studies of disease progression

Brossard

Paterson

Espin‐Garcia

et al. 2021

Preprint

View full text Add to dashboard Cite

When quantitative longitudinal traits are risk factors for disease progression, endogenous, and/or subject to random errors, joint model specification of multiple time-to-event and multiple longitudinal traits can effectively identify direct and/or indirect genetic association of single nucleotide polymorphisms (SNPs) with time-to-event traits. Here, we present a joint model that integrates: i) a linear mixed model describing the trajectory of each longitudinal trait as a function of time, SNP effects and subject-specific random effects, and ii) a frailty Cox survival model that depends on SNPs, longitudinal trajectory effects, and a subject-specific frailty term accounting for unexplained dependency between time-to-event traits. Inference is based on a two-stage approach with bootstrap joint covariance estimation. We develop a hypothesis testing procedure to identify direct and/or indirect SNP association with each time-to-event trait. Motivated by complex genetic architecture of type 1 diabetes complications (T1DC) observed in the Diabetes Control and Complications Trial (DCCT), we show by realistic simulation study that joint modelling of two time-to-T1DC (retinopathy, nephropathy) and two longitudinal risk factors (HbA1c, systolic blood pressure) reduces bias and improves identification of direct and/or indirect SNP associations, compared to alternative methods ignoring measurement errors in intermediate risk factors. Through analysis of DCCT, we identify two SNPs with indirect associations with multiple time-to-T1DC traits and obtain similar conclusions using alternative formulations of time-dependent HbA1c effects on T1DC. In total, joint analysis of multiple longitudinal and multiple time-to-event traits provides insight into etiology of complex traits.

show abstract

Section: Discussionmentioning

confidence: 99%

Characterization of direct and/or indirect genetic associations for multiple traits in longitudinal studies of disease progression

Brossard

Paterson

Espin‐Garcia

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Simplified directed acyclic graph depicting a joint model for a longitudinal outcome and its observation process A simplified DAG that illustrates how the joint model accounts for the correlation between a longitudinal outcome Y and its observation process R is included as Figure 1 (Liu, Zheng, & Kang, 2018); X represents covariates included in the model, and U represents the shared random effects. After adjusting for all covariates (e.g., confounders) X, the longitudinal outcome and the observation process are associated only through the shared U.…”

Section: Figurementioning

confidence: 99%

“…A simplified DAG that illustrates how the joint model accounts for the correlation between a longitudinal outcome Y and its observation process R is included as Figure 1 (Liu, Zheng, & Kang, 2018); X represents covariates included in the model, and U represents the shared random effects. After adjusting for all covariates (e.g., confounders) X, the longitudinal outcome and the observation process are associated only through the shared U.…”

Section: Figure 1 Simplified Directed Acyclic Graph Depicting a Joint...mentioning

confidence: 99%

Mixed‐effects models for health care longitudinal data with an informative visiting process: A Monte Carlo simulation study

Gasparini

Abrams

Barrett

et al. 2019

Statistica Neerlandica

View full text Add to dashboard Cite

Electronic health records are being increasingly used in medical research to answer more relevant and detailed clinical questions; however, they pose new and significant methodological challenges. For instance, observation times are likely correlated with the underlying disease severity: Patients with worse conditions utilise health care more and may have worse biomarker values recorded. Traditional methods for analysing longitudinal data assume independence between observation times and disease severity; yet, with health care data, such assumptions unlikely hold. Through Monte Carlo simulation, we compare different analytical approaches proposed to account for an informative visiting process to assess whether they lead to unbiased results. Furthermore, we formalise a joint model for the observation process and the longitudinal outcome within an extended joint modelling framework. We illustrate our results using data from a pragmatic trial on enhanced care for individuals with chronic kidney disease, and we introduce user‐friendly software that can be used to fit the joint model for the observation process and a longitudinal outcome.

show abstract

“…In further recent work, Albert et al consider arbitrary groups of possibly inter‐related mediators sequential in time, although they prefer particular types of contrasts in estimation (eg, transitions from low to high socio‐economic status) to overcome problems with the identifiability of causal effects. Several other papers have sought to extend these methods for longitudinal mediation analysis to incorporate time‐to‐event in a survival setting …”

Section: Introductionmentioning

confidence: 99%

“…Several other papers have sought to extend these methods for longitudinal mediation analysis to incorporate time-to-event in a survival setting. [25][26][27][28][29][30][31][32][33] The structure of this paper is as follows. In Section 2, we provide a motivating example from our work in dental epidemiology.…”

Section: Introductionmentioning

confidence: 99%

Effect decomposition through multiple causally nonordered mediators in the presence of exposure‐induced mediator‐outcome confounding

Mittinty

Lynch

Forbes

et al. 2019

Statistics in Medicine

View full text Add to dashboard Cite

Avin et al (2005) showed that, in the presence of exposure‐induced mediator‐outcome confounding, decomposing the total causal effect (TCE) using standard conditional exchangeability assumptions is not possible even under a nonparametric structural equation model with all confounders observed. Subsequent research has investigated the assumptions required for such a decomposition to be identifiable and estimable from observed data. One approach was proposed by VanderWeele et al (2014). They decomposed the TCE under three different scenarios: (1) treating the mediator and the exposure‐induced confounder as joint mediators; (2) generating path‐specific effects albeit without distinguishing between multiple distinct paths through the exposure‐induced confounder; and (3) using so‐called randomised interventional analogues where sampling values from the distribution of the mediator within the levels of the exposure effectively marginalises over the exposure‐induced confounder. In this paper, we extend their approach to the case where there are multiple mediators that do not influence each other directly but which are all influenced by an exposure‐induced mediator‐outcome confounder. We provide a motivating example and results from a simulation study based on from our work in dental epidemiology featuring the 1982 Pelotas Birth Cohort in Brazil.

show abstract

Exploring causality mechanism in the joint analysis of longitudinal and survival data

Cited by 13 publications

References 52 publications

Characterization of direct and/or indirect genetic associations for multiple traits in longitudinal studies of disease progression

Characterization of direct and/or indirect genetic associations for multiple traits in longitudinal studies of disease progression

Mixed‐effects models for health care longitudinal data with an informative visiting process: A Monte Carlo simulation study

Effect decomposition through multiple causally nonordered mediators in the presence of exposure‐induced mediator‐outcome confounding

Contact Info

Product

Resources

About