Estimation of population pharmacokinetic model parameters using a genetic algorithm

Nowadays, there is need to analyze data in such a way as to consider the interrelationships between variables that describe the behavior of such data. The analysis of multivariate data refers precisely to a wide variety of methods of description or inference for the analysis of these data so that the inter-relationships between the variables can be quantified and evaluated. One of the most useful methods is the nonlinear mixed effects modeling. Nonlinear mixed effects models have been implemented in a wide variety of disciplines such as social sciences, physics, and life sciences where complex data structures such as multivariate observations or longitudinal data are present. Implementing a nonlinear mixed effects model is an arduous and complicated task. This is because the estimation of the parameters is performed solving maximum likelihood functions that usually have no analytical solution. In this work, we presented an example of an implementation of nonlinear mixed effect modeling for the development of a population pharmacokinetic model using a genetic algorithm to improve the estimation of the population pharmacokinetic parameters. At the end of this work, we conducted the comparison between a classical estimation method and an estimation method using a genetic algorithm.