A functional linear model for comparing two pharmacokinetics profiles

Abstract

In a traditional pharmacokinetics (PK) study, compartmental models or non-compartmental models are often used to make indirect inferences on some PK parameters such as area under the plasma concentration curve (AUC), maximum plasma concentration ( C max), time to maximum plasma concentration ( T max) and half-life. The assumptions about compartmental models are sometimes not attainable or very difficult to validate. The indirect inferences on some PK parameters are sometimes not always accurate. In this paper, a functional linear model is proposed to compare PK profiles directly instead of the PK parameters. The model does not make any parametric assumptions about compartments, and is general enough to allow the number of observations, as well as, the administration and measuring time to be different for each experimental unit. The usefulness of the proposed model is demonstrated by using a real data set from a PK study.