Search PubMed⌕ Search

Biomedical subjects

L Z Shen

Publications and source records attributed to L Z Shen.

7 recordsLinked to original sources
PubMed1999

Estimation of mean quality adjusted survival time.

In clinical studies, we often consider not only patients' survival time, but also their quality of life. Quality adjusted life years (QALY) is an integrated measure of medical outcome that combines a patient's quantity and quality of life. Estimation of mean QALY for a group of patients is complicated by the fact that some patients are censored. The conventional approach is to obtain the Kaplan-Meier estimate of the survival function associated with individual QALYs and then use the area under the Kaplan-Meier curve as an estimate of mean QALY. Glasziou, Simes and Gelber showed that this method is biased because censoring at the nominal time scale is informative for predicting unobserved QALYs. In this paper, we propose a methodology for consistent estimation of mean QALY. Simulation studies are conducted to investigate the relative performance of the new method and the conventional method.

Computer Simulation↗
PubMed1999

Two-sample continual reassessment method.

We discuss an extension of the continual reassessment method (CRM) for use in phase I dose-finding studies. The extension enables the method to be applied to two groups of patients to determine the appropriate dose levels for each group. The method takes the specification of a simple relationship between the dose-toxicity curves for the two groups and runs the CRM on the bivariate model using maximum likelihood. We prove consistency of the method under fairly weak conditions and provide several simulations to give an idea how the method works in practice. We also undertake an evaluation of its performance by considering three possible situations: The first is the two-sample CRM, which directly uses a working model for the relationship between the two groups, carrying out a single trial using this method; the second situation carries out single trials for each of the two groups separately using the original (one-sample) CRM. The third situation is the case where such heterogeneity is ignored and the two groups are pooled into a single group, again using the original (one-sample) CRM. Simulations are carried out under a large class of model misspecifications, both of the dose-toxicity relationships and of the functional form linking the groups, and are backed up by asymptotic results. Our conclusions match intuition: The first scheme gives the most favorable results when the two groups are different but share some features. When the groups are very different, the second scheme performs similarly to the first for finite sample sizes while having some advantages in terms of asymptotic efficiency. The third, as expected, gives the best results in the absence of patient heterogeneity. The two-sample method appears particularly advantageous when there may not be enough subjects in one of the subgroups for it to be feasible to carry out two trials.

Clinical Trials, Phase I as Topic↗
PubMed1998

Sample size determination for controlling the upper confidence limit of incidence rate of a binomial endpoint.

Assume that in a comparative clinical study the primary endpoint is a binary event, such as life or death. A new treatment or therapy is tested for a significant reduction of the incidence of the binary event compared with a control group. Another objective is to ensure that the incidence in the new treatment group is below some clinically acceptable value. This is done by calculating the exact upper 95% confidence limit for the probability of the event. The study is considered successful if the upper confidence limit is lower than a historical threshold, as well as if there is a significant reduction in the incidence of the event by the new treatment. In this article, we provide an exact method for calculating the sample size so that there will be adequate power to ensure that the exact upper confidence limit is below the threshold. Based on this we can design a study to achieve both objectives.

Binomial Distribution↗
PubMed1996

Continual reassessment method: a likelihood approach.

The continual reassessment method as described by O'Quigley, Pepe, and Fisher (1990, Biometrics 46, 33-48) leans to a large extent upon a Bayesian methodology. Initial experimentation and sequential updating are carried out in a natural way within the context of a Bayesian framework. In this paper we argue that such a framework is easily changed to a more classic one leaning upon likelihood theory. The essential features of the continual reassessment method remain unchanged. In particular, large sample properties are the same unless the prior is degenerate. For small samples and as far as the final recommended dose level is concerned, simulations indicate that there is not much to choose between a likelihood approach and a Bayesian one. However, for in-trial allocation of dose levels to patients, there are some differences and these are discussed. In contrast to the Bayesian approach, a likelihood one requires some extra effort to get off the ground. This is because the likelihood equation has no solution until we observe a toxicity. Initially then we suggest working with either a standard Up-and-Down scheme or standard continual reassessment method until toxicity is observed and then switching to the new scheme.

Bayes Theorem↗