Statistical methods for healthcare performance monitoring / Alex Bottle and Paul Aylin.

Format:

Book

Author/Creator:

Bottle, Alex, author.

Aylin, Paul, author.

Contributor:

CRC Press.

Murray Galt Motter Memorial Fund.

Series:

Chapman & Hall/CRC biostatistics series

Language:

English

Subjects (All):

Medical care--Evaluation.

Medical care.

Medical statistics.

Medical care--Quality control.

Medical care--Safety measures.

Quality Assurance, Health Care--methods.

Medical Subjects:

Quality Assurance, Health Care--methods.

Physical Description:

1 online resource (xxi, 269 pages) : illustrations.

Place of Publication:

Boca Raton : Taylor & Francis, [2017]

System Details:

text file

Summary:

Healthcare is important to everyone, yet large variations in its quality have been well documented both between and within many countries. With demand and expenditure rising, it's more crucial than ever to know how well the healthcare system and all its components - from staff member to regional network - are performing. This requires data, which inevitably differ in form and quality. It also requires statistical methods, the output of which needs to be presented so that it can be understood by whoever needs it to make decisions. Statistical Methods for Healthcare Performance Monitoring covers measuring quality, types of data, risk adjustment, defining good and bad performance, statistical monitoring, presenting the results to different audiences and evaluating the monitoring system itself. Using examples from around the world, it brings all the issues and perspectives together in a largely non-technical way for clinicians, managers and methodologists. Features Comprehensive coverage of all the elements of performance monitoring including presenting results to different kinds of users, International examples from the United Kingdom, the United States, Australia, Canada, Scandinavia and the World Health Organization, Tables and boxes summarise the main points for many chapters, Clear straightforward language with minimal use of jargon Statistical Methods for Healthcare Performance Monitoring is aimed at statisticians and researchers who need to know how to measure and compare performance, health service regulators, health service managers with responsibilities for monitoring performance, and quality improvement scientists, including those involved in clinical audits. Book jacket.

Contents:

