Fully Bayesian Experimental Design for Pharmacokinetic Studies

被引:30
作者
Ryan, Elizabeth G. [1 ,2 ]
Drovandi, Christopher C. [1 ]
Pettitt, Anthony N. [1 ,3 ]
机构
[1] Queensland Univ Technol, Math Sci, Brisbane, Qld 4001, Australia
[2] Kings Coll London, Inst Psychiat, Biostat Dept, London SE5 8AF, England
[3] Queensland Univ Technol, ARC Ctr Excellence Math & Stat Frontiers, Brisbane, Qld 4001, Australia
基金
澳大利亚研究理事会;
关键词
MIXED-EFFECTS MODELS; 2009; INFLUENZA; MONTE-CARLO; ADULT PATIENTS; TIMES;
D O I
10.3390/e17031063
中图分类号
O4 [物理学];
学科分类号
0702 ;
摘要
Utility functions in Bayesian experimental design are usually based on the posterior distribution. When the posterior is found by simulation, it must be sampled from for each future dataset drawn from the prior predictive distribution. Many thousands of posterior distributions are often required. A popular technique in the Bayesian experimental design literature, which rapidly obtains samples from the posterior, is importance sampling, using the prior as the importance distribution. However, importance sampling from the prior will tend to break down if there is a reasonable number of experimental observations. In this paper, we explore the use of Laplace approximations in the design setting to overcome this drawback. Furthermore, we consider using the Laplace approximation to form the importance distribution to obtain a more efficient importance distribution than the prior. The methodology is motivated by a pharmacokinetic study, which investigates the effect of extracorporeal membrane oxygenation on the pharmacokinetics of antibiotics in sheep. The design problem is to find 10 near optimal plasma sampling times that produce precise estimates of pharmacokinetic model parameters/measures of interest. We consider several different utility functions of interest in these studies, which involve the posterior distribution of parameter functions.
引用
收藏
页码:1063 / 1089
页数:27
相关论文
共 45 条
  • [1] Sertraline treatment of children and adolescents with obsessive-compulsive disorder or depression: Pharmacokinetics, tolerability and efficacy
    Alderman, J
    Wolkow, R
    Chung, M
    Johnston, HF
    [J]. JOURNAL OF THE AMERICAN ACADEMY OF CHILD AND ADOLESCENT PSYCHIATRY, 1998, 37 (04) : 386 - 394
  • [2] Bayesian-optimal design via interacting particle systems
    Amzal, Billy
    Bois, Frederic Y.
    Parent, Eric
    Robert, Christian R.
    [J]. JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 2006, 101 (474) : 773 - 785
  • [3] [Anonymous], TECHNICAL REPORT
  • [4] [Anonymous], THEORY OF OPTIMAL EX
  • [5] Atkinson A. C., 1992, OPTIMUM EXPERIMENTAL
  • [6] OPTIMUM EXPERIMENTAL-DESIGNS FOR PROPERTIES OF A COMPARTMENTAL MODEL
    ATKINSON, AC
    CHALONER, K
    HERZBERG, AM
    JURITZ, J
    [J]. BIOMETRICS, 1993, 49 (02) : 325 - 337
  • [7] Bengtsson T., 2008, PROBABILITY AND STAT
  • [8] Berry, 2006, DECIS ANAL, V3, P197, DOI DOI 10.1287/DECA.1060.0079
  • [9] Decision analysis by augmented probability simulation
    Bielza, C
    Müller, P
    Insua, DR
    [J]. MANAGEMENT SCIENCE, 1999, 45 (07) : 995 - 1007
  • [10] Extracorporeal membrane oxygenation in adults with severe respiratory failure: a multi-center database
    Brogan, Thomas V.
    Thiagarajan, Ravi R.
    Rycus, Peter T.
    Bartlett, Robert H.
    Bratton, Susan L.
    [J]. INTENSIVE CARE MEDICINE, 2009, 35 (12) : 2105 - 2114