Obtaining pharmacokinetic population models using a genetic algorithm approach

Abstract

Nonlinear mixed effect model is the most used technique when developing a pharmacokinetic population model (PopPK), the characterization of a drug disposition into the body and taking decisions related to the dose adjustments. The covariate model is used to establish a relationship between the model parameters and the characteristics of the patients, and it helps to explain sources of variability in the PopPK. A known problem in the development of a covariate model is to decide which covariates should or should not be included in the model. In this work, a genetic algorithm (GA) was used to decide which covariates contribute in a major degree prediction of the variability in a PopPK model.