1 Introduction 1

1.1 The Need for Performance Monitoring 1

1.2 Measuring and Monitoring Quality 2

1.3 The Need for This Book 2

1.4 Who Is This Book For and How Should It Be Used? 3

Common Abbreviations Used in the Book 4

Acknowledgment 6

2 Origins and Example of Monitoring system 7

Aims of This Chapter 7

2.1 Origins 7

2.2 Healthcare Scandals 8

2.2.1 Responses to the Scandals 12

2.3 Examples of Monitoring Schemes 14

2.4 Goals of Monitoring 15

2.4.1 Accountability 15

2.4.2 Regulation and Accreditation 16

2.4.3 Patient Choice 19

2.4.4 Openness and Transparency 21

2.4.5 Quality Improvement 21

2.4.6 Prevent Harm and Unsafe Care 22

2.4.7 Professionalism 23

2.4.8 Informed Consent 23

3 Choosing the Unit of Analysis and Reporting 25

Aims of This Chapter 25

3.1 Issues Principally Concerning the Analysis 26

3.1.1 Clustering (*) 26

3.1.2 Episode Treatment Groups 32

3.2 Issues More Relevant to Reporting: Attributing Performance to a Given Unit in a System 34

4 What to Measure: Choosing and Defining Indicators 37

Aims of This Chapter 37

4.1 How Can We Define Quality? 38

4.2 Common Indicator Taxonomies 38

4.3 Particular Challenges of Measuring Patient Safety 42

4.4 Particular Challenges of Multimorbidity 45

4.5 Measuring the Health of the Population and Quality of the Whole Healthcare System 47

4.5.1 The WHO Annual World Health Statistics Report 50

4.6 Efficiency and Value 53

4.6.1 Data Envelopment Analysis and Stochastic Frontier Analysis (*) 57

4.7 Features of an Ideal Indicator 59

4.8 Steps in Construction and Common Issues in Definition 59

4.9 Validation of Indicators 62

4.10 Some Strategies for Choosing among Candidates 63

4.11 Time to Go: When to Withdraw Indicators 64

4.12 Conclusion 65

5 Sources of Data 67

Aims of This Chapter 67

5.1 Plow to Assess Data Quality 67

5.2 Administrative Data 69

5.2.1 Coding Systems for Administrative Data 71

5.2.2 Use of Administrative Databases to Flag Patient Safety Events 74

5.3 Clinical Registry Data 75

5.4 Accuracy of Administrative and Clinical Databases Compared 77

5.5 Incident Reports and Other Ways to Capture Safety Events 84

5.6 Surveys 87

5.7 Other Sources 89

5.8 Other Issues Concerning Data Sources 90

5.9 Conclusion 91

6 Risk-Adjustment Principles and Methods 93

Aims of This Chapter 93

6.1 Risk Adjustment and Risk Prediction 94

6.2 When and Why Should We Adjust for Risk? 95

6.3 Alternatives to Risk Adjustment 96

6.4 What Factors Should We Adjust For? 96

6.4.1 Factors Not under the Control of the Provider 96

6.4.2 Proxies Such as Age and Socioeconomic Status 98

6.4.3 Comorbidity 98

6.4.4 Disease Severity 100

6.5 Selecting an Initial Set of Candidate Variables 101

6.6 Dealing with Missing and Extreme Values 102

6.7 Timing of the Risk Factor Measurement 104

6.8 Building the Model 108

6.8.1 Choosing the Final Set of Variables from the Initial Set of Candidates 108

6.8.2 Decide How Each Variable Should Be Entered into the Model 111

6.8.3 Decide on the Statistical Method for Modelling (*) 111

6.8.4 Assess the Fit of the Model (*) 114

6.8.4.1 Adjusted R² 115

6.8.4.2 Area under the Receiver Operating Characteristic Curve: c Statistic 115

6.8.4.3 The Hosmer-Lemeshow Statistic for Calibration 116

6.8.5 Which Is More Important, Discrimination or Calibration? 117

6.8.6 What Can Be Done If the Model Fit or Performance Is Unacceptable? 117

6.8.7 Convert Regression Coefficients into a Risk Score If Desired 118

7 Output the Observed and Model-Predicted Outcomes (*) 121

Aims of This Chapter 121

7.1 Ratios versus Differences 122

7.2 Deriving SMRs from Standardisation and Logistic Regression 123

7.3 Other Fixed Effects Approaches to Generate an SMR 126

7.4 Random Effects-Based SMRs (*) 126

7.5 Marginal versus Multilevel Models (*) 129

7.6 Which Is the "Best" Modelling Approach Overall? (*) 130

7.7 Further Reading on Producing Risk-Adjusted Outcomes by Unit 134

8 Composite Measures 135

Aims of This Chapter 135

8.1 Some Examples 136

8.2 Steps in the Construction 137

8.2.1 Specify the Scope and Purpose 138

8.2.2 Choose the Unit 138

8.2.3 Select the Data and Deal with Missing Values 138

8.2.4 Choose the Indicators and Run Descriptive Analyses 138

8.2.5 Normalise the Metrics 140

8.2.6 Assign Weights and Aggregate the Component Indicators 140

8.2.7 Run Sensitivity Analyses 144

8.2.8 Present the Results 145

8.3 Some Real Examples 146

8.3.1 AHRQ's Patient Safety Indicator Composite 146

8.3.2 Leapfrog Group Patient Safety Composite 147

8.4 Pros and Cons of Composites 148

8.5 Alternatives to the Use of Composites 149

9 Setting Performance Thresholds and Defining Outliers 151

Aims of This Chapter 151

9.1 Defining Acceptable Performance 152

9.1.1 Targets 152

9.1.2 Historical Benchmarks 153

9.1.3 Referring to Inter-Unit Variation 153

9.2 Bayesian Methods for Comparing Providers 155

9.3 Statistical Process Control and Funnel Plots 157

9.4 Multiple Testing (*) 163

9.4.1 Multivariate Statistical Process Control Methods (*) 165

9.4.2 Further Reading on SPC 166

9.5 Ways of Assessing Variation between Units 166

9.6 How Much Variation Is "Acceptable"? 167

9.7 Impact on Outlier Status of Using Fixed versus Random Effects to Derive SMRs 171

9.8 How Reliably Can We Detect Poor Performance? 172

9.9 Some Resources for Quality Improvement Methods 174

10 Making Comparisons across National Borders 177

Aims of This Chapter 177

10.1 Examples of Multinational Patient-Level Databases 178

10.2 Challenges 180

10.2.1 Worked Example of Combining Administrative Databases from Multiple Countries: Stroke Mortality 181

10.2.2 Clustering within Countries 184

10.2.3 Countries with Unusual Data or Apparent Performance 184

10.3 Interpreting Apparent Differences in Performance between Countries 185

10.4 Conclusion 186

11 Presenting the Results to Stakeholders 189

Aims of This Chapter 189

11.1 The Main Ways of Presenting Comparative Performance Data 189

11.2 Effect on Behaviour of the Choice of Format When Providing Performance Data 192

11.3 The Importance of the Method of Presentation 195

11.3.1 Presenting Performance Data to Managers and Clinicians 195

11.3.2 Presenting Results to the Public 197

11.4 Examples of Giving Performance Information to Units 198

11.5 Examples of Giving Performance Information to the Public 202

11.6 Metadata 206

12 Evaluating the Monitoring System 207

Aims of This Chapter 207

12.1 Study Design and Statistical Approaches to Evaluating a Monitoring System 208

12.1.1 Interrupted Time-Series Design and Analysis (*) 209

12.1.2 Adjusting for Confounding (*) 212

12.1.3 Difference-in-Differences 214

12.1.4 Instrumental Variable Analysis 216

12.1.5 Regression Discontinuity Designs 217

12.2 Economic Evaluation Methods 220

13 Concluding Thoughts 225

13.1 Simple versus Complex 225

13.2 Specific versus Genera) 226

13.3 The Future 227.

Notes:

"A CRC title, part of the Taylor & Francis imprint, a member of the Taylor & Francis Group, the academic division of T&F Informa plc."

Includes bibliographical references and index.

Electronic reproduction. Boca Raton, FL Available via World Wide Web.

Description based on print version record.

Local Notes:

Acquired for the Penn Libraries with assistance from the Murray Galt Motter Memorial Fund.

Other Format:

Electronic version: Bottle, Alex. Statistical methods for healthcare performance monitoring.

ISBN:

9781315372778

1315372770

Publisher Number:

99969300713

Access Restriction:

Restricted for use by site license.