Ogungbenro Kayode, Aarons Leon
Centre for Applied Pharmacokinetics Research, The University of Manchester, Oxford Road, Manchester, UK.
Pharm Stat. 2010 Oct-Dec;9(4):255-68. doi: 10.1002/pst.388.
This paper describes an approach for calculating sample size for population pharmacokinetic experiments that involve hypothesis testing based on multi-group comparison detecting the difference in parameters between groups under mixed-effects modelling. This approach extends what has been described for generalized linear models and nonlinear population pharmacokinetic models that involve only binary covariates to more complex nonlinear population pharmacokinetic models. The structural nonlinear model is linearized around the random effects to obtain the marginal model and the hypothesis testing involving model parameters is based on Wald's test. This approach provides an efficient and fast method for calculating sample size for hypothesis testing in population pharmacokinetic models. The approach can also handle different design problems such as unequal allocation of subjects to groups and unbalanced sampling times between and within groups. The results obtained following application to a one compartment intravenous bolus dose model that involved three different hypotheses under different scenarios showed good agreement between the power obtained from NONMEM simulations and nominal power.
本文描述了一种用于计算群体药代动力学实验样本量的方法，该实验涉及基于多组比较进行假设检验，以检测混合效应模型下组间参数的差异。此方法将仅涉及二元协变量的广义线性模型和非线性群体药代动力学模型中所描述的内容，扩展到了更复杂的非线性群体药代动力学模型。结构非线性模型围绕随机效应进行线性化，以获得边际模型，并且涉及模型参数的假设检验基于 Wald 检验。该方法为群体药代动力学模型中假设检验的样本量计算提供了一种高效且快速的方法。该方法还可以处理不同的设计问题，例如组间受试者分配不均以及组间和组内采样时间不均衡。将其应用于一个一室静脉推注剂量模型，该模型在不同场景下涉及三种不同假设，结果表明从 NONMEM 模拟获得的值与名义效能之间具有良好的一致性。
