ANALYSIS OF NONRANDOMLY CENSORED ORDERED CATEGORICAL LONGITUDINAL DATA FROM ANALGESIC TRIALS

A clinical trial of an analgesic agent compares pain relief scores ove r time among groups of patients. All subjects experience the same pain ful procedure, but different subjects are given different randomly ass igned doses of active agent or placebo when they first request it. The data are short individual time series of ordered categorical pain rel ief scores subsequent to dosing. Nonrandom right censoring may be pres ent because patients can elect to remedicate with an active agent if t heir pain relief is insufficient. The trial is meant to address two qu estions: (a) Is there proof that the drug relieves pain? If so, (b) Wh at dosage patterns should be investigated further, or recommended for use by a typical patient? Marginal models of human pharmacology are ba sically empirical models, and although an analysis of a study based on such a model can adequately address the first question, such is not t he case for the second question, because this question requires extrap olation to untested dosing patterns. We propose to analyze study data using a hierarchical model so as to address both questions. The analys is uses a semimechanistic subject-specific pain-relief model for the d istribution of all (uncensored and censored) observations, conditional on individual random effects, and an empirical model for the censorin g outcome, remedication, conditional on observed pain relief and indiv idual random effects. We estimate the parameters of the foregoing (non linear mixed effects) model via maximum likelihood, assuming normally distributed random effects. Monte Carlo integration with respect to th e random effects is used to compute marginal statistics relevant to th e dosing question. Of particular note is that this formulation encoura ges use of subject matter information in model specification so that t he extrapolations required to address the dosing question are credible . An example is given of the application of the analysis to analgesic trial data for the drug ketorolac.