Estimation of treatment effect in presence of noncompliance with early or late switching: a simulation study

Abstract

To assess the effect of treatment in survival studies, a randomized controlled trial (RCTs) is usually designed. Due to disease progression or other safety reasons, patients in the standard group may be allowed to switch to the experimental treatment. In such cases, estimation of the treatment effect is inevitably performed using naive methods such as intention-to-treat (ITT), per-protocol (PP), or more advanced methods such as the rank-preserving structural failure time (RPSFT) models or iterative parameter estimation (IPE). In some trials, people who progress early might be more likely to switch, and in other trials, people who progress late might be more likely to switch – depending on the characteristics of the disease and the drug being examined. So, this study simulated a new range of realistic scenarios with regard to patients’ prognosis and investigated the performance of the adjusted methods in the early and late switching with respect to the median of the survival time.

Keywords:

• Early and late switching
• IPE
• Noncompliance
• RPSFT
• Survival
• Treatment effect

MATHEMATICAL SUBJECT CLASSIFICATION:

• 62N02

Acknowledgments

Many thanks go to the Vice-Chancellor of Research and Technology, Hamadan University of Medical Sciences for the approval and support of this project (project number 9711237184 with Ethics Committee ID of IR.UMSHA.REC.1397.835). Also, we would like to thanks Dr. Andisheh Bakhshi and Dr. Ayoub Dabiri for reading, editing, and commenting on our manuscript.

Disclosure statement

No conflict of interest is declared for authors M.S., H.M., and G.H.R. The opinions expressed in this article are those of the author H.E. and do not reflect the views of Staburo GmbH, Munich.

Funding

This study was conducted as part of Ph.D. thesis of the first author and it was supported by Hamadan University of Medical Sciences.