Extension of the SAEM algorithm for nonlinear mixed models with 2 levels of random effects
| Autor: | Xavière Panhard, Adeline Samson |
|---|---|
| Přispěvatelé: | Comets, Emmanuelle, Modèles et méthodes de l'évaluation thérapeutique des maladies chroniques (U738 / UMR_S738), Université Paris Diderot - Paris 7 (UPD7)-Institut National de la Santé et de la Recherche Médicale (INSERM), Mathématiques Appliquées Paris 5 (MAP5 - UMR 8145), Université Paris Descartes - Paris 5 (UPD5)-Institut National des Sciences Mathématiques et de leurs Interactions (INSMI)-Centre National de la Recherche Scientifique (CNRS), Modèles et méthodes de l'évaluation thérapeutique des maladies chroniques, Université Paris Diderot - Paris 7 ( UPD7 ) -Institut National de la Santé et de la Recherche Médicale ( INSERM ), Mathématiques Appliquées à Paris 5 ( MAP5 - UMR 8145 ), Université Paris Descartes - Paris 5 ( UPD5 ) -Institut National des Sciences Mathématiques et de leurs Interactions-Centre National de la Recherche Scientifique ( CNRS ), Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Paris Diderot - Paris 7 (UPD7) |
| Jazyk: | angličtina |
| Rok vydání: | 2009 |
| Předmět: |
Time Factors
Computer science Pyridines MESH: Drug Interactions SAEM algorithm 030226 pharmacology & pharmacy 01 natural sciences MESH: Regression Analysis MESH : Biometry MESH: Theophylline 010104 statistics & probability MESH : Therapeutic Equivalency 0302 clinical medicine Cross-over trial MESH : Regression Analysis Statistics Cluster Analysis Drug Interactions MESH : Bias (Epidemiology) MESH: Anti-HIV Agents [ SDV.BIBS ] Life Sciences [q-bio]/Quantitative Methods [q-bio.QM] MESH: Biometry MESH : Algorithms [INFO.INFO-BI] Computer Science [cs]/Bioinformatics [q-bio.QM] Likelihood Functions Cross-Over Studies [SDV.BIBS] Life Sciences [q-bio]/Quantitative Methods [q-bio.QM] Estimation theory Mathematical statistics Multilevel nonlinear mixed effects models Regression analysis Bioequivalence trials General Medicine MESH : Nonlinear Dynamics MESH: Bias (Epidemiology) Random effects model [SDV.BIBS]Life Sciences [q-bio]/Quantitative Methods [q-bio.QM] Markov Chains 3. Good health Multiple periods MESH: Nonlinear Dynamics Area Under Curve MESH: Oligopeptides Regression Analysis Statistics Probability and Uncertainty MESH : Likelihood Functions Algorithm Monte Carlo Method Oligopeptides Algorithms MESH : Time Factors MESH : Oligopeptides Statistics and Probability MESH : Pyridines Biometry Anti-HIV Agents Atazanavir Sulfate MESH: Algorithms MESH: Monte Carlo Method Stochastic approximation MESH: Therapeutic Equivalency Article MESH: Cross-Over Studies 03 medical and health sciences Bias Theophylline MESH: Markov Chains [ INFO.INFO-BI ] Computer Science [cs]/Bioinformatics [q-bio.QM] MESH : Theophylline MESH : Cluster Analysis Humans 0101 mathematics MESH : Markov Chains MESH: Humans Markov chain MESH : Anti-HIV Agents MESH : Humans MESH: Pyridines MESH: Time Factors Conditional probability distribution MESH : Cross-Over Studies MESH: Cluster Analysis MESH : Drug Interactions MESH : Monte Carlo Method Nonlinear Dynamics Therapeutic Equivalency MESH: Area Under Curve MESH: Likelihood Functions MESH : Area Under Curve [INFO.INFO-BI]Computer Science [cs]/Bioinformatics [q-bio.QM] Sufficient statistic |
| Zdroj: | Biostatistics Biostatistics, 2009, 10 (1), pp.121-35. ⟨10.1093/biostatistics/kxn020⟩ Biostatistics, Oxford University Press (OUP), 2009, 10 (1), pp.121-35. 〈10.1093/biostatistics/kxn020〉 Biostatistics, Oxford University Press (OUP), 2009, 10 (1), pp.121-35. ⟨10.1093/biostatistics/kxn020⟩ |
| ISSN: | 1465-4644 1468-4357 |
| DOI: | 10.1093/biostatistics/kxn020 |
| Popis: | International audience; This article focuses on parameter estimation of multilevel nonlinear mixed-effects models (MNLMEMs). These models are used to analyze data presenting multiple hierarchical levels of grouping (cluster data, clinical trials with several observation periods, ...). The variability of the individual parameters of the regression function is thus decomposed as a between-subject variability and higher levels of variability (e.g. within-subject variability). We propose maximum likelihood estimates of parameters of those MNLMEMs with 2 levels of random effects, using an extension of the stochastic approximation version of expectation-maximization (SAEM)-Monte Carlo Markov chain algorithm. The extended SAEM algorithm is split into an explicit direct expectation-maximization (EM) algorithm and a stochastic EM part. Compared to the original algorithm, additional sufficient statistics have to be approximated by relying on the conditional distribution of the second level of random effects. This estimation method is evaluated on pharmacokinetic crossover simulated trials, mimicking theophylline concentration data. Results obtained on those data sets with either the SAEM algorithm or the first-order conditional estimates (FOCE) algorithm (implemented in the nlme function of R software) are compared: biases and root mean square errors of almost all the SAEM estimates are smaller than the FOCE ones. Finally, we apply the extended SAEM algorithm to analyze the pharmacokinetic interaction of tenofovir on atazanavir, a novel protease inhibitor, from the Agence Nationale de Recherche sur le Sida 107-Puzzle 2 study. A significant decrease of the area under the curve of atazanavir is found in patients receiving both treatments. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|