Atjaunināt sīkdatņu piekrišanu

E-grāmata: Clinical Trial Design - Bayesian and Frequentist Adaptive Methods: Bayesian and Frequentist Adaptive Methods [Wiley Online]

Citas grāmatas par šo tēmu:
  • Wiley Online
  • Cena: 144,57 €*
  • * this price gives unlimited concurrent access for unlimited time
Clinical Trial Design - Bayesian and Frequentist Adaptive Methods: Bayesian and Frequentist Adaptive MethodsPalielināt
Citas grāmatas par šo tēmu:
Wiley Online E-booksMore info about Wiley Online
Rokasgrāmatas mājas lapa: https://onlinelibrary.wiley.com/doi/book/10.1002/9781118183335
A balanced treatment of the theories, methodologies, and design issues involved in clinical trials using statistical methods

There has been enormous interest and development in Bayesian adaptive designs, especially for early phases of clinical trials. However, for phase III trials, frequentist methods still play a dominant role through controlling type I and type II errors in the hypothesis testing framework. From practical perspectives, Clinical Trial Design: Bayesian and Frequentist Adaptive Methods provides comprehensive coverage of both Bayesian and frequentist approaches to all phases of clinical trial design. Before underpinning various adaptive methods, the book establishes an overview of the fundamentals of clinical trials as well as a comparison of Bayesian and frequentist statistics.

Recognizing that clinical trial design is one of the most important and useful skills in the pharmaceutical industry, this book provides detailed discussions on a variety of statistical designs, their properties, and operating characteristics for phase I, II, and III clinical trials as well as an introduction to phase IV trials. Many practical issues and challenges arising in clinical trials are addressed. Additional topics of coverage include:





Risk and benefit analysis for toxicity and efficacy trade-offs



Bayesian predictive probability trial monitoring



Bayesian adaptive randomization



Late onset toxicity and response



Dose finding in drug combination trials



Targeted therapy designs





The author utilizes cutting-edge clinical trial designs and statistical methods that have been employed at the world's leading medical centers as well as in the pharmaceutical industry. The software used throughout the book is freely available on the book's related website, equipping readers with the necessary tools for designing clinical trials.

