Audience: Of interest to HTA producers.
What you’ll learn: Knowledge of methods needed to carry out a meta-analysis of diagnostic test accuracy, including the methods needed to correct for imperfect reference standard.
- Dr. Nandini Dendukuri, McGill University
- Ian Schiller, McGill University Health Centre‒Research Institute
Abstract: The goal of this workshop is to provide participants with an overview of models used for diagnostic test accuracy (DTA) meta-analyses. Bivariate meta-analysis models are necessary as two parameters are involved — sensitivity and specificity. We will also show how these models can be extended to correct for the bias that arises when the reference test is not perfect. Examples from a Cochrane review will be used. R Shiny apps which implement the models will be introduced.