Document Detail


Predictive probability of success and the assessment of futility in large outcomes trials.
MedLine Citation:
PMID:  17219755     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
We consider a class of futility rules based on a Bayesian approach for computing the predictive probability of success for large clinical trials, given a certain amount of observed data. This paper focuses on outcomes trials in particular, thus we are concerned with binary response variables. The proposed method determines the likelihood of observing a statistically significant treatment effect at the end of a study, conditional on the data observed at an interim time point and assuming that event rates governing future observations follow beta distributions. In particular, the prior distributions for the event rates of interest are updated based on the observed data at an interim time point, such that means and variances are intuitive functions of the data. Computational aspects will be discussed for the case in which event counts are functions of sample size and event rates only, and for situations in which they are functions of sample size, event rates, and exposure duration. We will discuss appropriate thresholds for declaring futility based on this approach, and the potential impact of overdispersion, a common phenomenon particularly in global outcomes trials.
Authors:
Benjamin Trzaskoma; Andreas Sashegyi
Related Documents :
15901405 - Asymptotic theory of information-theoretic experimental design.
2727465 - Surrogate endpoints in clinical trials: cardiovascular diseases.
18639475 - Carotid endarterectomy: technical practices of surgeons participating in the gala trial.
10398975 - Stability, repeatability, and the expression of signal magnitude in functional magnetic...
16672925 - Finding function in novel targets: c. elegans as a model organism.
10347875 - A mathematical model for toxin accumulation by killer yeasts based on the yeast populat...
Publication Detail:
Type:  Journal Article    
Journal Detail:
Title:  Journal of biopharmaceutical statistics     Volume:  17     ISSN:  1054-3406     ISO Abbreviation:  J Biopharm Stat     Publication Date:  2007  
Date Detail:
Created Date:  2007-01-15     Completed Date:  2007-02-09     Revised Date:  2007-11-15    
Medline Journal Info:
Nlm Unique ID:  9200436     Medline TA:  J Biopharm Stat     Country:  United States    
Other Details:
Languages:  eng     Pagination:  45-63     Citation Subset:  IM    
Affiliation:
Eli Lilly and Company, Lilly Corporate Center, DC 6072, Indianapolis, IN 46285, USA.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Algorithms
Anti-Infective Agents / therapeutic use
Bayes Theorem*
Clinical Trials Data Monitoring Committees
Computer Simulation
Controlled Clinical Trials as Topic / statistics & numerical data*
Humans
Medical Futility*
Probability
Protein C / therapeutic use
Recombinant Proteins / therapeutic use
Research Design
Sample Size
Sepsis / drug therapy
Software
Time Factors
Treatment Outcome
Chemical
Reg. No./Substance:
0/Anti-Infective Agents; 0/Protein C; 0/Recombinant Proteins; 0/drotrecogin alfa activated

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  A note on sample size calculation based on propensity analysis in nonrandomized trials.
Next Document:  The application of a Bayesian approach to the analysis of a complex, mechanistically based model.