Bayesian adaptive designs provide a critical approach to improve the efficiency and success of drug development that has been embraced by the US Food and Drug Administration (FDA). This is particularly important for early phase trials as they form the basis for the development and success of subsequent phase II and III trials.
The objective of this book is to describe the state-of-the-art model-assisted designs to facilitate and accelerate the use of novel adaptive designs for early phase clinical trials. Model-assisted designs possess avant-garde features where superiority meets simplicity. Model-assisted designs enjoy exceptional performance comparable to more complicated model-based adaptive designs, yet their decision rules often can be pre-tabulated and included in the protocol—making implementation as simple as conventional algorithm-based designs. An example is the Bayesian optimal interval (BOIN) design, the first dose-finding design to receive the fit-for-purpose designation from the FDA. This designation underscores the regulatory agency's support of the use of the novel adaptive design to improve drug development.
Features
Represents the first book to provide comprehensive coverage of model-assisted designs for various types of dose-finding and optimization clinical trials
Describes the up-to-date theory and practice for model-assisted designs
Presents many practical challenges, issues, and solutions arising from early-phase clinical trials
Illustrates with many real trial applications
Offers numerous tips and guidance on designing dose finding and optimization trials
Provides step-by-step illustrations of using software to design trials
Develops a companion website (www.trialdesign.org) to provide freely available, easy-to-use software to assist learning and implementing model-assisted designs
Written by internationally recognized research leaders who pioneered model-assisted designs from the University of Texas MD Anderson Cancer Center, this book shows how model-assisted designs can greatly improve the efficiency and simplify the design, conduct, and optimization of early-phase dose-finding trials. It should therefore be a very useful practical reference for biostatisticians, clinicians working in clinical trials, and drug regulatory professionals, as well as graduate students of biostatistics. Novel model-assisted designs showcase the new KISS principle: Keep it simple and smart!
Author(s): Ying Yuan, Ruitao Lin, J. Jack Lee
Series: Chapman & Hall/CRC Biostatistics Series
Publisher: CRC Press/Chapman & Hall
Year: 2022
Language: English
Pages: 233
City: Boca Raton
Cover
Half Title
Series Page
Title Page
Copyright Page
Dedication
Contents
Preface
Author Biographies
1. Bayesian Statistics and Adaptive Designs
1.1. Basics of Bayesian statistics
1.1.1. Bayes' theorem
1.1.2. Bayesian inference
1.2. Bayesian adaptive designs
1.3. Adoption of Bayesian adaptive designs
2. Algorithm-Based and Model-Based Dose Finding Designs
2.1. Introduction
2.2. Traditional 3+3 design
2.3. Cohort expansion
2.4. Accelerated titration design
2.5. Continual reassessment method
2.6. Bayesian model averaging CRM
2.7. Escalation with overdose control
2.8. Bayesian logistic regression method
2.9. Software
3. Model-Assisted Dose Finding Designs
3.1. Introduction
3.2. Modified toxicity probability interval design
3.3. Keyboard design
3.4. Bayesian optimal interval (BOIN) design
3.4.1. Trial design
3.4.2. Theoretical derivation
3.4.3. Specification of design parameters
3.4.4. Statistical properties
3.4.5. Frequently asked questions
3.5. Operating characteristics
3.6. Software and case study
4. Drug-Combination Trials
4.1. Introduction
4.2. Model-based designs
4.3. Model-assisted designs
4.3.1. BOIN combination design
4.3.2. Keyboard combination design
4.3.3. Waterfall design
4.4. Operating characteristics
4.5. Software and case study
5. Late-Onset Toxicity
5.1. A common logistical problem
5.2. Late-onset toxicities
5.3. TITE-CRM
5.4. TITE-BOIN
5.4.1. Trial design
5.4.2. Incorporating prior information
5.4.3. Statistical properties
5.4.4. Operating characteristics
5.5. A unified approach using "effective" data
5.6. TITE-keyboard and TITE-mTPI designs
5.7. Software and case study
6. Incorporating Historical Data
6.1. Historical data and prior information
6.1.1. Incorporate prior information in CRM
6.2. BOIN with Informative Prior (iBOIN)
6.2.1. Trial design
6.2.2. Practical guidance
6.3. iKeyboard design
6.4. Operating characteristics
6.5. Software and case study
7. Multiple Toxicity Grades
7.1. Multiple toxicity grades
7.2. gBOIN accounting for toxicity grade
7.2.1. Trial design
7.2.2. Statistical derivation and properties
7.3. Multiple toxicity BOIN
7.3.1. Trial design
7.3.2. Statistical derivation and properties
7.4. Software and illustration
8. Finding Optimal Biological Dose
8.1. Introduction
8.1.1. Phase I–II design paradigm
8.2. EffTox design
8.2.1. Efficacy–toxicity trade-off
8.2.2. Joint probability model for efficacy and toxicity
8.2.3. Admissible rules
8.2.4. Dose-finding algorithm
8.3. U-BOIN design
8.3.1. Utility-based risk-benefit trade-off
8.3.2. Statistical model
8.3.3. Admissible rules
8.3.4. Dose-finding algorithm
8.3.5. Operating characteristics
8.4. BOIN12 design
8.4.1. Utility estimation using quasi-binomial likelihood
8.4.2. Admissible rules and dose comparison
8.4.3. Dose-finding rules
8.4.4. Operating characteristics
8.4.5. Extension to more complicated endpoints
8.5. TITE-BOIN12 design
8.6. Other model-assisted phase I/II designs
8.6.1. uTPI design
8.6.2. STEIN and BOIN-ET designs
8.7. Software and case study
Bibliography
Index
