Statistical Methods for Evaluating Safety in Medical Product Development

Кеш страницы книги с сайта:

Автор: Gould, Lawrence

Название: Statistical Methods for Evaluating Safety in Medical Product Development

Язык: английский

Издательство: Chichester, England: Wiley

Год: 2015

Объем: 400 p.

Формат: pdf

Размер: 12,2 mb

This book gives professionals in clinical research valuable information on the challenging issues of the design, execution, and management of clinical trials, and how to resolve these issues effectively. It also provides understanding and practical guidance on the application of contemporary statistical methods to contemporary issues in safety evaluation during medical product development. Each chapter provides sufficient detail to the reader to undertake the design and analysis of experiments at various stages of product development, including comprehensive references to the relevant literature.

Provides a guide to statistical methods and application in medical product development

Assists readers in undertaking design and analysis of experiments at various stages of product development

Features case studies throughout the book, as well as, SAS and R code



List of Contributors

1 Introduction

A. Lawrence Gould

1.1 Introduction

1.2 Background and context

1.3 A fundamental principle for understanding safety evaluation

1.4 Stages of safety evaluation in drug development

1.5 National medical product safety monitoring strategy

1.6 Adverse events vs adverse drug reactions, and an overall view safety evaluation

1.7 A brief historical perspective on safety evaluation

1.8 International conference on harmonization

1.9 ICH guidelines References

2 Safety graphics

A. Lawrence Gould

2.1 Introduction

2.1.1 Example and general objectives

2.1.2 What is the graphic trying to say?

2.2 Principles and guidance for constructing effective graphics

2.2.1 General principles

2.3 Graphical displays for addressing specific issues

2.3.1 Frequency of adverse event reports or occurrences

2.3.2 Timing of adverse event reports or occurrences

2.3.3 Temporal variation of vital sign and laboratory measurements

2.3.4 Temporal variation of combinations of vital sign and laboratory-measurements

2.3.5 Functional/multidimensional data

2.3.6 Multivariate outlier detection with multiplicity adjustment based on robust estimates of mean and covariance matrix

2.3.7 Monitoring individual patient trends

2.4 Discussion


3 QSAR modeling: prediction of biological activity from chemical structure Andy Liaw and Vladimir Svetnik

3.1 Introduction

3.2 Data

3.2.1 Chemical descriptors

3.2.2 Activity data

3.3 Model building

3.3.1 Random forests

3.3.2 Stochastic gradient boosting

3.4 Model validation and interpretation

3.5 Data example

3.6 Discussion References

4 Ethical and practical issues in phase 1 trials in healthy volunteers Stephen Senn

4.1 Introduction

4.2 Ethical basics

4.3 Inferential matters

4.3.1 Analysis of serious side-effects

4.3.2 Timing of events

4.4 Design for subject safety

4.4.1 Dosing interval

4.4.2 Contemporary dosing

4.5 Analysis

4.5.1 Objectives of first-in-man trials

4.5.2 (In)adequacy of statistical analysis plans

4.5.3 ‘Formal’ statistical analyses

4.6 Design for analysis

4.6.1 Treatment assignments and the role of placebo

4.6.2 Dose-escalation trial design issues

4.6.3 Precision at interim stages

4.7 Some final thoughts

4.7.1 Sharing information

4.8 Conclusions

4.9 Further reading References

5 Phase 1 trials

A. Lawrence Gould

5.1 Introduction

5.2 Dose determined by toxicity

5.2.1 Algorithmic (rule-based) approaches

5.3 Model-based approaches

5.3.1 Basic CRM design

5.3.2 Adaptive refinement of dosage list

5.3.3 Hybrid designs

5.3.4 Comparisons with rule-based designs

5.4 Model-based designs with more than one treatment (or non-monotonic toxicity)

5.5 Designs considering toxicity and efficacy

5.5.1 Binary' efficacy and toxicity considered jointly

5.5.2 Use of surrogate efficacy outcomes

5.5.3 Reduction of efficacy and toxicity outcomes to ordered categories

5.5.4 Binary' toxicity and continuous efficacy

5.5.5 Time to occurrence of binary toxicity and efficacy endpoints

5.5.6 Determining dosage and treatment schedule

5.6 Combinations of active agents

5.7 Software

5.8 Discussion References

6 Summarizing adverse event risk A. Lawrence Gould

6.1 Introduction

6.2 Summarization of key features of adverse event occurrence

6.3 Confidence/credible intervals for risk differences and ratios

6.3.1 Metrics

6.3.2 Coverage and interpretation

6.3.3 Binomial model

6.3.4 Poisson model

6.3.5 Computational results

6.4 Screening for adverse events

6.4.1 Outline of approach

6.4.2 Distributional model

6.4.3 Specification of priors

6.4.4 Example

6.5 Discussion References

7 Statistical analysis of recurrent adverse events Liqun Diao, Richard J. Cook and Ker-Ai Lee

7.1 Introduction

7.2 Recurrent adverse event analysis

7.2.1 Statistical methods for a single sample

7.2.2 Recurrent event analysis and death

7.2.3 Summary statistics for recurrent adverse events

7.3 Comparisons of adverse event rates

7.4 Remarks on computing and an application

7.4.1 Computing and software

7.4.2 Illustration: Analyses of bleeding in a transfusion trial

7.5 Discussion


Cardiovascular toxicity, especially QT/QTc prolongation Arne Ring and Robert Schall

8.1 Introduction

8.1.1 The QT interval as a biomarker of cardiovascular risk

8.1.2 Association of the QT interval with the heart rate

8.2 Implementation in preclinical and clinical drug development

8.2.1 Evaluations from sponsor perspective

8.2.2 Regulatory considerations on TQT trials

8.3 Design considerations for ‘‘Thorough QT trials”

8.3.1 Selection of therapeutic and supra-therapeutic exposure

8.3.2 Singlc-vcrsus multiple-dose studies: co-administration of interacting drugs

8.3.3 Baseline measurements

8.3.4 Parallel versus cross-over design

8.3.5 Timing of ECG measurements

8.3.6 Sample size

8.3.7 Complex situations

8.3.8 TQT trials in patients

8.4 Statistical analysis: thorough QT/QTc study

8.4.1 Data

8.4.2 Heart rate correction

8.4.3 A general framework for the assessment of QT prolongation

8.4.4 Statistical inference: Proof of “Lack of QT prolongation”

8.4.5 Mixed models for data from TQT studies

8.5 Examples of ECG trial designs and analyses from the literature

8.5.1 Parallel trial: Nalmefene

8.5.2 Cross-over trial: Linagliptin

8.5.3 Cross-over with minor QTc effect: Sitagliptin

8.5.4 TQT study with heart rate changes but without QTc effect: Darifenacin

8.5.5 Trial with both changes in HR and QT(c): Tolterodine

8.5.6 Boosting the exposure with pharmacokinetic interactions: Domperidone

8.5.7 Double placebo TQT cross-over design

8.6 Other issues in cardiovascular safety

8.6.1 Rosiglitazonc

8.6.2 Requirements of the FDA guidance

8.6.3 Impact on the development of antidiabetic drugs

8.6.4 General impact on biomarker validation References

9 Hepatotoxicity Donald C. Trost

9.1 Introduction

9.2 Liver biology and chemistry

9.2.1 Liver function

9.2.2 Liver pathology

9.2.3 Clinical laboratory tests for liver status

9.2.4 Other clinical manifestations of liver abnormalities

9.3 Drug-induced liver injury

9.3.1 Literature review

9.3.2 Liver toxicology

9.3.3 Clinical trial design

9.4 Classical statistical approaches to the detection of hepatic toxicity

9.4.1 Statistical distributions of analytes

9.4.2 Reference limits

9.4.3 Hy’s rule and other empirical methods

9.5 Stochastic process models for liver homeostasis

9.5.1 The Omstcin-Uhlcnbeck process model

9.5.2 OU data analysis

9.5.3 OU model applied to reference limits

9.6 Summary References

10 Neurotoxicity

A. Lawrence Gould

10.1 Introduction

10.2 Multivariate longitudinal observations

10.3 Electroencephalograms (EEGs)

10.3.1 Special considerations

10.3.2 Mixed effect models

10.3.3 Spatial smoothing by incorporating spatial relationships of channels

10.3.4 Explicit adjustment for muscle-induced (non-EEG) artifacts

10.3.5 Potential extensions

10.4 Discussion


11 Safety monitoring Jay Herson

11.1 Introduction

11.2 Planning for safety monitoring

11.3 Safety monitoring-sponsor view (masked, treatment groups pooled)

11.3.1 Frequentist methods for masked or pooled analysis

11.3.2 Likelihood methods for masked or pooled analysis

11.3.3 Bayesian methods for masked or pooled analysis

11.4 Safety monitoring-DMC view (partially or completely unmasked)

11.4.1 DMC data review operations

11.4.2 Types of safety data routinely reviewed

11.4.3 Assay sensitivity

11.4.4 Comparing safety between treatments

11.5 Future challenges in safety monitoring

11.5.1 Adaptive designs

11.5.2 Changes in the setting of clinical trials

11.5.3 New technologies

11.6 Conclusions References

12 Sequential testing for safety evaluation Jie Chen

12.1 Introduction

12.2 Sequential probability ratio test (SPRT)

12.2.1 Wald SPRT basics

12.2.2 SPRT for a single-parameter exponential family

12.2.3 A clinical trial example

12.2.4 Application to monitoring occurrence of adverse events

12.3 Sequential generalized likelihood ratio tests

12.3.1 Sequential GLR tests and stopping boundaries

12.3.2 Extension of sequential GLR tests to multiparameter exponential families

12.3.3 Implementation of sequential GLR tests

12.3.4 Example from Section 12.2.3, continued

12.4 Concluding remarks References

13 Evaluation of post-marketing safety using spontaneous reporting databases Ismati Ahmed, Bernard Begaud and Pascale Tubert-Bitter

13.1 Introduction

13.2 Data structure

13.3 Disproportionality methods

13.3.1 Frequentist methods

13.3.2 Bayesian methods

13.4 Issues and biases

13.4.1 Notoriety bias

13.4.2 Dilution bias

13.4.3 Competition bias

13.5 Method comparisons

13.6 Further refinements

13.6.1 Recent improvements on the detection rule

13.6.2 Bayesian screening approach

13.6.3 Confounding and interactions

13.6.4 Comparison of two signals

13.6.5 An alternative approach References

14 Pharmacovigilance using observational/longitudinal databases and web-based information A. Lawrence Gould

14.1 Introduction

14.2 Methods based on observational databases

14.2.1 Disproportionality analysis with redefinition of report frequency table entries

14.2.2 LGPS and LEOPARD

14.2.3 Self-controlled case series (SCCS)

14.2.4 Case-control approach

14.2.5 Self-controlled cohort

14.2.6 Temporal pattern discovery

14.2.7 Unexpected temporal association rules

14.2.8 Time to onset for vaccine safety

14.3 Web-based pharmacovigilance (infodemiology and infoveillance)

14.4 Discussion References




Дата и время

Страница сгенерирована:

Оригинальная дата и время страницы:

Ссылка на эту страницу: