CADTH (Free!) Virtual Workshop 2021
This workshop was first scheduled to take place at the CADTH Symposium in 2020, but was cancelled due to the Covid-19 pandemic. It is now being offered for free by CADTH as part of a virtual series. Click here for registration details
The goal of this interactive workshop is to provide participants with an overview of bivariate meta-analysis methods for diagnostic accuracy. We will first introduce the traditional model where the reference test is perfect. We will then cover latent class meta-analysis for the situation when the reference test is not perfect. Lectures will be followed by tutorials of the following Shiny app for a hands-on experience:
- Bayesian Diagnostic Test Accuracy Meta-Analysis (from https://bayesdta.shinyapps.io/meta-analysis/)
Session 1: Bivariate Meta-analyses (9:00 – 10:30am)
Session 2: Latent class meta-Analysis (10:30am-noon)
Kohli M, Schiller I, Dendukuri N, Dheda K, Denkinger CM, Schumacher SG, Steingart KR. Xpert(®) MTB/RIF assay for extrapulmonary tuberculosis and rifampicin resistance. Cochrane Database Syst Rev. 2018 Aug 27;8:CD012768
Xie X, Sinclair A, Dendukuri N. Evaluating the accuracy and economic value of a new test in the absence of a perfect reference test. Res Synth Methods. 2017 Sep;8(3):321-332.
Comparison of Saliva and Nasopharyngeal Swab Nucleic Acid Amplification Testing for Detection of SARS-CoV-2: A Systematic Review and Meta-analysis. JAMA Intern Med. 2021 Jan 15:e208876.
Contents OVERVIEW MOTIVATING EXAMPLE AND DATA THE MODEL INITIAL VALUES COMPILING AND RUNNING THE MODEL MONITORING CONVERGENCE SUMMARY STATISTICS SROC plot SCRIPT...Read more
Want to use a Bayesian approach to plan your study for comparing proportions? The R package SampleSizeProportions implements sample size calculations based on...Read more