The effect of covariate adjustment for baseline severity in acute stroke clinical trials with responder analysis outcomes
1 Department of Public Health Sciences, Medical University of South Carolina, 135 Cannon Street, Charleston, SC 29425, USA
2 Division of Emergency Medicine, Department of Medicine, Medical University of South Carolina, 169 Ashley Avenue, Charleston, SC 29425, USA
3 Department of Neurology, University of Virginia School of Medicine, 81 Hospital Drive, McKim Hall Room 2026, Charlottesville, VA 22908, USA
Trials 2013, 14:98 doi:10.1186/1745-6215-14-98Published: 11 April 2013
Traditionally in acute stroke clinical trials, the primary clinical outcome employed is a dichotomized modified Rankin Scale (mRS). New statistical methods, such as responder analysis, are being used in stroke studies to address the concern that baseline prognostic variables, such as stroke severity, impact the likelihood of a successful outcome. Responder analysis allows the definition of success to vary according to baseline prognostic variables, producing a more clinically relevant insight into the actual effect of investigational treatments. It is unclear whether or not statistical analyses should adjust for prognostic variables when responder analysis is used, as the outcome already takes these prognostic variables into account. This research aims to investigate the effect of covariate adjustment in the responder analysis framework in order to determine the appropriate analytic method.
Using a current stroke clinical trial and its pilot studies to guide simulation parameters, 1,000 clinical trials were simulated at varying sample sizes under several treatment effects to assess power and type I error. Covariate-adjusted and unadjusted logistic regressions were used to estimate the treatment effect under each scenario. In the case of covariate-adjusted logistic regression, the trichotomized National Institute of Health Stroke Scale (NIHSS) was used in adjustment.
Under various treatment effect settings, the operating characteristics of the unadjusted and adjusted analyses do not substantially differ. Power and type I error are preserved for both the unadjusted and adjusted analyses.
Our results suggest that, under the given treatment effect scenarios, the decision whether or not to adjust for baseline severity when using a responder analysis outcome should be guided by the needs of the study, as type I error rates and power do not appear to vary largely between the methods. These findings are applicable to stroke trials which use the mRS for the primary outcome, but also provide a broader insight into the analysis of binary outcomes that are defined based on baseline prognostic variables.
This research is part of the Stroke Hyperglycemia Insulin Network Effort (SHINE) trial, Identification Number NCT01369069.