The fourth and final paper in a series on statistics for clinical trials, published Dec. 21 in the Journal of the American College of Cardiology (JACC), further explores challenging issues that can arise during randomized clinical trials.

Stuart J. Pocock, PhD, et al., explore the design of noninferiority trials, looking at the value of factorial designs, the importance and challenges of strategy trials, data monitoring, and the role of adaptive designs. The authors cite several examples and offer guidance on how to design and interpret noninferiority trials.

They explain that when conducting a noninferiority trial to test if a new treatment is as good as the standard treatment, it is important to have a pre-defined noninferiority margin for the primary endpoint. A number of factors affect the choice of margin, including prior knowledge of the efficacy of the active control compared with placebo; and the sample size.

After the margin and other elements are applied, the authors state, “The trial’s conclusions then depend on where the 95 percent confidence interval (CI) for the treatment difference ends up in relation to this margin. If the upper bound of the two-sided 95 percent CI is less than delta, one can claim evidence that the new treatment is noninferior.”

The authors discuss the role of Data Monitoring Committees (DMC) in detail, identifying their main responsibilities and the factors that affect each. The DMC protects patient safety by watching carefully to identify any evidence of harm. The DNC also evaluates whether a trial should be stopped because of overwhelming evidence of superiority or inefficacy, and looks at quality issues. “If problems with noncompliance, missing visits/data, or slowness in event adjudication are evident, the DMC should provide feedback to the study leadership to facilitate improvements.”

The paper concludes with the authors’ recommendations regarding the controversial form of adaptive design where protocol changes are made on the basis of the unblinded interim results.

“I sincerely hope that this series of articles will help to elucidate some of these considerations for trialists and clinicians,” says Valentin Fuster, MD, PhD, MACC, editor in chief of JACC, who commissioned the four-part series. 

Keywords: Biometry, Clinical Trials Data Monitoring Committees, Confidence Intervals, Patient Compliance, Patient Safety, Research Design

< Back to Listings