Simultaneous Confidence Intervals for Signal Detection and Ascertaining Precision of Adverse Event Rates in Clinical Trials

The marketing authorization of a medicinal product is contingent upon demonstration of safety and efficacy in support of the product's labeled conditions of use. To demonstrate safety, one group of adverse events that requires detailed consideration is common adverse reactions (ARs). ARs and their frequency are reported in prescription drug labeling in the US and EU. The determination of these adverse reactions generally takes a simple approach - usually, inclusion is through the frequency of reporting and whether the adverse event (AE) rate for the drug exceeds the placebo rate. This standard method does not account for confounders or multiplicity. To overcome these limitations, we propose a Monte-Carlo approach to detect drug safety signals in clinical trials. We fit regression models incorporating covariates to assess the drug effect on the rate of AEs. Adjustment for multiplicity is carried out through the construction of simultaneous confidence intervals accounting for arbitrary correlations. A computationally efficient multiplier bootstrap approach using the Rademacher sequences is developed to generate random samples from the joint distribution of the estimators for all the AE rates. Compared to Bonferroni-based methods, the proposed method leads to narrower simultaneous confidence intervals and is more powerful in detecting potential safety signals.