Dataset Information

Comparison of statistical approaches dealing with time-dependent confounding in drug effectiveness studies.

ABSTRACT: In longitudinal studies, if the time-dependent covariates are affected by the past treatment, time-dependent confounding may be present. For a time-to-event response, marginal structural Cox models are frequently used to deal with such confounding. To avoid some of the problems of fitting marginal structural Cox model, the sequential Cox approach has been suggested as an alternative. Although the estimation mechanisms are different, both approaches claim to estimate the causal effect of treatment by appropriately adjusting for time-dependent confounding. We carry out simulation studies to assess the suitability of the sequential Cox approach for analyzing time-to-event data in the presence of a time-dependent covariate that may or may not be a time-dependent confounder. Results from these simulations revealed that the sequential Cox approach is not as effective as marginal structural Cox model in addressing the time-dependent confounding. The sequential Cox approach was also found to be inadequate in the presence of a time-dependent covariate. We propose a modified version of the sequential Cox approach that correctly estimates the treatment effect in both of the above scenarios. All approaches are applied to investigate the impact of beta-interferon treatment in delaying disability progression in the British Columbia Multiple Sclerosis cohort (1995-2008).

SUBMITTER: Karim ME

PROVIDER: S-EPMC5770217 | biostudies-literature | 2018 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Comparison of statistical approaches dealing with time-dependent confounding in drug effectiveness studies.

Karim Mohammad Ehsanul ME Petkau John J Gustafson Paul P Platt Robert W RW Tremlett Helen H

Statistical methods in medical research 20160921 6

In longitudinal studies, if the time-dependent covariates are affected by the past treatment, time-dependent confounding may be present. For a time-to-event response, marginal structural Cox models are frequently used to deal with such confounding. To avoid some of the problems of fitting marginal structural Cox model, the sequential Cox approach has been suggested as an alternative. Although the estimation mechanisms are different, both approaches claim to estimate the causal effect of treatmen ...[more]

PMID: 27659168

Similar Datasets

Project description:Using observational data to assess the relative effectiveness of alternative cancer treatments is limited by patient selection into treatment, which often biases interpretation of outcomes. We evaluated methods for addressing confounding in treatment and survival of patients with early-stage prostate cancer in observational data and compared findings with those from a benchmark randomized clinical trial.We selected 14?302 early-stage prostate cancer patients who were aged 66-74 years and had been treated with radical prostatectomy or conservative management from linked Surveillance, Epidemiology, and End Results-Medicare data from January 1, 1995, through December 31, 2003. Eligibility criteria were similar to those from a clinical trial used to benchmark our analyses. Survival was measured through December 31, 2007, by use of Cox proportional hazards models. We compared results from the benchmark trial with results from models with observational data by use of traditional multivariable survival analysis, propensity score adjustment, and instrumental variable analysis.Prostate cancer patients receiving conservative management were more likely to be older, nonwhite, and single and to have more advanced disease than patients receiving radical prostatectomy. In a multivariable survival analysis, conservative management was associated with greater risk of prostate cancer-specific mortality (hazard ratio [HR] = 1.59, 95% confidence interval [CI] = 1.27 to 2.00) and all-cause mortality (HR = 1.47, 95% CI = 1.35 to 1.59) than radical prostatectomy. Propensity score adjustments resulted in similar patient characteristics across treatment groups, although survival results were similar to traditional multivariable survival analyses. Results for the same comparison from the instrumental variable approach, which theoretically equalizes both observed and unobserved patient characteristics across treatment groups, differed from the traditional multivariable and propensity score results but were consistent with findings from the subset of elderly patient with early-stage disease in the trial (ie, conservative management vs radical prostatectomy: for prostate cancer-specific mortality, HR = 0.73, 95% CI = 0.08 to 6.73; for all-cause mortality, HR = 1.09, 95% CI = 0.46 to 2.59).Instrumental variable analysis may be a useful technique in comparative effectiveness studies of cancer treatments if an acceptable instrument can be identified.

Project description:We present a simple, one-dimensional model of an atom exposed to a time-dependent intense, short-pulse EM field with the objective of teaching undergraduates how to apply various numerical methods to study the behavior of this system as it evolves in time using several time propagation schemes.In this model, the exact Coulomb potential is replaced by a soft-core interaction to avoid the singularity at the origin. While the model has some drawbacks, it has been shown to be a reasonable representation of what occurs in the fully three-dimensional hydrogen atom.The model can be used as a tool to train undergraduate physics majors in the art of computation and software development.Program summaryProgram Title:: 1d hydrogen light interactionProgram Files doi:: http://dx.doi.org/10.17632/2275fmvdzc.1Code Ocean Capsule:: https://doi.org/10.24433/CO.1476487.v1Licensing provisions:: MIT licenseProgramming language:: FORTRAN90Nature of problem:: The one dimensional time dependent Schrödinger equation has been shown to be quite useful as a model to study the Hydrogen atom exposed to an intense, short pulse, electromagnetic field. We use a model potential that is cut-off near x = 0 and avoids the singularity of the true 1-D potential, but retains the characteristic Rydberg series and continuum to study excitation and ionization of the true H atom. The code employs a number of numerical methods to understand and compare the efficacy and accuracy when applied to this model problem.Solution method:: The program uses and contrasts a number of approaches; the Crank-Nicolson, Short Iterative Lanczos, various incarnations of the split-operator and the Chebychev method have been programmed. These methods have been compared using a 3-point finite difference (FD) discretization of the space coordinate. For completeness, some attention has also been given to using 5-9 FD formulas in order to show how higher order discretization affects the accuracy and efficiency of the methods but the primary focus of the method is the time propagation.Additional comments including restrictions and unusual features:: The main purpose of this code is as a teaching tool for undergraduates interested in acquiring knowledge of numerical methods and programming skills useful to a practicing computational physicist.

Dataset Information

Comparison of statistical approaches dealing with time-dependent confounding in drug effectiveness studies.

Publications

Comparison of statistical approaches dealing with time-dependent confounding in drug effectiveness studies.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure