Adaptive randomization biased coin design: Experience in a cooperative group clinical trial

1980 ◽  
Vol 1 (2) ◽  
pp. 175 ◽  
Author(s):  
John F. Hannigan ◽  
Maria M. Koretz ◽  
Ed McGuigan ◽  
Bradley Efron ◽  
Byron W. Brown
Keyword(s):  
Clinical Trial ◽  
Cooperative Group ◽  
Adaptive Randomization ◽  
Biased Coin Design ◽  
Design Experience ◽  
Biased Coin

Which design is better? Ehrenfest urn versus biased coin

2000 ◽  
Vol 32 (03) ◽  
pp. 738-749 ◽  
Author(s):  
Yung-Pin Chen
Keyword(s):  
Clinical Trial ◽  
Statistical Inferences ◽  
Biased Coin Design ◽  
Biased Coin

Two features are desired in designing a sequential clinical trial: randomness and balance. The former makes the ground for valid statistical inferences and the latter strengthens efficiency in inference procedures. Unfortunately randomness and balance can be in conflict with one another, and clinicians may be caught between the need for both of them. This paper raises an interesting question: can one design consistently achieve more balance than another when both designs own the same randomness? The Ehrenfest urn design is presented to allocate two treatments under a sequential clinical trial, and its balance and randomness properties are investigated. The design is compared with the biased coin design with imbalance tolerance.

Which design is better? Ehrenfest urn versus biased coin

2000 ◽  
Vol 32 (3) ◽  
pp. 738-749 ◽  
Author(s):  
Yung-Pin Chen
Keyword(s):  
Clinical Trial ◽  
Statistical Inferences ◽  
Biased Coin Design ◽  
Biased Coin

Two features are desired in designing a sequential clinical trial: randomness and balance. The former makes the ground for valid statistical inferences and the latter strengthens efficiency in inference procedures. Unfortunately randomness and balance can be in conflict with one another, and clinicians may be caught between the need for both of them. This paper raises an interesting question: can one design consistently achieve more balance than another when both designs own the same randomness? The Ehrenfest urn design is presented to allocate two treatments under a sequential clinical trial, and its balance and randomness properties are investigated. The design is compared with the biased coin design with imbalance tolerance.

scholarly journals Bayesian Adaptive Randomization Designs for Clinical Trial

2015 ◽  
Vol 15 (2) ◽  
pp. 374-376
Author(s):  
Busaba Supawattan ◽  
Lily Ingsrisawa
Keyword(s):  
Clinical Trial ◽  
Adaptive Randomization

Abstract 128: Can Response Adaptive Randomization Increase Participation in Acute Stroke Trials?

Stroke ◽  
2013 ◽  
Vol 44 (suppl_1) ◽  
Author(s):  
Jason Tehranisa ◽  
William J Meurer
Keyword(s):  
Clinical Trial ◽  
Acute Stroke ◽  
Research Participation ◽  
Cross Sectional Survey ◽  
Multivariable Logistic Regression Model ◽  
Cross Sectional ◽  
Absolute Increase ◽  
Adaptive Randomization ◽  
The Impact ◽  
Stroke Trial

Introduction: Acute stroke trials may be improved by using response-adaptive randomization (RAR) because it works in favor of the trial population on average. With RAR, the ratio of participants assigned to each trial arm is adjusted to favor the better performing treatment using outcome information from earlier participants in the clinical trial. Hypothesis: When presented a hypothetical acute stroke trial, more patients would agree to a RAR versus a standard clinical trial with all other aspects of trial held constant. Methods: This cross-sectional survey included adult ED patients presenting without stroke or other critical illness. A standardized protocol was used and subjects were randomized to view either an RAR or standard hypothetical acute stroke trial. After viewing the video describing the hypothetical trial (http://youtu.be/cKIWduCaPZc), reviewing the consent form, and having questions answered, subjects indicated whether they would consent to the trial. Adequacy of the informed consent process was measured by ICQ-4. A multivariable logistic regression model was fitted to estimate the impact of RAR, while controlling for demographic factors and patient understanding of the design. Results: A total of 418 subjects (210 standard 208 RAR) were enrolled. All baseline characteristics were balanced between groups. There was significantly higher participation in the RAR trial (67.3%) versus the standard trial (54.5%), absolute increase: 12.8% (95% CI: 3.7 to 22.2%). The trials were generally well understood by the participants (Table); however standard randomization appeared to be better understood. The RAR group had a higher odds ratio of agreeing to research (O.R. 1.89, 95% CI [1.2 - 2.9]), while adjusting for patient level factors. Conclusion: The RAR trial attracted more research participation than standard randomization and has potential to increase recruitment and offer benefit to future trial participants.

