Muutke küpsiste eelistusi

Handbook of Adaptive Designs in Pharmaceutical and Clinical Development [Kõva köide]

Edited by (Merck Research Laboratories, Rahway, New Jersey, USA), Edited by (Duke Univ, USA)
  • Formaat: Hardback, 496 pages, kõrgus x laius: 254x178 mm, kaal: 1020 g, 46 Tables, black and white; 60 Illustrations, black and white
  • Ilmumisaeg: 25-Oct-2010
  • Kirjastus: CRC Press Inc
  • ISBN-10: 1439810168
  • ISBN-13: 9781439810163
Teised raamatud teemal:
Handbook of Adaptive Designs in Pharmaceutical and Clinical DevelopmentSuurem pilt
  • Formaat: Hardback, 496 pages, kõrgus x laius: 254x178 mm, kaal: 1020 g, 46 Tables, black and white; 60 Illustrations, black and white
  • Ilmumisaeg: 25-Oct-2010
  • Kirjastus: CRC Press Inc
  • ISBN-10: 1439810168
  • ISBN-13: 9781439810163
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9781439810163.html
Märksõnad:
In response to the US FDAs Critical Path Initiative, innovative adaptive designs are being used more and more in clinical trials due to their flexibility and efficiency, especially during early phase development. Handbook of Adaptive Designs in Pharmaceutical and Clinical Development provides a comprehensive and unified presentation of the principles and latest statistical methodologies used when modifying trial procedures based on accrued data of ongoing clinical trials. The book also gives a well-balanced summary of current regulatory perspectives.

The first several chapters focus on the fundamental theory behind adaptive trial design, the application of the Bayesian approach to adaptive designs, and the impact of potential population shift due to protocol amendments. The book then presents a variety of statistical methods for group sequential design, classical design, dose-finding trials, Phase I/II and Phase II/III seamless adaptive designs, multiple stage seamless adaptive trial design, adaptive randomization trials, hypotheses-adaptive design, and treatment-adaptive design. It also covers predictive biomarker diagnostics for new drug development, clinical strategies for endpoint selection in translational research, the role of independent data monitoring committees in adaptive clinical trials, the enrichment process in targeted clinical trials for personalized medicine, applications of adaptive designs that use genomic or genetic information, adaptive trial simulation, and the efficiency of adaptive design. The final chapters discuss case studies as well as standard operating procedures for good adaptive practices.

With contributions from leading clinical researchers in the pharmaceutical industry, academia, and regulatory agencies, this handbook offers an up-to-date, complete treatment of the principles and methods of adaptive design and analysis. Along with reviewing recent developments, it examines issues commonly encountered when applying adaptive design methods in clinical trials.
Preface vii
Editors ix
Contributors xi
1 Overview of Adaptive Design Methods in Clinical Trials
1(1)
Annpey Pong
Shein-Chung Chow
1.1 Introduction
1(1)
1.2 What is Adaptive Design?
2(6)
Adaptations
Type of Adaptive Designs
Regulatory/Statistical Perspectives
1.3 Impact, Challenges, and Obstacles
8(1)
Impact of Protocol Amendments
Challenges in By Design Adaptation
Obstacles of Retrospective Adaptations
1.4 Some Examples
9(6)
1.5 Strategies for Clinical Development
15
Adaptive Design Strategies
Controversial Issues
2 Fundamental Theory of Adaptive Designs with Unplanned Design Change in Clinical Trials with Blinded Data
2(1)
Qing Liu
George Y. H. Chi
2.1 Background
1(1)
2.2 Conditional Theory
2(1)
2.3 Application
3(3)
Trial Description
Statistical Considerations
Calculation of nd
2.4 Discussion
6
3 Bayesian Approach for Adaptive Design
3(1)
Guosheng Yin
Ying Yuan
3.1 Introduction
1(2)
3.2 Bayesian Model Averaging Continual Reassessment Method
3(4)
Continual Reassessment Method
Bayesian Model Averaging CRM
Dose-Finding Algorithm
Simulation Study
3.3 Jointly Modeling Toxicity and Efficacy in Phase I/II Design
7(3)
Likelihood and Prior
Odds-Ratio Trade-Off
Simulation Studies
3.4 Drug-Combination Trial
10(3)
Copula-Type Regression
Dose-Finding Algorithm
Simulation Study
3.5 Adaptive Randomization with Drug Combinations
13(4)
Bayesian Adaptive Randomization
Phase I/II Design in Drug-Combination Trials
3.6 Conclusion
17
4 The Impact of Protocol Amendments in Adaptive Trial Designs
4(1)
Shein-Chung Chow
Annpey Pong
4.1 Introduction
1(1)
4.2 Moving Target Patient Population
2(1)
4.3 Statistical Inference with Covariate Adjustment
3(6)
Approach with Fixed Covariate
Alternative Approach with Random Covariate
Bayesian Approach
4.4 Inference Based on Mixture Distribution
9(9)
The Case Where μActual is Random and σActual is Fixed
Sample Size Adjustment
Remarks
4.5 Concluding Remarks
18
5 From Group Sequential to Adaptive Designs
5(1)
Christopher Jennison
Bruce W. Turnbull
5.1 Introduction
1(1)
5.2 The Canonical Joint Distribution of Test Statistics
2(1)
5.3 Hypothesis Testing Problems and Decision Boundaries with Equally Spaced Looks
3(5)
Two-Sided Tests
One-Sided Tests
One-Sided Tests with a Nonbinding Lower Boundary
Other Boundaries
5.4 Computations for Group Sequential Tests: Armitage's Iterated Integrals
8(2)
5.5 Error Spending Procedures for Unequal, Unpredictable Increments of Information
10(2)
5.6 P-Values and Confidence Intervals
12(2)
P-Values on Termination
A Confidence Interval on Termination
Repeated Confidence Intervals and Repeated P-Values
5.7 Optimal Group Sequential Procedures
14(4)
Optimizing Within Classes of Group Sequential Procedures
Optimizing with Equally Spaced Information Levels
Optimizing Over Information Levels
Procedures with Data Dependent Increments in Information
5.8 Tests Permitting Flexible, Data Dependent Increments in Information
18(5)
Flexible Redesign Protecting the Type I Error Probability
Efficiency of Flexible Adaptive Procedures
5.9 Discussion
23
6 Determining Sample Size for Classical Designs
6(1)
Simon Kirby
Christy Chuang-Stein
6.1 Introduction
1(1)
6.2 The Hypothesis Testing Approach
2(14)
Sample Size to Show Superiority of a Treatment
Sample Size for Studies to Show Noninferiority
Sample Size for Studies to Show Equivalence
Information-Based Approach to Sample Sizing
6.3 Other Approaches to Sample Sizing
16(5)
Estimation
Sample Sizing for Dual Criteria
Prespecifying Desirable Posterior False-Positive and False-Negative Probabilities
Assurance for Confirmatory Trials
6.4 Other Topics
21(2)
Missing Data
Multiple Comparisons
Reducing Sample Size Due to Efficiency Gain in an Adjusted Analysis
6.5 Summary
23
7 Sample Size Reestimation Design with Applications in Clinical Trials
7(1)
Lu Cui
Xiaoru Wu
7.1 Flexible Sample Size Design
1(2)
7.2 Sample Size Reestimation
3(3)
7.3 Measure of Adaptive Performance
6(3)
7.4 Performance Comparison
9(3)
7.5 Implementation
12
8 Adaptive Interim Analyses in Clinical Trials
8(1)
Gernot Wassmer
8.1 Introduction
1(1)
8.2 Confirmatory Adaptive Designs
2(2)
8.3 Most Relevant Types of Adaptations
4(6)
Adaptive Sample Size Recalculation
Confirmatory Adaptive Designs in Multiarmed Trials
Patient Enrichment Designs
8.4 Concluding Remarks
10
9 Classical Dose-Finding Trial
9(1)
Naitee Ting
9.1 Background and Clinical Development Plan
1(1)
9.2 Dose-Finding in Oncology
2(2)
Example: A Traditional 3+3 Design
9.3 Challenges
4(1)
Scientific Challenges
Business Challenges
9.4 Objectives
5(1)
9.5 Pharmacokinetic and Pharmacodynamic
6(1)
9.6 Clinical Trial Simulations
7(1)
9.7 Confirmation Versus Exploration
8(1)
9.8 Selection of Type I and Type II Error
9(2)
9.9 Analysis of Dose-Finding Trials: The MCP-Mod Method
11(1)
9.10 Range of Doses to be Studied
12(2)
9.11 Other Types of Design
14(1)
Cross-Over Dose-Response
Forced Titration
Optional Titration (Placebo-Controlled Titration to Endpoint)
9.12 Example: A True Case Study in Osteoarthritis (OA)
15(3)
9.13 Summary
18
10 Improving Dose-Finding: A Philosophic View
10(1)
Carl-Fredrik Burman
Frank Miller
Kiat Wee Wong
10.1 Introduction
1(1)
10.2 Traditional Dose-Finding: Can it be Improved?
2(4)
The Dose-Finding Process
Traditional Design of a Phase IIB Dose-Finding Study
Room for Improvement
10.3 Simple Examples of Optimal and Adaptive Designs
6(6)
An Example of a Fully Adaptive Design
Optimal Design
Adaptive Optimal Design
10.4 More on Optimal and Adaptive Designs
12(2)
The Multiparameter Model
Adaptive Sample Size
10.5 Dose-Finding: A Trade-Off Between Efficacy and Safety
14(3)
A Net Benefit Example
Temporal Aspects
10.6 Program Design
17(3)
Designing Phase IIB with the Big Picture in Mind
Dose Information from Confirmatory Phase
Adaptive Dose Selection in Phase III
10.7 Summary and Discussion
20
11 Adaptive Dose-Ranging Studies
11(1)
Marc Vandemeulebroecke
Frank Bretz
Jose Pinheiro
Bjorn Bornkamp
11.1 Introduction
1(2)
11.2 Dose-Ranging Studies
3(2)
Main Objectives of a Dose-Ranging Study
Multiple Comparison Procedures
Modeling
11.3 Adaptive Analysis of Dose-Ranging Studies
5(4)
Combining Multiple Comparisons and Modeling into an Adaptive Analysis Approach
Example
11.4 Adaptive Design of Dose-Ranging Studies
9(4)
Adaptive Designs
Optimal Designs
Adaptively Designed Dose-Ranging Studies
Example
11.5 Summary
13
12 Seamless Phase I/II Designs
12(1)
Vladimir Dragalin
12.1 Introduction
1(1)
12.2 Study Objectives
2(2)
Frequentist Formulation
Bayesian Formulation
12.3 Dose-Response Models
4(4)
Gumbel Model
Cox Bivariate Binary Model
Bivariate Probit Model
Continuation-Ratio Bivariate Binary Model
Proportional Odds Model
Continuation-Ratio Model
Models Based on Bivariate Discrete Distributions
12.4 Designs
8(14)
Nonparametric Designs
Bayesian Designs
Adaptive Optimal Designs
12.5 Conclusion
22
13 Phase II/III Seamless Designs
13(1)
Jeff Maca
13.1 Introduction
1(1)
13.2 General Considerations for Designing a Seamless Phase I/III Study
1(2)
13.3 Sample Sizes in Seamless Phase II/III Trials
3(1)
13.4 Methodologies
4(2)
13.5 Decision Process
6(1)
13.6 Case Study, Seamless Adaptive Designs in Respiratory Disease
6(1)
13.7 Conclusions
7(7)
14 Sample Size Estimation/Allocation for Two-Stage Seamless Adaptive Trial Designs
14(1)
Shein-Chung Chow
Annpey Pong
14.1 Introduction
1(1)
14.2 Two-Stage Adaptive Seamless Design
2(2)
Definition and Characteristics
Comparison
Practical Issues
14.3 Sample Size Calculation/Allocation
4(10)
Continuous Study Endpoints
Binary Responses
Time-to-Event Data
Remarks
14.4 Major Obstacles and Challenges
14(1)
Instability of Sample Size
Moving Patient Population
14.5 Examples
15(1)
14.6 Concluding Remarks
16
15 Optimal Response-Adaptive Randomization for Clinical Trials
15(1)
Lanju Zhang
William Rosenberger
15.1 Introduction
1(3)
Randomization in Clinical Trials
Adaptive Randomization
Balance, Ethics, and Efficiency
Response-Adaptive Randomization
15.2 Optimization
4(5)
Binary Outcomes
Continuous Outcomes
Survival Outcomes
More than Two Treatments
Optimal Allocation for Covariate-Adjusted Response-Adaptive Randomization
15.3 Implementation
9(2)
Real-Valued Urn Models
The Doubly Biased Coin Design Procedures
Efficient Randomized Adaptive Design (ERADE)
DA-Optimal Procedure
Performance Evaluation of Optimal Response-Adaptive Randomization Procedures
15.4 Inference
11(1)
15.5 Conclusion
11(5)
16 Hypothesis-Adaptive Design
16(1)
Gerhard Hommel
16.1 Introduction
1(1)
16.2 Definitions and Notions
2(1)
16.3 Global Tests with Adaptive Designs
2(1)
16.4 Multiple Tests
3(1)
16.5 General Methodology
4(1)
The Closure Test
The Closure Test for Adaptive Designs
Remarks
16.6 Applications
5(3)
