Analysing population PK/PD data with MONOLIX 4.0
Marc Lavielle (1), Hector Mesa (1), Jean-François Si Abdallah (1), Benoît Charles (1), Kaelig Chatel (1), Eric Blaudez (1)
(1) INRIA
MONOLIX performs maximum likelihood estimation in nonlinear mixed effects models without linearization. The algorithms used in MONOLIX combine the SAEM (stochastic approximation version of EM) algorithm with MCMC (Markov Chain Monte Carlo) and a Simulated Annealing procedure. The convergence of this algorithm and its good statistical properties have been proven and published in the best statistical journals [1,2]. The algorithm is fast and efficient in practice. MONOLIX 3.2 already propose many important and useful features:
- MLXTRAN allows writing complex models (ODEs defined models, count data and categorical data models, time-to-events data models, complex administrations, multiple compartments, transit compartment...)
- An extensive library of PK model (1, 2 and 3 cpts ; effect compartment ; bolus, infusion, oral0 and oral1 absorption ; linear and nonlinear elimination ; single dose, multiple doses and steady state)
- An extensive library of PD models
- Continuous and categorical covariate models,
- Constant, proportional, combined and exponential error models,
- Predifined distributions for the individual parameters (normal, log-normal, logit-normal, probit-normal, power-normal, ...)
- Model selection: information criteria (AIC, BIC), statistical tests (LRT, Wald test)
- Data in NONMEM format,
- Enhanced goodness of fit plots (VPC, weighted residuals, NPDE, ...),
- Mixture models & model mixtures (parameter mixture, between subject model mixture, within subject model mixture),
- Data simulation,
- Automatic reporting,
A beta version of release 4.0 will be presented during PAGE 2011. This version will contain several new important features such as:
- A new MLXTRAN for easy full project programming (any GUI feature can be controlled via MLXTRAN and vice-versa)
- Advanced workflow support (multi-instances & multi-users, GUI-less batch mode)
- PERL scripting (Mass processing, Multi-threaded batch scripts)
- Advanced graphics (stratify the data, interactive plots, create and save custom settings)
References:
[1] Delyon B, Lavielle M and Moulines E. "Convergence of a stochastic approximation version of the EM algorithm", Annals of Statistics. 27, 94- 128, 1999.
[2] Kuhn E and Lavielle M. "Maximum likelihood estimation in nonlinear mixed effects model", Computational Statistics and Data Analysis. 49, 1020-1038, 2005.
[3] Chan P., Jacqmin P., Lavielle M., McFadyen L., Weatherley B. "The Use of the SAEM Algorithm in MONOLIX Software for Estimation of Population Pharmacokinetic-Pharmacodynamic-Viral Dynamics Parameters of Maraviroc in Asymptomatic HIV Subjects'' Journal of Pharmacokinetics and Pharmacodynamics, vol. 38, pp. 41-61, 2011.
[4] Snoeck E., Chanu P., Lavielle M., Jacqmin P., Jonsson N., Jorga K., Goggin T., Jumbe S. , Frey N. "Hepatitis C Viral Dynamics Explaining Breakthrough, Relapse or Response after Chronic Treatment", Clinical Pharmacology and Therapeutics, Vol 87 (6), pp 706-713, 2010. AAPS Outstanding Manuscript Award in Modeling and Simulation.
[5] Savic R., Mentré F., Lavielle M. "Implementation and Evaluation of an SAEM algorithm for longitudinal ordered categorical data with an illustration in pharmacometrics'', The AAPS Journal, vol. 13, n. 1, pp; 44-53, 2011.