Statistical Methods for Hospital Monitoring with R

Description

Hospitals monitoring is becoming more complex and is increasing both because staff want their data analysed and because of increasing mandated surveillance. This book provides a suite of functions in R, enabling scientists and data analysts working in infection management and quality improvement departments in hospitals, to analyse their often non-independent data which is frequently in the form of trended, over-dispersed and sometimes auto-correlated time series; this is often difficult to analyse using standard office software.

This book provides much-needed guidance on data analysis using R for the growing number of scientists in hospital departments who are responsible for producing reports, and who may have limited statistical expertise.

This book explores data analysis using R and is aimed at scientists in hospital departments who are responsible for producing reports, and who are involved in improving safety. Professionals working in the healthcare quality and safety community will also find this book of interest

Statistical Methods for Hospital Monitoring with R:

• Provides functions to perform quality improvement and infection management data analysis.
• Explores the characteristics of complex systems, such as self-organisation and emergent behaviour, along with their implications for such activities as root-cause analysis and the Pareto principle that seek few key causes of adverse events.
• Provides a summary of key non-statistical aspects of hospital safety and easy to use functions.
• Provides R scripts in an accompanying web site enabling analyses to be performed by the reader http://www.wiley.com/go/hospital_monitoring
• Covers issues that will be of increasing importance in the future, such as, generalised additive models, and complex systems, networks and power laws.

Table of Contents

Introduction.
Overview and rationale for this book
Motivation for this book
Why R?
Other reading for R
What methods are covered in this book?
Structure of his book
Using R
Entering data
Dates
Dates, important note and chron()
Exporting data
Further notes
Charts introduction
When there is no date column
Control Chart Menu

Chapter 1.

• Proportion
• Confidence interval for
• Significance test for
• Likelihood ratio
• Confidence interval for series of proportions
• Difference between two proportions
• Confidence intervals for
• Significance test for
• More than two proportions
• Summary average of a series of proportions, Newcombe’s method
• Stratified proportion data, differences between rates, Newcombe’s method
• Mantel-Haenszel analysis
• DerSimonian-Laird analysis

Chapter 2.

• Risk adjustment
• Stratification
• Logistic regression
• Discrimination
• Calibration
• Re-calibration
• Displaying and analyzing data from multiple institutions
• Tabulations
• Tables in wide format
• Z-scores
• Multiple confidence intervals
• Funnel plot
• Indirect standardisation
• False discovery
• SMR
• Random effects, shrinkage
• Openbugs Gamma-Poisson Hierarchical Model
• Empirical Bayes
• Bootstrap
• Variation in predicted values
• Complex surgical site infections (low rate data)
• Funnel plot analysis of low rate data
• Shrinkage analysis of low rate data with Openbugs Gamma-Poisson Hierarchical Model
• Appendix 1, further tabulations
• Appendix 2, risk scores for a hospital derived from data with its data removed

Chapter 3.

• CUSUM and related charts for binary data
• Cumulative Observed-Expected (O-E) chart and combined CUSUM and O-E chart
• Cumulative Funnel plot and combined CUSUM and Funnel plot
• Example
• Including Risk Adjustment
• CUSUM chart
• Cumulative observed minus expected (O-E) chart
• Funnel plot
• Discrimination and Calibration of Risk Adjustment
• Shewhart P chart and EWMA chart
• Run-Sum chart
• The EWMA chart
• Expected values
• Spline or generalized additive model (GAM) chart
• Few time periods
• Quarterly data and data without a first date column
• Composite measures
• Additional tabulations
• Underreporting
• New CUSUM and EWMA charts, predicting the current value for low-rate data
• Risk-adjusted Bernoulli CUSUM
• Single observation data and EWMA charts
• Quarterly rates for current rate values in low rate data
• Intervals between uncommon binary adverse events
• Appendix single observation EWMA limits, a proposal

Chapter 4.

• Introduction
• Rate and count data
• Single count or rate
• Confidence Interval for single count or rate
• Significance Test for single count or rate
• Confidence limits for columns of counts and rates
• Two independent rates
• Confidence interval for two independent rates
• Hypothesis test for two independent rates
• Bayesian approach
• Chi-squared and trend tests for count and rate data
• Stratified count and rate data
• Summary rate
• Stratified count and rate data two sets of rates
• Indirect standardisation
• Direct standardisation
• Mantel-Haenszel, Homogeneity and Trend Tests
• Count data variation
• Complex Systems, Networks and Variation

Chapter 5

• Introduction, data, limitations of aggregated count data analysis
• Confidence intervals for the hospitals’ Staphylococcus aureus data
• Funnel plots for the Staphylococcus aureus data
• Tabulations and Z-scores
• Overdispersion, false discovery, very small expected
• Proposal for false discovery modified funnel plot
• Bayesian shrinkage
• Openbugs gamma-Poisson hierarchical model
• Empirical Bayes
• Further tabulations, device-related and MRSA bacteraemias
• Rearranging hospital levels for MRSA
• Bacteraemia Risk Adjustment demonstration

Chapter 6.

• Arranging data by weeks, months, quarters
• Means and variances
• Predictability
• Tabulations
• Denominators
• Shewhart, EWMA and GAM control charts without denominators
• Shewhart/EWMA charts
• Shewhart, EWMA and GAM control charts with denominators
• Overdispersion
• Charts for quarterly data and data without a first date column
• When there are few time periods
• Cross-tabulation in wide format
• Uncommon count data AEs.
• Additional scripts for tabulations and charts
• Intervals between uncommon count data events
• Negative binomial parameters for control charts when denominators vary
• Weighted variance
• Linear approximation (Bissell)
• Comparisons of simple weighted variance and linear approximation

Chapter 7

• Multiple antibiotic-resistant organism (MRO) Prevalence
• Antibiotic Usage
• Spurious proportions
• RIDIT charts
• Numerical data
• Length of stay (LOS) data
• Change point
• Assessing agreement
• Numerical data agreement
• Making Decisions (Decision Analysis)
• Investigating Outbreaks, analysis of stratified data
• Reviewing stratified data analysis
• Outbreak investigation example

Chapter 8.

• Overview of Hospital Quality Improvement
• Five pillars
• Customer
• Practitioner
• Evidence based system
• Manifestations of poor systems
• Malpractice
• Criminal activity
• Substandard performance
• Medical error
• Bundles and checklists
• Discipline and accountability
• Analyzing & implementing evidence-based systems
• Change management
• The Feedback loop
• Implementation of the Quality Improvement Process
• Obtaining data
• Hospital as a network

Author Information

Anthony Morton and Geoffrey Playford, Princess Alexandra Hospital, Brisbane, Australia
Kerrie Mengersen, Science and Engineering Faculty, Queensland University of Technology, Australia
Michael Whitby, Greenslopes Specialist Centre, Queensland, Australia