Understanding, appraising, interpreting and summarising evidence regarding diagnostic tests
This is the second in a series of two workshops presented by Cochrane Netherlands and Cochrane Methods Screening and Diagnostic Tests. This one-day hands-on workshop will address meta-analysis of diagnostic test accuracy. This type of meta-analysis requires complex statistical methods and special software packages, such as R, Stata or SAS. Participants will learn the main aspects of meta-analysis of diagnostic studies. Meta-analysis is directed at combining sensitivity and specificity of primary diagnostic studies. Because those parameters are not independent of each other, they must be analysed jointly by the use of advanced statistical models. We will address both hierarchical and bivariate models for diagnostic meta-analysis by the use of R software. In addition, we will address how to explore heterogeneity and to perform subgroup analyses. This workshop is intended for researchers (statisticians and epidemiologists), but is also very useful for healthcare workers, clinicians, guideline developers and policy makers who wish to perform diagnostic meta-analyses.