Journal of Pharmacokinetics and Pharmacodynamics

, Volume 31, Issue 1, pp 75–107 | Cite as

A Bayesian Approach to Tracking Patients Having Changing Pharmacokinetic Parameters

Article

Abstract

This paper considers the updating of Bayesian posterior densities for pharmacokinetic models associated with patients having changing parameter values. For estimation purposes it is proposed to use the Interacting Multiple Model (IMM) estimation algorithm, which is currently a popular algorithm in the aerospace community for tracking maneuvering targets. The IMM algorithm is described, and compared to the multiple model (MM) and Maximum A-Posteriori (MAP) Bayesian estimation methods, which are presently used for posterior updating when pharmacokinetic parameters do not change. Both the MM and MAP Bayesian estimation methods are used in their sequential forms, to facilitate tracking of changing parameters. Results indicate that the IMM algorithm is well suited for tracking time-varying pharmacokinetic parameters in acutely ill and unstable patients, incurring only about half of the integrated error compared to the sequential MM and MAP methods on the same example.

health sciences estimation filtering Markov Chain decision support systems pharmacokinetics therapeutic drug monitoring interactive multiple model time-varying parameters 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    D.¡S.¡ Bayard,¡R.¡W.¡ Jelliffe,¡A.¡ Schumitzky,¡M.¡H.¡ Milman,¡and¡M.¡ Van¡Guilder.¡Precision¡drug¡dosage¡regimens¡using¡multiple¡model¡adaptive¡control:¡Theory¡and¡application¡to¡simulated¡Vancomycin¡therapy.,¡In¡Selected¡Topics¡in¡Mathematical¡Physics,¡Prof.¡R.¡Vasudevan¡Memorial¡Volume,¡by,¡R.¡ Sridhar,¡K.¡S.¡ Rao,¡V.¡ Lakshminarayanan¡(eds),¡World¡Scientific¡Publishing¡Co.,¡Madras,¡1995,¡pp.¡407-426.Google Scholar
  2. 2.
    B.¡G.¡ Lindsay.¡The¡geometry¡of¡mixture¡likelihoods:¡A¡general¡theory ¡Ann.¡Stat.¡11:86-94¡(1983).Google Scholar
  3. 3.
    A.¡ Mallet.¡A¡maximum¡likelihood¡estimation¡method¡for¡random¡coefficient¡regression¡models.¡Biometrika¡73:645(1986).Google Scholar
  4. 4.
    A.¡ Schumitzky.¡Nonparametric¡EM¡algorithms¡for¡estimating¡prior¡distributions.¡App.¡Math.¡Comput.¡45:143-158¡(1991).Google Scholar
  5. 5.
    R.¡ Leary,¡R.¡ Port,¡A.¡ Schumitzky,¡and¡R.¡ Jelliffe.¡New¡methods¡for¡statistically¡consistent¡and¡efficient¡PK/PD¡population¡estimation.¡A¡Poster¡at¡the¡International¡Congress¡on¡Therapeutic¡Drug¡Monitoring¡and¡Clinical¡Toxicology.¡Basel,¡Switzerland,¡¡September¡7–11,¡2003.Google Scholar
  6. 6.
    D.¡G.¡ Lainiotis.¡Partitioning:¡A¡unifying¡framework¡for¡adaptive¡systems,¡Part¡1:¡Estimation..¡IEEE¡Proc.¡64:1126-1143¡(1976).Google Scholar
  7. 7.
    A.¡ Schumitzky,¡D.¡S.¡ Bayard,¡M.¡H.¡ Milman,¡and¡R.¡W.¡ Jelliffe.¡Multiple¡model¡linear¡quadratic¡control¡of¡pharmacokinetic¡systems.,¡Proc.¡1994¡Western¡Multiconference:¡Simulations¡in¡the¡Health¡Sciences,¡IEEE,¡Piscataway,¡N.J.,¡1994,¡pp.¡99-104.Google Scholar
  8. 8.
    D.¡S.¡ Bayard,¡M.¡H.¡ Milman,¡and¡A.¡ Schumitzky.¡Design¡of¡dosage¡regimens:¡A¡multiple¡model¡stochastic¡control¡approach.¡Int.¡J.¡Bio-Med.¡Comput.¡36:103-115¡(1994).Google Scholar
  9. 9.
    J.¡K.¡ Tugnait.¡Detection¡and¡estimation¡for¡abruptly¡changing¡systems.¡Automatica¡15:607-615¡(1982).Google Scholar
  10. 10.
    E.¡ Mazor,¡A.¡ Averbuch,¡Y.¡ Bar-Shalom,¡and¡J.¡ Dayan.¡Interacting¡multiple¡model¡methods¡in¡target¡tracking:¡A¡survey.¡IEEE¡Trans.¡Aerospace¡Electr.¡Syst.¡34(1):103-123¡(1998).Google Scholar
  11. 11.
    H.¡A.¡P.¡ Blom.¡An¡efficient¡filter¡for¡abruptly¡changinhg¡systerms.¡Proc.¡23rd¡IEEE¡Conf¡on¡Decision¡and¡Control¡(Las¡Vegas,¡NV,¡December¡1984),¡IEEE,¡Piscataway,¡N.J.,¡1984.Google Scholar
  12. 12.
    H.¡A.¡P.¡ Blom¡and¡Y.¡ Bar-Shalom.¡The¡interacting¡multiple¡model¡algorithm¡for¡systems¡with¡Markovian¡switching¡coefficients.¡IEEE¡Trans.¡Automatic¡Control.¡33:780-783¡(1988).Google Scholar
  13. 13.
    D.¡S.¡ Bayard¡and¡R.¡W.¡ Jelliffe.¡Bayesian¡estimation¡of¡posterior¡densities¡for¡pharmacokinetic¡models¡having¡changing¡parameter¡values.¡Proc.¡SCS¡2000¡Western¡Multiconference,¡Int.¡Conf.¡on¡Health¡Sciences¡Simulation,¡San¡Diego,¡CA,¡January¡23–27,¡2000.Google Scholar
  14. 14.
    A.¡ Bustad,¡R.¡ Jelliffe,¡and¡D.¡ Terziivanov.¡A¡comparison¡of¡parametric¡and¡nonparametric¡methods¡of¡population¡pharmacokinetic¡modeling.¡Poster¡Presentation¡at¡the¡Annual¡Meetings¡of¡the¡American¡Society¡for¡Clinical¡Pharmacology¡and¡Therapeutics,¡Atlanta,¡GA,¡March¡26,¡2002.Google Scholar
  15. 15.
    R.¡ Jellife.¡Estimation¡of¡creatinine¡clearance¡in¡patients¡with¡unstable¡renal¡function,¡without¡a¡urine¡specimen.¡Am.¡J.¡Nephrol.¡22:3200-324¡(2002).Google Scholar
  16. 16.
    R.¡W.¡ Jelliffe,¡D.¡S.¡ Bayard,¡A.¡ Schumitzky,¡M.¡ Milman,¡F.¡ Jiang,¡S.¡ Leonov,¡A.¡ Gandhi,¡and¡A.¡ Botnen.¡A¡new¡clinical¡software¡package¡for¡multiple¡model¡(MM)¡design¡of¡drug¡dosage¡regiments¡for¡planning,¡monitoring,¡and¡adjusting¡optimally¡individualized¡drug¡therapy¡for¡patients.¡Presented¡at¡the¡4th¡International¡Meeting¡on¡Mathematical¡Modeling,¡Technical¡University¡of¡Vienna,¡Vienna,¡Austria,¡February¡6,¡2003.Google Scholar
  17. 17.
    P.¡ Maire,¡X.¡ Barbaut,¡P.¡ Girard,¡A.¡ Mallet,¡R.¡W.¡ Jelliffe,¡and¡T.¡ Berod.¡Preliminary¡results¡of¡three¡methods¡for¡population¡pharmacokinetic¡analysis¡(NONMEM,¡NPML,¡NPEM)¡of¡Amikacin¡in¡geriatric¡and¡general¡medicine¡patients.¡Int.¡J.¡Bio-Med.¡Comput.¡36:139-141¡(1994).Google Scholar

Copyright information

© Plenum Publishing Corporation 2004

Authors and Affiliations

  1. 1.Jet Propulsion LaboratoryCalifornia Institute of TechnologyPasadena
  2. 2.Laboratory of Applied Pharmacokinetics, School of MedicineUniversity of Southern CaliforniaLos Angeles

Personalised recommendations