Literature DB >> 18283074

Estimating effects from randomized trials with discontinuations: the need for intent-to-treat design and G-estimation.

Sander Greenland1, Stephan Lanes, Michele Jara.   

Abstract

BACKGROUND: Randomized trials provide pivotal evidence for evaluation and approval of therapies. Nonetheless, such trials are often plagued by noncompliance, especially in the form of premature discontinuation of treatment. While intent-to-treat (ITT) analysis can provide valid tests of no-effect hypotheses, some trials may make ITT analysis impossible by ceasing follow-up when patients go off assigned treatment. Furthermore, estimates based on ITT, on-treatment, or per-protocol comparisons can seriously understate harm or benefit.
PURPOSE: To show how g-estimation based on randomization status is a natural generalization of ITT null testing to estimating efficacy from trials with important discontinuation or noncompliance.
METHODS: We contrast with an analysis of the effect of a tiotropium inhaler on the occurrence of chronic obstructive pulmonary disease (COPD) events in a six-month double-blind placebo-controlled trial of 1829 patients with good but imperfect compliance.
RESULTS: The covariate-adjusted point estimates, 95% confidence limits (CL), and null P-values comparing expected COPD event times in placebo versus tiotropium patients were: ITT, 1.21, CL = 1.02, 1.43, P = 0.027; on-treatment, 1.27, CL = 1.06, 1.52, P = 0.009; per-protocol, 1.36, CL = 1.13, 1.63, P = 0.001; and g-estimation, 1.31, CL = 1.03,1.72, P = 0.027. Thus g-estimation preserved the ITT test of the null, but exhibited more uncertainty about the size of the tiotropium effect than the other methods. In particular, it allowed for a much larger potential effect than did ITT analysis, but produced a much larger null P than exhibited by per-protocol analysis. LIMITATIONS: Like ITT analysis, g-estimation requires all patients be followed to the end of the trial protocol, regardless of whether they comply with the protocol. Like on-treatment and per-protocol analyses, it also requires accurate compliance information be recorded.
CONCLUSION: G-estimation should become a standard procedure for the analysis of trials with noncompliance. Software to do so is available in major packages, and the procedure is easily coded for other packages.

Entities:  

Mesh:

Substances:

Year:  2008        PMID: 18283074     DOI: 10.1177/1740774507087703

Source DB:  PubMed          Journal:  Clin Trials        ISSN: 1740-7745            Impact factor:   2.486


  19 in total

1.  The Implications of Using Lagged and Baseline Exposure Terms in Longitudinal Causal and Regression Models.

Authors:  Mohammad Ali Mansournia; Ashley I Naimi; Sander Greenland
Journal:  Am J Epidemiol       Date:  2019-04-01       Impact factor: 4.897

2.  Estimating treatment effects with treatment switching via semicompeting risks models: an application to a colorectal cancer study.

Authors:  Donglin Zeng; Qingxia Chen; Ming-Hui Chen; Joseph G Ibrahim
Journal:  Biometrika       Date:  2011-12-29       Impact factor: 2.445

3.  Estimating absolute risks in the presence of nonadherence: an application to a follow-up study with baseline randomization.

Authors:  Sengwee Toh; Sonia Hernández-Díaz; Roger Logan; James M Robins; Miguel A Hernán
Journal:  Epidemiology       Date:  2010-07       Impact factor: 4.822

4.  Methods for adjusting for bias due to crossover in oncology trials.

Authors:  K Jack Ishak; Irina Proskorovsky; Beata Korytowsky; Rickard Sandin; Sandrine Faivre; Juan Valle
Journal:  Pharmacoeconomics       Date:  2014-06       Impact factor: 4.981

5.  Theoretical Basis of the Test-Negative Study Design for Assessment of Influenza Vaccine Effectiveness.

Authors:  Sheena G Sullivan; Eric J Tchetgen Tchetgen; Benjamin J Cowling
Journal:  Am J Epidemiol       Date:  2016-09-01       Impact factor: 4.897

6.  Generalizing evidence from randomized clinical trials to target populations: The ACTG 320 trial.

Authors:  Stephen R Cole; Elizabeth A Stuart
Journal:  Am J Epidemiol       Date:  2010-06-14       Impact factor: 4.897

7.  Using marginal structural measurement-error models to estimate the long-term effect of antiretroviral therapy on incident AIDS or death.

Authors:  Stephen R Cole; Lisa P Jacobson; Phyllis C Tien; Lawrence Kingsley; Joan S Chmiel; Kathryn Anastos
Journal:  Am J Epidemiol       Date:  2009-11-24       Impact factor: 4.897

8.  Effect of highly active antiretroviral therapy on incident AIDS using calendar period as an instrumental variable.

Authors:  Lauren E Cain; Stephen R Cole; Sander Greenland; Todd T Brown; Joan S Chmiel; Lawrence Kingsley; Roger Detels
Journal:  Am J Epidemiol       Date:  2009-03-24       Impact factor: 4.897

Review 9.  Nonadherence to treatment protocol in published randomised controlled trials: a review.

Authors:  Susanna Dodd; Ian R White; Paula Williamson
Journal:  Trials       Date:  2012-06-18       Impact factor: 2.279

10.  Gene-environment interaction testing in family-based association studies with phenotypically ascertained samples: a causal inference approach.

Authors:  David W Fardo; Jinze Liu; Dawn L Demeo; Edwin K Silverman; Stijn Vansteelandt
Journal:  Biostatistics       Date:  2011-11-13       Impact factor: 5.279

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.