Effect of baseline measurement on the change from baseline in QTc intervals

Phase I thorough QT (TQT) studies are routinely conducted by pharmaceutical companies for all new compounds to satisfy the requirements of International Conference on Harmonisation (ICH) E14 guidance on the evaluation of QTc prolongation. The primary endpoint is the change from baseline in QT interval corrected for heart rate (QTc), and the hypothesis of interest is the noninferiority of drug to placebo. Sometimes, due to the properties of the compound, it becomes necessary to use parallel group designs for TQT studies. In such situations, the effect of the baseline on the change from baseline in QTc becomes an important issue because differing baseline between the drug and placebo groups may not allow for proper estimation of the drug's effect. In this work, we evaluate the effect of baseline on the change from baseline using the placebo data from several TQT studies. Resampling techniques are used to evaluate the impact of differing baselines across groups.