Reduction of the Set of Initial Hypotheses
Reweighting
A Priori Ordered Hypotheses
Inclusion of New Hypotheses
16.7 How Much Freedom Should be Allowed?
8(1)
16.8 Further Aspects
9(2)
More than Two Stages
Logical Relations of Hypotheses
Correlations of Test Statistics
Two-Sided Tests
Confidence Intervals and Point Estimates
Many Hypotheses
16.9 Closing Remarks
11(6)
17 Treatment Adaptive Allocations in Randomized Clinical Trials: An Overview
17(1)
Atanu Biswas
Rahul Bhattacharya
17.1 Introduction
1(2)
17.2 Requirements of an Allocation Design: A Clinician's Perspective
3(2)
Treatment Imbalance
Selection Bias
17.3 Treatment Adaptive Allocations: Without Covariates
5(5)
Random Allocation Rule
Truncated Binomial Design
Permuted Block Design
Biased Coin Designs
17.4 Treatment Adaptive Allocations: With Covariates
10(6)
Stratified Randomization
Covariate-Adaptive Randomization
17.5 Concluding Remarks
16(2)
18 Integration of Predictive Biomarker Diagnostics into Clinical Trials for New Drug Development
18(1)
Richard Simon
18.1 Introduction
1(1)
18.2 Terminology
2(1)
18.3 Development of Predictive Biomarkers
3(1)
18.4 Phase II Designs for Oncology Trials
4(1)
18.5 Clinical Trial Designs Incorporating Predictive Biomarkers
5(1)
18.6 Enrichment Designs
5(1)
18.7 Designs that Include Both Test Positive and Test Negative Patients
6(5)
Analysis of Test Negatives Contingent on Significance in Test Positives
Analysis Determined by Interaction Test
Fallback Analysis Plan
Max Test Statistic
18.8 Adaptively Modifying Types of Patients Accrued
11(1)
18.9 Biomarker Adaptive Threshold Design
11(1)
18.10 Multiple Biomarker Design
12(1)
18.11 Adaptive Signature Design
12(1)
18.12 Conclusions
13(6)
19 Clinical Strategy for Study Endpoint Selection
19(1)
Siu Keung Tse
Shein-Chung Chow
Qingshu Lu
19.1 Introduction
1(2)
19.2 Model Formulation and Assumptions
3(2)
19.3 Comparison of the Different Clinical Strategies
5(2)
Results for Test Statistics, Power, and Sample Size Determination
Determination of the Noninferiority Margin
19.4 A Numerical Study
7(2)
Absolute difference Versus Relative difference
Responders' Rate Based on Absolute Difference
Responders' Rate Based on Absolute Difference
19.5 Concluding Remarks
9(11)
20 Adaptive Infrastructure
20(1)
Bill Byrom
Damian McEntegart
Graham Nicholls
20.1 Implementation of Randomization Changes
2(7)
Approaches to Implementation of Randomization Changes
Possible Pitfalls and Considerations
20.2 Maintaining the Invisibility of Design Changes
9(3)
Invisibility of Changes to Site Personnel
Invisibility of Changes to Sponsor Personnel
20.3 Drug Supply Considerations
12(2)
Case Study
20.4 Drug Supply Management
14(1)
20.5 Rapid Access to Response Data
15(3)
How Clean Should the Data be?