Clinical Trial Design is an excellent book for courses on the topic at the graduate level. The book also serves as a valuable reference for statisticians and biostatisticians in the pharmaceutical industry as well as for researchers and practitioners who design, conduct, and monitor clinical trials in their everyday work.
Preface xv
1 Introduction
1(12)
1.1 What Are Clinical Trials?
1(1)
1.2 Brief History and Adaptive Designs
2(3)
1.3 Modern Clinical Trials
5(2)
1.4 New Drug Development
7(3)
1.5 Emerging Challenges
10(1)
1.6 Summary
10(3)
2 Fundamentals of Clinical Trials
13(16)
2.1 Key Components of Clinical Trials
13(9)
2.1.1 Protocol
13(2)
2.1.2 Primary Objective
15(1)
2.1.3 Eligibility Criteria and Accrual
15(1)
2.1.4 Power and Sample Size
16(1)
2.1.5 Blinding
17(1)
2.1.6 Randomization
18(1)
2.1.7 Parallel and Crossover Designs
19(1)
2.1.8 Data Collection
20(1)
2.1.9 Adverse Events
20(1)
2.1.10 Closeout
21(1)
2.2 Pharmacokinetics and Pharmacodynamics
22(3)
2.3 Phases I-IV of Clinical Trials
25(2)
2.3.1 Phase I
25(1)
2.3.2 Phase II
25(1)
2.3.3 Phase III
26(1)
2.3.4 Phase IV
26(1)
2.4 Summary
27(2)
Exercises
28(1)
3 Frequentist versus Bayesian Statistics
29(48)
3.1 Basic Statistics
29(12)
3.1.1 Probability and Univariate Distributions
29(6)
3.1.2 Multivariate Distributions
35(3)
3.1.3 Copula
38(1)
3.1.4 Convergence of Sequences of Random Variables
39(2)
3.2 Frequentist Methods
41(11)
3.2.1 Maximum Likelihood Estimation
41(1)
3.2.2 Method of Moments
42(1)
3.2.3 Generalized Method of Moments
43(1)
3.2.4 Confidence Interval
44(2)
3.2.5 Hypothesis Testing
46(3)
3.2.6 Generalized Linear Model and Quasi-Likelihood
49(2)
3.2.7 Random Effects Model
51(1)
3.3 Survival Analysis
52(6)
3.3.1 Kaplan-Meier Estimator
52(4)
3.3.2 Log-Rank Test
56(1)
3.3.3 Proportional Hazards Model
56(2)
3.3.4 Cure Rate Model
58(1)
3.4 Bayesian Methods
58(14)
3.4.1 Bayes' Theorem
58(3)
3.4.2 Prior Elicitation
61(2)
3.4.3 Conjugate Prior Distribution
63(2)
3.4.4 Bayesian Generalized Method of Moments
65(1)
3.4.5 Credible Interval
66(1)
3.4.6 Bayes Factor
67(1)
3.4.7 Bayesian Model Averaging
68(1)
3.4.8 Bayesian Hierarchical Model
69(2)
3.4.9 Decision Theory
71(1)
3.5 Markov Chain Monte Carlo
72(2)
3.5.1 Inversion Sampling
72(1)
3.5.2 Rejection Sampling
72(1)
3.5.3 Gibbs Sampler
73(1)
3.5.4 Metropolis-Hastings Algorithm
73(1)
3.6 Summary
74(3)
Exercises
75(2)
4 Phase I Trial Design
77(38)
4.1 Maximum Tolerated Dose
77(2)
4.2 Initial Dose and Spacing
79(3)
4.3 3 + 3 Design
82(3)
4.4 A + B Design
85(2)
4.5 Accelerated Titration Design
87(2)
4.5.1 Acceleration and Escalation
87(1)
4.5.2 Modeling Toxicity with Random Effects
87(2)
4.6 Biased Coin Dose-Finding Method
89(1)
4.7 Continual Reassessment Method
90(5)
4.7.1 Probability Model
90(1)
4.7.2 Likelihood and Posterior
91(2)
4.7.3 Dose-Finding Algorithm
93(1)
4.7.4 Simulation Study
94(1)
4.8 Bayesian Model Averaging Continual Reassessment Method
95(8)
4.8.1 Skeleton of the CRM
95(1)
4.8.2 BMA-CRM
96(1)
4.8.3 Dose-Finding Algorithm
97(1)
4.8.4 Simulation Study
97(5)
4.8.5 Sensitivity Analysis
102(1)
4.9 Escalation with Overdose Control
103(2)
4.10 Bayesian Hybrid Design
105(6)
