Format

Send to

Choose Destination
See comment in PubMed Commons below
Comput Methods Programs Biomed. 2013 Aug;111(2):447-58. doi: 10.1016/j.cmpb.2013.04.014. Epub 2013 Jun 10.

NIMROD: a program for inference via a normal approximation of the posterior in models with random effects based on ordinary differential equations.

Author information

1
Univ. Bordeaux, ISPED, Centre INSERM U897-Epidemiologie-Biostatistique, F-33000 Bordeaux, France. melanie.prague@isped.u-bordeaux2.fr

Erratum in

  • Comput Methods Programs Biomed. 2014 Mar;113(3):927.

Abstract

Models based on ordinary differential equations (ODE) are widespread tools for describing dynamical systems. In biomedical sciences, data from each subject can be sparse making difficult to precisely estimate individual parameters by standard non-linear regression but information can often be gained from between-subjects variability. This makes natural the use of mixed-effects models to estimate population parameters. Although the maximum likelihood approach is a valuable option, identifiability issues favour Bayesian approaches which can incorporate prior knowledge in a flexible way. However, the combination of difficulties coming from the ODE system and from the presence of random effects raises a major numerical challenge. Computations can be simplified by making a normal approximation of the posterior to find the maximum of the posterior distribution (MAP). Here we present the NIMROD program (normal approximation inference in models with random effects based on ordinary differential equations) devoted to the MAP estimation in ODE models. We describe the specific implemented features such as convergence criteria and an approximation of the leave-one-out cross-validation to assess the model quality of fit. In pharmacokinetics models, first, we evaluate the properties of this algorithm and compare it with FOCE and MCMC algorithms in simulations. Then, we illustrate NIMROD use on Amprenavir pharmacokinetics data from the PUZZLE clinical trial in HIV infected patients.

KEYWORDS:

HIV; Maximum a posteriori; Maximum likelihood; Non-linear mixed-effects model; Ordinary differential equations; Pharmacokinetics

PMID:
23764196
DOI:
10.1016/j.cmpb.2013.04.014
[Indexed for MEDLINE]
PubMed Commons home

PubMed Commons

0 comments
How to join PubMed Commons

    Supplemental Content

    Full text links

    Icon for Elsevier Science
    Loading ...
    Support Center