Document Detail


Duration of accrual and follow-up for two-stage clinical trials.
MedLine Citation:
PMID:  11280845     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
Group sequential trials with time to event end points can be complicated to design. Not only are there unlimited choices for the number of events required at each stage, but for each of these choices, there are unlimited combinations of accrual and follow-up at each stage that provide the required events. Methods are presented for determining optimal combinations of accrual and follow-up for two-stage clinical trials with time to event end points. Optimization is based on minimizing the expected total study length as a function of the expected accrual duration or sample size while providing an appropriate overall size and power. Optimal values of expected accrual duration and minimum expected total study length are given assuming an exponential proportional hazards model comparing two treatment groups. The expected total study length can be substantially decreased by including a follow-up period during which accrual is suspended. Conditions that warrant an interim follow-up period are considered, and the gain in efficiency achieved by including an interim follow-up period is quantified. The gain in efficiency should be weighed against the practical difficulties in implementing such designs. An example is given to illustrate the use of these techniques in designing a clinical trial to compare two chemotherapy regimens for lung cancer. Practical considerations of including an interim follow-up period are discussed.
Authors:
L D Case; T M Morgan
Related Documents :
8210815 - The continual reassessment method in cancer phase i clinical trials: a simulation study.
21850445 - Effects of stress on alcohol drinking: a review of animal studies.
4037245 - Ethical issues in cooperative cancer therapy trials from a statistical viewpoint. ii. s...
17524255 - A comparison of fixed-step-size and bayesian staircases for sensory threshold estimation.
11007325 - Non-random dispersal in the butterfly maniola jurtina: implications for metapopulation ...
21119855 - The matching relation and situation-specific bias modulation in professional football p...
Publication Detail:
Type:  Journal Article; Research Support, U.S. Gov't, P.H.S.    
Journal Detail:
Title:  Lifetime data analysis     Volume:  7     ISSN:  1380-7870     ISO Abbreviation:  Lifetime Data Anal     Publication Date:  2001 Mar 
Date Detail:
Created Date:  2001-04-02     Completed Date:  2001-04-19     Revised Date:  2007-11-15    
Medline Journal Info:
Nlm Unique ID:  9516348     Medline TA:  Lifetime Data Anal     Country:  United States    
Other Details:
Languages:  eng     Pagination:  21-37     Citation Subset:  IM    
Affiliation:
Department of Public Health Sciences and the Comprehensive Cancer Center of Wake Forest University, Wake Forest University School of Medicine, USA. dcase@wfubmc.edu
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Antineoplastic Agents / therapeutic use
Carcinoma, Small Cell / drug therapy
Clinical Trials as Topic / methods*
Follow-Up Studies
Humans
Lung Neoplasms / drug therapy
Patient Selection
Proportional Hazards Models
Randomized Controlled Trials as Topic / methods
Research Design*
Sample Size
Survival Analysis
Grant Support
ID/Acronym/Agency:
5-P30-CA12197/CA/NCI NIH HHS
Chemical
Reg. No./Substance:
0/Antineoplastic Agents

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


Previous Document:  Chronic non-cancer pain: an overview of assessment and contemporary management.
Next Document:  Marginal likelihood estimation for proportional odds models with right censored data.