Statistics and Biostatistics seminar series
Areti Veroniki
University of Toronto/St. Michael’s Hospital, Unity Health Toronto
Room: M3 3127
Network meta-analysis of diagnostic test accuracy studies
Diagnostic test accuracy (DTA) meta-analyses typically focus on a single index test. However, there may be several index tests available for a target condition, where their comparative accuracy is important for decision-making.
Comparative evaluation of these tests is critical for evidence-based decision-making, and various analytical frameworks have been developed to address this need. The transition to network meta-analysis (NMA) allows for a more integrated and comprehensive evaluation of multiple diagnostic tests simultaneously in a single model. A growing number of studies and systematic reviews are now conducting comparisons of the accuracy of various index tests, aiming to identify the best performing test(s) for patient care.
Several NMA models have been developed over the past few years to evaluate the comparative accuracy of multiple tests. This presentation will briefly describe recently developed models to perform a DTA-NMA, explain the basic principles and assumptions of a DTA-NMA, and explain why diagnostic tests cannot be evaluated in NMA methods of interventions.