Premium
Modification of pharmacokinetic sampling schedules in clinical phase I trials: a use of Kullback–Leibler information
Author(s) -
Yafune Akifumi,
Ishiguro Makio
Publication year - 2001
Publication title -
statistics in medicine
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.996
H-Index - 183
eISSN - 1097-0258
pISSN - 0277-6715
DOI - 10.1002/sim.749
Subject(s) - computer science , kullback–leibler divergence , sampling (signal processing) , clinical trial , statistics , mathematics , medicine , artificial intelligence , filter (signal processing) , computer vision
In clinical phase I trials, pharmacokinetic sampling schedules often have to be modified while the trials proceed. The modifications are based on the observations from a limited number of subjects or only one subject in extreme cases. This paper describes a Kullback–Leibler information approach for modifying pharmacokinetic sampling schedules in clinical phase I trials. The proposed approach presupposes that the pharmacokinetic profile for each subject is specified by an appropriate pharmacokinetic model and the subject‐specific parameters. The best modification plan is selected from arbitrarily chosen candidates based on the Kullback–Leibler information. Applications are given to a simulation study and an actual phase I trial of an anti‐cancer drug. Copyright © 2001 John Wiley & Sons, Ltd.