Dataset Information

Bias Due to Confounders for the Exposure-Competing Risk Relationship.

ABSTRACT: Epidemiologic studies that aim to estimate a causal effect of an exposure on a particular event of interest may be complicated by the existence of competing events that preclude the occurrence of the primary event. Recently, many articles have been published in the epidemiologic literature demonstrating the need for appropriate models to accommodate competing risks when they are present. However, there has been little attention to variable selection for confounder control in competing risk analyses.We employ simulation to demonstrate the bias in two variable selection strategies include covariates that are associated with the exposure and (1) which change the cause-specific hazard of any of the outcomes; or (2) which change the cause-specific hazard of the specific event of interest.We demonstrated minimal to no bias in estimators adjusted for confounders of exposure and either the event of interest or the competing event, but bias of varying magnitude in almost all estimators adjusted only for confounders of exposure and the primary outcome.When estimating causal effects for which there are competing risks, the analysis should control for confounders of both the exposure-primary outcome effect and of the exposure-competing outcome effect.

SUBMITTER: Lesko CR

PROVIDER: S-EPMC5489237 | biostudies-literature | 2017 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Bias Due to Confounders for the Exposure-Competing Risk Relationship.

Lesko Catherine R CR Lau Bryan B

Epidemiology (Cambridge, Mass.) 20170101 1

<h4>Background</h4>Epidemiologic studies that aim to estimate a causal effect of an exposure on a particular event of interest may be complicated by the existence of competing events that preclude the occurrence of the primary event. Recently, many articles have been published in the epidemiologic literature demonstrating the need for appropriate models to accommodate competing risks when they are present. However, there has been little attention to variable selection for confounder control in c ...[more]

PMID: 27748680

Similar Datasets

Project description:PurposeIn studies of effects of time-varying drug exposures, adequate adjustment for time-varying covariates is often necessary to properly control for confounding. However, the granularity of the available covariate data may not be sufficiently fine, for example when covariates are measured for participants only when their exposure levels change.MethodsTo illustrate the impact of choices regarding the frequency of measuring time-varying covariates, we simulated data for a large target trial and for large observational studies, varying in covariate measurement design. Covariates were measured never, on a fixed-interval basis, or each time the exposure level switched. For the analysis, it was assumed that covariates remain constant in periods of no measurement. Cumulative survival probabilities for continuous exposure and non-exposure were estimated using inverse probability weighting to adjust for time-varying confounding, with special emphasis on the difference between 5-year event risks.ResultsWith monthly covariate measurements, estimates based on observational data coincided with trial-based estimates, with 5-year risk differences being zero. Without measurement of baseline or post-baseline covariates, this risk difference was estimated to be 49% based on the available observational data. With measurements on a fixed-interval basis only, 5-year risk differences deviated from the null, to 29% for 6-monthly measurements, and with magnitude increasing up to 35% as the interval length increased. Risk difference estimates diverged from the null to as low as -18% when covariates were measured depending on exposure level switching.ConclusionOur simulations highlight the need for careful consideration of time-varying covariates in designing studies on time-varying exposures. We caution against implementing designs with long intervals between measurements. The maximum length required will depend on the rates at which treatments and covariates change, with higher rates requiring shorter measurement intervals.

Project description:BackgroundElevated cardiovascular disease risk has been reported with proximity to highways or busy roadways, but proximity measures can be challenging to interpret given potential confounders and exposure error.MethodsWe conducted a cross sectional analysis of plasma levels of C-Reactive Protein (hsCRP), Interleukin-6 (IL-6), Tumor Necrosis Factor alpha receptor II (TNF-RII) and fibrinogen with distance of residence to a highway in and around Boston, Massachusetts. Distance was assigned using ortho-photo corrected parcel matching, as well as less precise approaches such as simple parcel matching and geocoding addresses to street networks. We used a combined random and convenience sample of 260 adults >40 years old. We screened a large number of individual-level variables including some infrequently collected for assessment of highway proximity, and included a subset in our final regression models. We monitored ultrafine particle (UFP) levels in the study areas to help interpret proximity measures.ResultsUsing the orthophoto corrected geocoding, in a fully adjusted model, hsCRP and IL-6 differed by distance category relative to urban background: 43% (-16%,141%) and 49% (6%,110%) increase for 0-50 m; 7% (-39%,45%) and 41% (6%,86%) for 50-150 m; 54% (-2%,142%) and 18% (-11%,57%) for 150-250 m, and 49% (-4%, 131%) and 42% (6%, 89%) for 250-450 m. There was little evidence for association for TNF-RII or fibrinogen. Ortho-photo corrected geocoding resulted in stronger associations than traditional methods which introduced differential misclassification. Restricted analysis found the effect of proximity on biomarkers was mostly downwind from the highway or upwind where there was considerable local street traffic, consistent with patterns of monitored UFP levels.ConclusionWe found associations between highway proximity and both hsCRP and IL-6, with non-monotonic patterns explained partly by individual-level factors and differences between proximity and UFP concentrations. Our analyses emphasize the importance of controlling for the risk of differential exposure misclassification from geocoding error.

Dataset Information

Bias Due to Confounders for the Exposure-Competing Risk Relationship.

Publications

Bias Due to Confounders for the Exposure-Competing Risk Relationship.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets