Evaluating Medical Tests Objective and Quantitative Guidelines,9780803946125

Evaluating Medical Tests Objective and Quantitative Guidelines

by
ISBN13: 9780803946125
ISBN10: 0803946120
Format: Paperback
Pub. Date: 1992-03-23
Publisher(s): Sage Publications
List Price: $94.95

Buy New

Usually Ships in 8 - 10 Business Days.
$94.86
Add to Cart

Rent Textbook

Select for Price
Add to Cart
There was a problem. Please try again later.

Used Textbook

We're Sorry
Sold Out

eTextbook

We're Sorry
Not Available

Buy from our Marketplace starting at $53.38

How Marketplace Works:

  • This item is offered by an independent seller and not shipped from our warehouse
  • Item details like edition and cover design may differ from our description; see seller's comments before ordering.
  • Sellers much confirm and ship within two business days; otherwise, the order will be cancelled and refunded.
  • Marketplace purchases cannot be returned to eCampus.com. Contact the seller directly for inquiries; if no response within two days, contact customer service.
  • Additional shipping costs apply to Marketplace purchases. Review shipping costs at checkout.

Summary

In this book, Kraemer presents a systematic, objective methodology by which to determine the effectiveness of medical tests. She shows clearly and concisely how to define statistical terms and approaches consistently from study to study, how to stipulate statistical assumptions underlying various approaches, how to check for empirical validity and how to judge the robustness of statistical outcomes, resulting in models that integrate many different approaches and extend the strengths of each.

Table of Contents

List of Statistical Notations: Commonly Used Names and Symbols
x
Foreword xi
A. John Rush
Preface xv
Acknowledgments xxi
Introduction
1(4)
Disorder and Diagnosis
5(13)
The Disorder
5(1)
The Diagnosis of the Disorder
6(2)
Diagnostic and Prognostic Tests
8(1)
The Basic Model
9(5)
The Prevalence and Reproducibility of the Diagnosis
14(1)
High- and Low-Risk Populations
15(1)
Pre- and Posttest Risk, Prevalence, and Incidence: Confusing Terms
16(1)
Summary
17(1)
Definition: Test Protocol, Response, Referent
18(5)
The Basic Model
20(1)
Summary
21(2)
Families of Test Referents
23(3)
Definitions: Base and Family
23(2)
A Special Family: Multiple Discriminant Rules
25(1)
Summary
25(1)
Population and Sampling
26(37)
Outcomes: True and False Positives and Negatives
26(2)
Blind Evaluation
28(1)
The Basic Model
29(4)
Descriptors of Outcomes: Sensitivity, Specificity, Predictive Values, and Efficiency
33(1)
Naturalistic Sampling
34(6)
The Two-by-Two Chi-Square Test
40(4)
Retrospective Sampling
44(5)
The Problem of Dropouts
49(4)
Prospective Sampling
53(4)
The Sampling Unit
57(1)
Pseudo-Retrospective Sampling: An Invalid Approach
58(3)
Summary
61(2)
Sensitivity and Specificity: The Signal Detection Approach
63(33)
Problems with Sensitivity and Specificity
63(2)
The Basic Model
65(6)
The Receiver Operating Characteristic Curve (Test ROC)
71(4)
The Quality Receiver Operating Characteristic Curve (QROC)
75(2)
All Q-Level Tests
77(5)
What Is a Good Test? The Diagnosis ROC, QROC
82(4)
What Is the Ideal Test? The Disorder ROC, QROC
86(5)
Thc Myth of the Constancy of Sensitivity and Specificity
91(3)
Summary
94(2)
Predictive Values: The Bayesian Approach, Risk Ratios, and Odds Ratio
96(18)
Problems with Predictive Values
96(2)
The Basic Model
98(2)
A Geometric Approach: The Test QROC
100(3)
Risk Ratios, Odds Ratio, and the Test QROC
103(10)
Summary
113(1)
Efficiency: Choosing Clinically Optimal Tests
114(17)
The Problem with Efficiency
114(1)
The Basic Model
115(4)
Consideration of Medical Consequences of Errors: The Weighted Kappa Coefficient
119(4)
A Geometric Approach: The Test QROC
123(6)
Summary
129(2)
Taking Test Costs into Account: Costworthy Tests
131(24)
Introduction
131(4)
The Basic Model
135(10)
Derivation of the Quality Index k(r,t)
135(3)
The Benefit Threshold of a Medical Test
138(2)
Full Evaluation of a Test Family
140(5)
A Geometric Approach: The QCROC
145(4)
The Costs and Risks of Too Much Information
149(2)
Informed Consent for Medical Tests
151(2)
Summary
153(2)
Basic Issues in Using Multiple Tests
155(10)
Introduction
155(1)
Tests in Parallel or Tests in Sequence
156(5)
The Quality of Combined Tests
161(2)
When Should a Test Be Repeated?
163(1)
Should a Test Be Done Blind to Previous Test Results?
163(1)
Summary
164(1)
Evaluating Batteries of Medical Tests: Optimal Sequences
165(34)
Introduction
165(1)
The Basic Model
166(4)
Compiling the Raw Data Base
170(6)
Compiling the Working Data Base
176(3)
Selection of the Optimal First Test and Reiteration
179(1)
Increasing the Yield
180(5)
Testing the Quality Index Using a Statistical Jackknife
185(2)
Completing the Search for the Optimal Battery Structure
187(1)
The Final Recommendation for Battery Structure
188(5)
An Alternative Strategy
193(1)
Summary
194(5)
Evaluating Batteries of Medical Tests: Optimal Scores
199(29)
Introduction
199(5)
The Basic Model
204(5)
Multiple Linear Discrimination
209(7)
Logistic Regression Analysis
216(6)
Some Practical Considerations in Choosing and Using Models
222(5)
Summary
227(1)
Evaluating Batteries of Prognostic Tests with Variable Follow up Times
228(38)
Introduction
228(3)
The Basic Model
231(3)
Ignoring the Problem of Variable Follow-up: A Possibly Invalid Approach
234(1)
Counting Time and Not Patients: Another Possibly Invalid Procedure
234(5)
Tailoring the Data to Fit the Solution: An Invalid and Inefficient Approach
239(2)
Estimating Survival Curves with Variable Follow-up Times: The Kaplan-Meier Method
241(6)
Some General Observations on the Choice of Follow-up Time and Its Impact on Test Evaluation
247(3)
Evaluating a Family of Prognostic Tests with a Variable Follow-up Time
250(6)
An Alternative? Randomized Clinical Trials for the Evaluation of Screening Programs (Test + Intervention) for Prevention
256(3)
Evaluating a Battery of Prognostic Tests with Variable Follow-up Periods: Sequential Structuring
259(1)
Evaluating a Battery of Prognostic Tests Using Variable Follow-up: Scoring a Battery with the Proportional Hazards Model
259(4)
Summary
263(3)
Evaluation of Medical Tests: The Past, Present, and Future
266(20)
Introduction: The Past and the Present
266(6)
The Future: Unsolved Problems
272(4)
Problem: Evaluation of Monitoring Tests
272(1)
Problem: Multicategory Responses
273(1)
Problem: Stopping Rules
274(1)
Other Pro6lems
275(1)
The Present: An Overall Summary
276(10)
What Is the Disorder? What Diagnosis Is to Be Used? Is the Diagnosis Clinically Valid and Reliable?
276(1)
In What Clinical Population or Populations Is the Test Proposed for Use? How Can the Sampling Be Done so as to Obtain a Representative Sample from That Population or Populations?
277(1)
If the Test Is to Be Evaluated as a Prognostic Test, Will the Follow-up Be Fixed or Variable? If the Follow-up Is to Be Fixed, Fixed at What Time?
277(1)
Will Sampling Be Naturalistic, Retrospective, or Prospective?
277(1)
How Large a Sample Is Needed?
278(1)
How Are Dropouts and Missing Responses Avoided?
278(1)
What Are the Clinical Benefits in this Situation?
279(1)
What Are the Tests under Evaluation--Their Protocols, Responses, and Referents? What Are the Test Costs? If This is a Single Test (a Single Fixed Cost for All the Responses) or Is This to Be Considered a Battery of Tests (Separable Costs)?
279(1)
How Are the Blinding of the Diagnosis and Test Results Assured? If There Are Multiple Tests in a Battery under Evaluation, Are These Blinded to Each Other?
280(1)
Is There any Internal or External Standard Provided for the Performance of an Excellent Test?
280(1)
Was the Data Base Properly Compiled and Thoroughly Checked for Errors?
281(1)
For Each Single Test under Evaluation, for Each Test in the Battery Under Evaluation, and for Each Population Under Evaluation, Have the Descriptive Statistics Been Properly Computed?
282(1)
What Is the Quality of Each Single Test Under Evaluation, and for Each Population Under Evaluation (and in an Evaluation of a Prognostic Test with Variable Follow-up Time, for Each Possible Value of Follow-up Time)?
282(2)
Has the Optimal Referent for a Test, or the Optimal First Test in a Battery of Tests Been Appropriately Selected?
284(1)
If There Is a Battery of Tests Under Consideration, Has the Battery Been Appropriately Evaluated?
285(1)
References 286(5)
Index 291(4)
About the Author 295

An electronic version of this book is available through VitalSource.

This book is viewable on PC, Mac, iPhone, iPad, iPod Touch, and most smartphones.

By purchasing, you will be able to view this book online, as well as download it, for the chosen number of days.

Digital License

You are licensing a digital product for a set duration. Durations are set forth in the product description, with "Lifetime" typically meaning five (5) years of online access and permanent download to a supported device. All licenses are non-transferable.

More details can be found here.

A downloadable version of this book is available through the eCampus Reader or compatible Adobe readers.

Applications are available on iOS, Android, PC, Mac, and Windows Mobile platforms.

Please view the compatibility matrix prior to purchase.