A Bayesian approach to tracking patients having changing pharmacokinetic parameters

• Published in: Journal of pharmacokinetics and pharmacodynamics Vol. 31; no. 1; pp. 75 - 107
• Main Authors: Bayard, David S., Jelliffe, Roger W.
• Format: Journal Article
• Language: English
• Published: Legacy CDMS Springer 01.02.2004; Springer Nature B.V
• Subjects: Algorithms; Bayes Theorem; Bayesian analysis; Biological and medical sciences; Clinical Trials as Topic; Economic models; Humans; Life Sciences (General); Linear Models; Medical sciences; Normal Distribution; Pharmacokinetics; Pharmacology. Drug treatments; Studies; Time Factors; Tobramycin - pharmacokinetics; Tobramycin/pharmacokinetics; Algorithms; Time Factors; Humans; Bayes Theorem; Linear Models; Pharmacokinetics; Clinical Trials; Normal Distribution; Human; Drug; Multiple; Decision support system; Health; Estimation; Pharmacology; time-varying parameters; health sciences; decision support systems; Therapeutic drug monitoring; Treatment; Surveillance; Markov Chain; Parameter; Surgical approach; Models; filtering; Monitoring; interactive multiple model
• ISSN: 1567-567X; 1573-8744
• DOI: 10.1023/B:JOPA.0000029490.76908.0c

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.