scholarly journals Effects of chlorambucil and therapeutic decision in initial forms of chronic lymphocytic leukemia (stage A): results of a randomized clinical trial on 612 patients. The French Cooperative Group on Chronic Lymphocytic Leukemia

Blood ◽  
1990 ◽  
Vol 75 (7) ◽  
pp. 1414-1421 ◽  
Keyword(s):  
Clinical Trial ◽  
Chronic Lymphocytic Leukemia ◽  
Disease Progression ◽  
Randomized Clinical Trial ◽  
Survival Rates ◽  
Harmful Effect ◽  
Good Prognosis ◽  
Untreated Group ◽  
Lymphocytic Leukemia ◽  
Cooperative Group

Abstract In 1980, the French Cooperative Group on Chronic Lymphocytic Leukemia started a randomized clinical trial in which 612 good prognosis patients (stage A) received either no treatment (309 patients) or an indefinite course of chlorambucil at the daily dose of 0.1 mg/kg (303 patients). Overall survival appeared to be better in the untreated group (50 deceased patients compared with 62 in the chlorambucil group), but the difference was not significant (P = .21) even after adjusting for both prognostic and imbalanced factors (P = .09). The crude 5-year survival rates were 82% in the untreated group and 75% in the chlorambucil group. The action of chlorambucil appeared to be a complex phenomenon associating beneficial effects consisting in slowing down disease progression to stage B or C (P less than .01), and favoring disease remission with harmful effects given by a short survival after disease progression to stage B or C in the chlorambucil group and an increased incidence of epithelial cancers (33 v 19), as well as an excess of epithelial cancer deaths (13 v 3), in the chlorambucil group. As these results suggested an overall harmful effect of chlorambucil, we tried to define, within stage A patients, a group of patients with a low probability of disease progression. We showed that stage A patients with hemoglobin greater than or equal to 120 g/L and lymphocyte count less than 30 x 10(9)/L had a survival that was not significantly different (P = .46) from that of the age- and sex- matched French population. These patients, accounting for about 50% of all chronic lymphocytic leukemia patients, should not be treated unless disease progression is observed.

scholarly journals A randomized clinical trial of chlorambucil versus COP in stage B chronic lymphocytic leukemia. The French Cooperative Group on Chronic Lymphocytic Leukemia

Blood ◽  
1990 ◽  
Vol 75 (7) ◽  
pp. 1422-1425 ◽  
Keyword(s):  
Clinical Trial ◽  
Overall Survival ◽  
Chronic Lymphocytic Leukemia ◽  
Randomized Clinical Trial ◽  
Survival Rates ◽  
Lymphocytic Leukemia ◽  
Cooperative Group ◽  
Survival Times ◽  
Treatment Groups ◽  
Significant Difference

Abstract In 1980, the French Cooperative Group on Chronic Lymphocytic Leukemia started a randomized clinical trial in which intermediate prognosis patients (stage B) received either an indefinite course of chlorambucil (0.1 mg/kg/d) or 12 cycles of the COP regimen (vincristine, cyclophosphamide, and prednisone). We present the results of the third interim analysis based on 291 patients (151 in the chlorambucil group and 140 in the COP group) with a mean follow-up of 53 months at the reference date of June 1, 1987. At this date, 129 deaths were observed, 65 in the chlorambucil group and 64 in the COP group; there was no improvement in overall survival with the COP regimen (P = .44) even after adjusting for both prognostic and imbalanced factors (P = .24). The 3-year and 5-year overall survival rates were, respectively, 69% and 44% in the chlorambucil group as compared with 73% and 43% in the COP group. The median survival times were 58 months in the chlorambucil group and 57 months in the COP group. Moreover, no significant difference was observed between the two treatment groups in terms of either treatment response, 9-month status, time to disease progression to stage C, or causes of death.

scholarly journals Challenges to National Cancer Institute–Supported Cooperative Group Clinical Trial Participation: An ASCO Survey of Cooperative Group Sites

2010 ◽  
Vol 6 (3) ◽  
pp. 114-117 ◽  
Author(s):  
Allison R. Baer ◽  
Chelsey A. Kelly ◽  
Suanna S. Bruinooge ◽  
Carolyn D. Runowicz ◽  
Douglas W. Blayney
Keyword(s):  
Clinical Trial ◽  
Clinical Research ◽  
National Cancer Institute ◽  
Trial Participation ◽  
Cooperative Group ◽  
Clinical Trial Participation ◽  
Anecdotal Information

Anecdotal information regarding clinical research sites limiting participation in NCI-funded cooperative group studies prompted ASCO to collect data on and investigate the reasons behind this trend.

Sign in / Sign up

Export Citation Format

Share Document