• English
  • Español

Diagnostic test accuracy reviews 5: Advanced meta-analysis: dealing with heterogeneity and test comparisons.

Topic category Diagnostic test accuracy review methods
Date and Location
Date: 
Friday 21 October 2011 - 16:00 - 17:30
Location: 
Methods Group
Methods Group: 
Screening and Diagnostic Tests Methods Group
Contact person
Contact person: 
Petra Macaskill (Contact this person)
Facilitators
First nameLast nameAffiliation and Country
First name: 
Petra
Last name: 
Macaskill
Affiliation and Country: 
University of Sydney, Australia
Target audience
Target audience: 
Review authors or statisticians intending to undertake a DTA meta-analysis.
Is your workshop restricted to a specific audience or open to all Colloquium participants?: 
Open
Level of knowledge required: 
Intermediate
Type of workshop
Type of workshop: 
Training
Abstract text
Abstract: 
Objective:
The Cochrane Diagnostic Reviews Methodology Working Group has developed a series of workshops addressing guidelines as formulated in the Handbook for Diagnostic Test Accuracy reviews. This workshop is designed to:
(1) explain the recommended statistical models used for diagnostic test accuracy meta-analysis and the concepts underlying these methods;
(2) illustrate the methods and their interpretation using examples;
(3) illustrate the use of RevMan 5 to display results.

Description:
This workshop will explain advanced statistical methods for the meta-analysis of studies of diagnostic test accuracy that report estimates of sensitivity and specificity. We will cover the recommended, commonly used hierarchical models (and the relationship between them):
(i) the bivariate model, which focuses on the estimation of a summary estimate of sensitivity and specificity; and
(ii) the Hierarchical Summary ROC model of Rutter and Gatsonis, that focuses on the estimation of a summary ROC curve.
Both methods will be illustrated by means of examples, and the choice of method will be discussed. The use of these models for investigating sources of heterogeneity through the inclusion of study level covariates will be described and discussed. The application of this approach to comparing the performance of alternative tests will also be covered.