Muutke küpsiste eelistusi

Bayesian Biostatistics and Diagnostic Medicine [Kõva köide]

(Medical Lake, Washington, USA)
  • Formaat: Hardback, 212 pages, kõrgus x laius: 234x156 mm, kaal: 560 g, 89 Tables, black and white; 1 Halftones, black and white; 26 Illustrations, black and white
  • Ilmumisaeg: 12-Jul-2007
  • Kirjastus: Chapman & Hall/CRC
  • ISBN-10: 1584887672
  • ISBN-13: 9781584887676
Teised raamatud teemal:
Bayesian Biostatistics and Diagnostic MedicineSuurem pilt
  • Formaat: Hardback, 212 pages, kõrgus x laius: 234x156 mm, kaal: 560 g, 89 Tables, black and white; 1 Halftones, black and white; 26 Illustrations, black and white
  • Ilmumisaeg: 12-Jul-2007
  • Kirjastus: Chapman & Hall/CRC
  • ISBN-10: 1584887672
  • ISBN-13: 9781584887676
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9781584887676.html
Märksõnad:
There are numerous advantages to using Bayesian methods in diagnostic medicine, which is why they are employed more and more today in clinical studies. Exploring Bayesian statistics at an introductory level, Bayesian Biostatistics and Diagnostic Medicine illustrates how to apply these methods to solve important problems in medicine and biology.

After focusing on the wide range of areas where diagnostic medicine is used, the book introduces Bayesian statistics and the estimation of accuracy by sensitivity, specificity, and positive and negative predictive values for ordinal and continuous diagnostic measurements. The author then discusses patient covariate information and the statistical methods for estimating the agreement among observers. The book also explains the protocol review process for cancer clinical trials, how tumor responses are categorized, how to use WHO and RECIST criteria, and how Bayesian sequential methods are employed to monitor trials and estimate sample sizes.

With many tables and figures, this book enables readers to conduct a Bayesian analysis for a large variety of interesting and practical biomedical problems.

Arvustused

It is interesting to read this book on Bayesian biostatistics and diagnostic medicine. this book has several unique features. an excellent introductory textbook on Bayesian methods and their application in diagnostic medicine. Non-experienced statisticians may also find that the systematic overview of the classification and purposes of the three phases in clinical trials and the basic Bayesian theory are useful references and would benefit from the program codes, particularly WinBUGS codes. Pharmaceutical Statistics, 2011, 10

the inclusion of plenty of real examples plus details of the necessary BUGS code was a very positive attribute. Some of the data sets are available for the reader to analyse and this would further enhance understanding. Overall, it is certainly a useful read or reference book for a practicing statistician with a good baseline theoretical knowledge who would like to expand their interest in this specific field of application. A. Wade, University College London, Journal of the Royal Statistical Society, Series A, 2010

This book is quite a good one for a statistician that is (or training to be) a statistical consultant to a cancer center department of diagnostic imaging . If you are such a person, this book should be in your library. David Booth, Technometrics, August 2010

Drawing on his collaborative experiences with medical researchers and his long-standing interests in Bayesian methods, the author of this book shows how the Bayesian approach can be used to advantage when medical diagnosis is based on data with uncertainty. a general strength of the book is careful discussion of study designs and protocols, which is a bonus relative to many biostatistical books written from a more narrow theory and methods perspective. A real strength is the strong integration between models and concepts on the one hand, and real studies on the other hand. The inclusion of WinBUGS code is also a plus. this book is highly recommended for anyone whose interests touch on the statistical side of diagnostic medicine. Biometrics, March 2009 It is interesting to read this book on Bayesian biostatistics and diagnostic medicine. this book has several unique features. an excellent introductory textbook on Bayesian methods and their application in diagnostic medicine. Non-experienced statisticians may also find that the systematic overview of the classification and purposes of the three phases in clinical trials and the basic Bayesian theory are useful references and would benefit from the program codes, particularly WinBUGS codes. Pharmaceutical Statistics, 2011, 10

the inclusion of plenty of real examples plus details of the necessary BUGS code was a very positive attribute. Some of the data sets are available for the reader to analyse and this would further enhance understanding. Overall, it is certainly a useful read or reference book for a practicing statistician with a good baseline theoretical knowledge who would like to expand their interest in this specific field of application. A. Wade, University College London, Journal of the Royal Statistical Society, Series A, 2010

This book is quite a good one for a statistician that is (or training to be) a statistical consultant to a cancer center department of diagnostic imaging . If you are such a person, this book should be in your library. David Booth, Technometrics, August 2010

Drawing on his collaborative experiences with medical researchers and his long-standing interests in Bayesian methods, the author of this book shows how the Bayesian approach can be used to advantage when medical diagnosis is based on data with uncertainty. a general strength of the book is careful discussion of study designs and protocols, which is a bonus relative to many biostatistical books written from a more narrow theory and methods perspective. A real strength is the strong integration between models and concepts on the one hand, and real studies on the other hand. The inclusion of WinBUGS code is also a plus. this book is highly recommended for anyone whose interests touch on the statistical side of diagnostic medicine. Biometrics, March 2009

Preface ix
Acknowledgments xi
Author xiii
1 Introduction 1
1.1 Introduction
1
1.2 Statistical Methods in Diagnostic Medicine
1
1.3 Preview of Book
2
1.4 Datasets for the Book
4
1.5 Software
4
References
5
2 Diagnostic Medicine 7
2.1 Introduction
7
2.2 Imaging Modalities
7
2.3 Activities in Diagnostic Imaging
11
2.4 Accuracy and Agreement
12
2.5 Developmental Trials for Imaging
14
2.6 Protocol Review and Clinical Trials
15
2.6.1 The Protocol
16
2.6.2 Phase I, II, and III Clinical Designs
16
2.7 The Literature
18
References
18
3 Other Diagnostic Procedures 21
3.1 Introduction
21
3.2 Sentinel Lymph Node Biopsy for Melanoma
21
3.3 Tumor Depth to Diagnose Metastatic Melanoma
22
3.4 Biopsy for Nonsmall Cell Lung Cancer
23
3.5 Coronary Artery Disease
24
References
24
4 Bayesian Statistics 27
4.1 Introduction
27
4.2 Bayes Theorem
28
4.3 Prior Information
29
4.4 Posterior Information
33
4.5 Inference
36
4.5.1 Introduction
36
4.5.2 Estimation
36
4.5.3 Testing Hypotheses
38
4.5.3.1 Introduction
38
4.5.3.2 Binomial Example of Testing
39
4.5.3.3 Comparing Two Binomial Populations
40
4.5.3.4 Sharp Null Hypothesis for the Normal Mean
41
4.6 Sample Size
41
4.6.1 Introduction
41
4.6.2 A One-Sample Binomial for Response
42
4.6.3 A One-Sample Binomial with Prior Information
44
4.6.4 Comparing Two Binomial Populations
45
4.7 Computing
45
4.7.1 Introduction
45
4.7.2 Direct Methods of Computation
46
4.7.3 Gibbs Sampling
49
4.7.3.1 Introduction
49
4.7.3.2 Common Mean of Normal Populations
50
4.7.3.3 MCMC Sampling with WinBUGS®
53
4.8 Exercises
56
References
57
5 Bayesian Methods for Diagnostic Accuracy 59
5.1 Introduction
59
5.2 Study Design
60
5.2.1 The Protocol
60
5.2.2 Objectives
60
5.2.3 Background
61
5.2.4 Patient and Reader Selection
61
5.2.5 Study Plan
62
5.2.6 Number of Patients
63
5.2.7 Statistical Design and Analysis
63
5.2.8 References
64
5.3 Bayesian Methods for Test Accuracy: Binary and Ordinal Data
65
5.3.1 Introduction
65
5.3.2 Classification Probabilities
65
5.3.3 Predictive Values
68
5.3.4 Diagnostic Likelihood Ratios
69
5.3.5 ROC Curve
69
5.4 Bayesian Methods for Test Accuracy: Quantitative Variables
73
5.4.1 Introduction
73
5.4.2 The Spokane Heart Study
73
5.4.3 ROC Area
74
5.4.4 Definition of the ROC Curve
77
5.4.5 Choice of Optimal Threshold Value
78
5.5 Clustered Data: Detection and Localization
79
5.5.1 Introduction
79
5.5.2 Bayesian ROC Curve for Clustered Information
80
5.5.3 Clustered Data in Mammography
82
5.6 Comparing Accuracy between Modalities
84
5.7 Sample Size Determination
87
5.7.1 Introduction
87
5.7.2 Discrete Diagnostic Scores
88
5.7.2.1 Binary Tests
88
5.7.2.2 Multinomial Outcomes
91
5.7.3 Sample Sizes: Continuous Diagnostic Scores
92
5.7.3.1 One ROC Curve
92
5.7.3.2 Two ROC Curves
95
5.8 Exercises
97
References
99
6 Regression and Test Accuracy 101
6.1 Introduction
101
6.2 Audiology Study
102
6.2.1 Introduction
102
6.2.2 Log Link Function
102
6.2.3 Logistic Link
103
6.2.4 Diagnostic Likelihood Ratio
105
6.3 ROC Area and Patient Covariates
107
6.3.1 Introduction
107
6.3.2 ROC Curve as Response to Therapy
108
6.3.3 Diagnosing Prostate Cancer
110
6.4 Exercises
111
References
111
7 Agreement 113
7.1 Introduction
113
7.2 Agreement for Discrete Ratings
114
7.2.1 Binary Scores
114
7.2.2 Other Indices of Agreement
116
7.2.3 A Bayesian Version of McNemar
117
7.2.4 Comparing Two Kappa Parameters
117
7.2.5 Kappa and Stratification
119
7.2.6 Multiple Categories and Two Readers
120
7.2.7 Multiple Categories
122
7.2.8 Agreement and Covariate Information
123
7.3 Agreement for a Continuous Response
126
7.3.1 Introduction
126
7.3.2 Intra-Class Correlation Coefficient
127
7.3.2.1 One-Way Random Model
127
7.3.2.2 Two-Way Random Model
131
7.3.3 Regression and Agreement
132
7.4 Combining Reader Information
134
7.5 Exercises
136
References
139
8 Diagnostic Imaging and Clinical Trials 141
8.1 Introduction
141
8.2 Clinical Trials
142
8.2.1 Introduction
142
8.2.2 Phase I Designs
142
8.2.3 Phase II Trials
143
8.2.4 Phase III Trials
145
8.3 Protocol
145
8.4 Guidelines for Tumor Response
146
8.5 Bayesian Sequential Stopping Rules
148
8.6 Software for Clinical Trials
152
8.6.1 CRM Simulator for Phase I Trials
153
8.6.2 Multc Lean for Phase II Trials
153
8.7 Examples
154
8.7.1 Phase I Trial for Renal Cell Carcinoma
154
8.7.2 An Ideal Phase II Trial
156
8.7.3 Phase II Trial for Advanced Melanoma
158
8.8 Exercises
162
References
163
9 Other Topics 165
9.1 Introduction
165
9.2 Imperfect Diagnostic Test Procedures
166
9.2.1 Extreme Verification Bias
166
9.2.2 Verification Bias
170
9.2.3 Estimating Test Accuracy with No Gold Standard
173
9.3 Test Accuracy and Survival Analysis
178
9.4 ROC Curves with a Non-Binary Gold Standard
180
9.5 Periodic Screening in Cancer
182
9.5.1 Inference for Sensitivity and Transition Probability
182
9.5.2 Bayesian Inference for Lead-Time
186
9.6 Decision Theory and Diagnostic Accuracy
189
9.7 Exercises
192
References 193
Index 195


Lyle D. Broemeling, MEDICAL LAKE WA, U.S.A