4.10.1 Algorithm- versus Model-Based Dose Finding
105(1)
4.10.2 Bayesian Hypothesis Testing
106(3)
4.10.3 Dose-Finding Algorithm
109(1)
4.10.4 Simulation Study
109(2)
4.11 Summary
111(4)
Exercises
112(3)
5 Phase II Trial Design
115(44)
5.1 Gehan's Two-Stage Design
117(2)
5.2 Simon's Two-Stage Design
119(3)
5.3 Bayesian Phase II Design with Posterior Probability
122(2)
5.4 Bayesian Phase II Design with Predictive Probability
124(2)
5.5 Predictive Monitoring in Randomized Phase II Trials
126(3)
5.6 Predictive Probability with Adaptive Randomization
129(7)
5.6.1 Bayesian Adaptive Randomization
129(1)
5.6.2 Predictive Probability
130(1)
5.6.3 Parameter Calibration
131(2)
5.6.4 Simulation Study
133(2)
5.6.5 Posterior versus Predictive Trial Monitoring
135(1)
5.7 Bayesian Phase II Design with Multiple Outcomes
136(4)
5.7.1 Bivariate Binary Outcomes
136(1)
5.7.2 Stopping Boundaries
137(3)
5.8 Phase I/II Design with Bivariate Binary Data
140(9)
5.8.1 Motivation
140(1)
5.8.2 Likelihood and Prior
141(3)
5.8.3 Odds Ratio and Dose-Finding Algorithm
144(3)
5.8.4 Numerical Comparison
147(2)
5.9 Phase I/II Design with Times to Toxicity and Efficacy
149(7)
5.9.1 Bivariate Times to Toxicity and Efficacy
150(1)
5.9.2 Areas Under Survival Curves
151(2)
5.9.3 Dose-Finding Algorithm
153(3)
5.10 Summary
156(3)
Exercises
156(3)
6 Phase III Trial Design
159(64)
6.1 Power and Sample Size
159(5)
6.1.1 Statistical Hypothesis
160(1)
6.1.2 Classification of Phase III Trials
161(2)
6.1.3 Superiority versus Noninferiority
163(1)
6.2 Comparing Means for Continuous Outcomes
164(8)
6.2.1 Testing for Equality
164(4)
6.2.2 Superiority Trial
168(1)
6.2.3 Noninferiority Trial
169(1)
6.2.4 Equivalence Trial
170(2)
6.3 Comparing Proportions for Binary Outcomes
172(8)
6.3.1 Testing for Equality
172(3)
6.3.2 Sample Size Formula with Unpooled Variance
175(1)
6.3.3 Superiority Trial
176(1)
6.3.4 Noninferiority Trial
177(2)
6.3.5 Equivalence Trial
179(1)
6.4 Sample Size with Survival Data
180(6)
6.4.1 Comparison of Survival Curves
180(1)
6.4.2 Parametric Approach under Exponential Distribution
181(2)
6.4.3 Nonparametric Approach with Counting Process
183(3)
6.5 Sample Size for Correlated Data
186(2)
6.5.1 Linear Model with Continuous Data
186(1)
6.5.2 Logistic Model with Binary Data
187(1)
6.6 Group Sequential Methods
188(16)
6.6.1 Multiple Testing
189(2)
6.6.2 Pocock's Design
191(2)
6.6.3 O'Brien and Fleming's Design
193(2)
6.6.4 Information and Asymptotic Distribution
195(3)
6.6.5 Stopping Boundary Computation
198(2)
6.6.6 Sample Size and Inflation Factor
200(2)
6.6.7 Futility Stopping Boundary
202(2)
6.6.8 Repeated Confidence Intervals
204(1)
6.7 Adaptive Designs
204(9)
6.7.1 Motivation
204(2)
6.7.2 Fisher's Combination Criterion
206(1)
6.7.3 Conditional Power
207(2)
6.7.4 Adaptive Group Sequential Method
209(2)
6.7.5 Self-Designing Strategy
211(2)
6.8 Causality and Noncompliance
213(5)
6.8.1 Causal Inference and Counterfactuals
213(1)
6.8.2 Noncompliance and Intent-to-Treat Analysis
214(2)
6.8.3 Instrumental Variable Approach
216(2)
6.9 Post-Approval Trial---Phase IV
218(5)
6.9.1 Limitations of Phase I---III Trials
218(1)
6.9.2 Drug Withdrawal
218(2)
Exercises
220(3)
7 Adaptive Randomization
223(30)
7.1 Introduction
223(2)
7.2 Simple Randomization
225(1)
7.3 Permuted Block Randomization
226(2)
7.4 Stratified Randomization
228(1)
7.5 Covariate-Adaptive Allocation by Minimization
228(3)
7.6 Biased Coin Design
231(1)
7.7 Play-the-Winner Rule
232(1)
7.7.1 Deterministic Scheme
232(1)
7.7.2 Randomized Scheme
232(1)
7.8 Drop-the-Loser Rule
233(1)
7.9 Optimal Adaptive Randomization
234(5)
7.9.1 Dichotomous Outcome
234(1)
7.9.2 Continuous Outcome
235(2)
7.9.3 Time-to-Event Outcome
237(2)
7.10 Doubly Adaptive Biased Coin Design
239(1)
7.11 Bayesian Adaptive Randomization
239(7)
7.11.1 Two-Arm Comparison
239(3)
7.11.2 Fixed-Reference Adaptive Randomization
242(1)
7.11.3 Moving-Reference Adaptive Randomization
242(4)
7.12 Adaptive Randomization with Efficacy and Toxicity Trade-offs
246(3)
7.12.1 Survival Model for Efficacy
247(1)
7.12.2 Probit Model for Toxicity
247(1)
7.12.3 Efficacy and Toxicity Trade-offs
248(1)
7.13 Fixed or Adaptive Randomization?
249(4)
Exercises
252(1)
8 Late-Onset Toxicity
253(18)
8.1 Missing Data with Delayed Outcomes
253(2)
8.2 Fractional 3 + 3 Design
255(5)
8.2.1 Redistributing Censored Data to the Right
255(2)
8.2.2 Dose-Finding Algorithm with a Target
257(1)
8.2.3 Simulation Study
258(2)
8.3 Fractional Continual Reassessment Method
260(1)
8.4 Time-to-Event Continual Reassessment Method
261(2)
8.4.1 Weighted Binomial Likelihood
261(1)
8.4.2 Numerical Comparison
262(1)
8.5 EM Continual Reassessment Method
263(8)
8.5.1 EM Algorithm with Missing Data
263(2)
8.5.2 Robust EM-CRM
265(1)
8.5.3 Dose-Finding Algorithm
266(1)
8.5.4 Simulation Study
267(3)
Exercises
270(1)
9 Drug-Combination Trials
271(26)
9.1 Why Are Drugs Combined?
271(3)
9.2 New Challenges
274(3)
9.3 Sequential Dose-Finding Scheme
277(2)
9.4 Dose Finding with Copula-Type Regression
279(6)
9.4.1 Clayton-Type Model
279(3)
9.4.2 Multiple Drugs in Combination
282(1)
9.4.3 Dose-Finding Algorithm
282(2)
9.4.4 Simulation Study
284(1)
9.5 Latent Contingency Table Approach
285(4)
9.5.1 Bivariate Binary Outcomes
285(2)
9.5.2 Latent Contingency Table
287(1)
9.5.3 Simulation Study
288(1)
9.6 Phase I/II Drug-Combination Trial
289(5)
9.6.1 Motivation
289(1)
9.6.2 Phase I/II Seamless Design
290(3)
9.6.3 Simulation Study
293(1)
9.7 Summary
294(3)
Exercises
295(2)
10 Targeted Therapy Design
297(14)
10.1 Cytostatic Agents
297(1)
10.2 Prognostic and Predictive Biomarkers
298(2)
10.3 Predictive Biomarker Validation
300(2)
10.3.1 Marker-by-Treatment Interaction Design
300(1)
10.3.2 Targeted Therapy Design with Marker-Based Strategy
301(1)
10.4 Randomized Discontinuation Design
302(2)
10.5 Adaptive Signature Design
304(2)
10.5.1 Split-Sample Approach
304(1)
10.5.2 Cross-Validation Approach
305(1)
10.6 Adaptive Threshold Design
306(5)
Exercises
309(2)
References 311(18)
Author Index 329(4)
Subject Index 333
GUOSHENG YIN, PhD, is Associate Professor in the Department of Statistics and Actuarial Science at The University of Hong Kong, and Adjunct Associate Professor in the Department of Biostatistics at The University of Texas MD Anderson Cancer Center.
Permanent link: https://www.kriso.lv/db/9781118183335_pe.html
Keywords: