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

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.
Type de document :
Article dans une revue
Computer Methods and Programs in Biomedicine, Elsevier, 2013, 111 (2), pp.447-58. 〈10.1016/j.cmpb.2013.04.014〉
Liste complète des métadonnées

http://www.hal.inserm.fr/inserm-00939447
Contributeur : Rodolphe Thiebaut <>
Soumis le : jeudi 30 janvier 2014 - 17:18:09
Dernière modification le : jeudi 4 janvier 2018 - 15:10:04

Identifiants

Collections

Citation

Mélanie Prague, Daniel Commenges, Jérémie Guedj, Julia Drylewicz, Rodolphe Thiébaut. NIMROD: a program for inference via a normal approximation of the posterior in models with random effects based on ordinary differential equations.. Computer Methods and Programs in Biomedicine, Elsevier, 2013, 111 (2), pp.447-58. 〈10.1016/j.cmpb.2013.04.014〉. 〈inserm-00939447〉

Partager

Métriques

Consultations de la notice

141