Data Collection Methods
20.6 Data Monitoring Committees, the Independent Statistician and Sponsor Involvement
18(3)
Data Monitoring
Monitoring for Adaptive Designs
20.7 Sample Size Reestimation
21(1)
20.8 Case Study
21(1)
Operational Considerations
20.9 Conclusions
22
21 Independent Data Monitoring Committees
21(1)
Steven Snapinn
Qi Jiang
21.1 Introduction
1(1)
21.2 Overview of Data Monitoring Committees
2(3)
History
Need for a DMC
Composition
Scope of Responsibilities
Setting Statistical Boundaries
21.3 Adaptive Trials and the Need for Data Monitoring
5(1)
21.4 DMC Issues Specific to Adaptive Trials
5(3)
Composition of the Committee
Need for Sponsor Involvement
Potential for Adaptive Decisions to Unblind
Other Issues
21.5 Summary
8(14)
22 Targeted Clinical Trials
22(1)
Jen-Pei Liu
22.1 Introduction
1(1)
22.2 Examples of Targeted Clinical Trials
2(3)
ALTTO Trial
TAILORx Trial
MINDACT Trial
22.3 Inaccuracy of Diagnostic Devices for Molecular Targets
5(1)
22.4 Inference for Treatment Under Enrichment Design
6(2)
22.5 Discussion and Concluding Remarks
8(15)
23 Functional Genome-Wide Association Studies of Longitudinal Traits
23(1)
Jiangtao Luo
Arthur Berg
Kwangmi Ahn
Kiranmoy Das
Jiahan Li
Zhong Wang
Yao Li
Rongling Wu
23.1 Introduction
1(1)
23.2 Why fGWAS: A Must-Tell Story
2(3)
A Biological Perspective
A Genetic Perspective
A Statistical Perspective
23.3 A Statistical Framework for fGWAS
5(4)
Model for fGWAS
Modeling the Mean Vectors
Modeling the Covariance Structure
Hypothesis Tests
23.4 High-Dimensional Models for fGWAS
9(1)
Multiple Longitudinal Variables and Time-to-Events
Multiple Genetic Control Mechanisms
23.5 Discussion
10(14)
24 Adaptive Trial Simulation
24(1)
Mark Chang
24.1 Clinical Trial Simulation
1(1)
24.2 A Unified Approach
2(3)
Stopping Boundary
Type-I Error Control, p-Value and Power
Selection of Test Statistics
Method for Stopping Boundary Determination
24.3 Method Based on the Sum of p-Values
5(2)
24.4 Method Based on Product of p-Values
7(2)
24.5 Method with Inverse-Normal p-Values
9(1)
24.6 Probability of Efficacy
10(1)
24.7 Design Evaluation: Operating Characteristics
10(3)
Stopping Probabilities
Expected Duration of an Adaptive Trial
Expected Sample-Sizes
Conditional Power and Futility Index
24.8 Sample-Size Reestimation
13(1)
24.9 Examples
13(5)
24.10 Summary
18(7)
25 Efficiency of Adaptive Designs
25(1)
Nigel Stallard
Tim Friede
25.1 Introduction
1(1)
25.2 Efficiency of Nuisance Parameter-Based Sample Size Reestimation Methods
2(3)
25.3 Efficiency of Group-Sequential Designs and Effect-Based Sample Size Reestimation
5(6)
Methodology for Sequential Designs
Methodology for Adaptive Designs with Effect-Based Sample Size Reestimation
Efficiency of Group-Sequential and Adaptive Designs Compared to Fixed Sample Size Tests
Comparison of Different Adaptive Design Approaches
25.4 Efficiency of Methods for Treatment and Subgroup Selection
11(1)
25.5 Efficiency Evaluation in Practice
12(14)
26 Case Studies in Adaptive Design
26(1)
Ning Li
Yonghong Gao
Shiowjen Lee
26.1 Introduction
1(2)
26.2 Some Concerns on Types of Design Adaptation
3(3)
Sample Size Reestimation
Withdrawal of Treatment/Dose Arms
Change of the Primary Endpoint
Changes Between Superiority and Noninferiority
Selection of Patient Subgroups Based on Interim Results
Issues on Simulations
26.3 Case Studies
6(7)
Case Study 1
Case Study 2
Case Study 3
Case Study 4
26.4 Concluding Remarks
13(14)
27 Good Practices for Adaptive Clinical Trials
27
Paul Gallo
27.1 Introduction
1(2)
27.2 General Considerations and Motivation for Using an Adaptive Design
3(1)
27.3 Scope of Adaptations in Confirmatory Trials
4(3)
Sample Size Reestimation
Seamless Trials
27.4 Interim Monitoring Practices in Adaptive Trials
7(2)
27.5 Other Trial Integrity Concerns for Adaptive Trials
9(1)
27.6 Consistency of Results Within Adaptive Trials
10(1)
27.7 Conclusion
11
Index 1
Annpey Pong is a manager in the Department of Biostatistics and Research Decision Sciences at Merck Research Laboratories. Dr. Pong is also the associate editor of the Journal of Biopharmaceutical Statistics. She earned her Ph.D. in statistics from Temple University.

Shein-Chung Chow is a professor in the Department of Biostatistics and Bioinformatics at Duke University School of Medicine. Dr. Chow is also a professor of clinical sciences at DukeNational University of Singapore Graduate Medical School and the editor of the Journal of Biopharmaceutical Statistics. He earned his Ph.D. in statistics from the University of WisconsinMadison.