TL33: Empirical Bayes methods in drug dosage individualization based on linear models
*Francisco J Diaz, The University of Kansas Medical Center 


Published developments show that random effects linear models may provide a solid theoretical framework for drug dosage individualization in chronic diseases (Diaz et al, 2007, Statistics in Medicine, 26, 2052-2073). In particular, individualized dosages computed with these models by means of an Empirical Bayesian Approach may produce better results than dosages computed with some methods routinely used in therapeutic drug monitoring. This is further supported by published empirical findings that show that random effects linear models may provide accurate representations of phase III and IV steady-state pharmacokinetic data, and may be useful for dosage computations. Empirical bayesian methods for drug dosage individualization have also been investigated in the context of nonlinear models (with very promising results). This roundtable will mainly discuss these methods in the context of linear models, although a very interesting discussion regarding the appropriateness of linear models versus non-linear ones will probably arise.