Incorporating covariates information in adaptive clinical trials for precision medicine

Abstract

Precision medicine is the systematic use of information that pertains to an individual patient to select or optimize that patient's preventative and therapeutic care. Recent studies have classified biomarkers into predictive and prognostic biomarkers based on their roles in clinical studies. To design a clinical trial for precision medicine, predictive biomarkers and prognostic biomarkers should both be included. In statistical analysis, biomarkers are mathematically treated as covariates. We first classify covariates into predictive and prognostic covariates according to their roles. We then provide a brief review of recent advances in adaptive designs that incorporate covariates. However, the literature includes no designs that incorporate both prognostic covariates and predictive covariates simultaneously. In this paper, we propose a new family of covariate-adjusted response-adaptive (CARA) designs that incorporate both prognostic and predictive covariates and the responses. It is important to note that the predictive biomarkers and prognostic biomarkers play different roles in the new designs. The advantages of the proposed methods are demonstrated via numerical studies, and some further statistical issues are also discussed.

Challenges and opportunities in biomarker-driven trials: adaptive randomization

“…To incorporate patients' biological covariates such as gene or protein expression, which may define the subset of patients who respond favorably to an experimental treatment, in RAR designs, CARA has been proposed. CARA estimates the response probability conditioning on the covariates for updating the treatment allocation probability (23)(24)(25)(26)(27)(28). Thus, RAR and CARA designs increase ethically treating patients based on accumulating data (35)(36)(37)(38).…”

“…This paper aims to discuss challenges and opportunities in biomarker-driven randomization. The biomarkerdriven randomization is a randomization strategy adapted based on biomarkers to identify patients who would respond better to the treatment and optimize the treatment allocation by adaptively randomizing more patients to the superior treatment based on biomarkers and accumulating information during the trial (23)(24)(25)(26)(27)(28). We consider several types of biomarker-driven randomization, which are the covariate-adjusted versions of the existing response-adaptive randomization (RAR) and examine the performance of the covariate-adjusted RAR (CARA) in group sequential clinical trials allowing early stopping.…”

The benefits of covariate adjustment for adaptive multi-arm designs

“…There are some publications that consider the role of covariates when other types of adaptation are implemented, such as the blinded sample size re-estimation method, 39,40 the standard group-sequential design, 41 and adaptive randomization. 42 In this paper, we aim to fill this gap in the literature and explore the impact of covariate adjustment in AMADs with treatment selection. We show how covariate adjustment affects treatment selection rules, hypothesis testing and power, as well as the estimation of the treatment effects.…”