Bayesian sequential monitoring design for two-arm randomized clinical trials with noncompliance

Stat Med. 2015 Jun 15;34(13):2104-15. doi: 10.1002/sim.6474. Epub 2015 Mar 10.

Abstract

In early-phase clinical trials, interim monitoring is commonly conducted based on the estimated intent-to-treat effect, which is subject to bias in the presence of noncompliance. To address this issue, we propose a Bayesian sequential monitoring trial design based on the estimation of the causal effect using a principal stratification approach. The proposed design simultaneously considers efficacy and toxicity outcomes and utilizes covariates to predict a patient's potential compliance behavior and identify the causal effects. Based on accumulating data, we continuously update the posterior estimates of the causal treatment effects and adaptively make the go/no-go decision for the trial. Numerical results show that the proposed method has desirable operating characteristics and addresses the issue of noncompliance.

Keywords: Bayesian design; causal effect; continuous monitoring; noncompliance; principal stratification.

Publication types

  • Research Support, N.I.H., Extramural

MeSH terms

  • Bayes Theorem
  • Bias
  • Computer Simulation
  • Early Termination of Clinical Trials / standards
  • Early Termination of Clinical Trials / statistics & numerical data
  • Endpoint Determination
  • Humans
  • Patient Compliance*
  • Randomized Controlled Trials as Topic / standards*
  • Randomized Controlled Trials as Topic / statistics & numerical data
  • Research Design*
  • Smoking Cessation / methods
  • Smoking Cessation / statistics & numerical data
  • Tobacco Use Cessation Devices / adverse effects
  • Tobacco Use Cessation Devices / standards
  • Tobacco Use Cessation Devices / statistics & numerical data