Over the past few months, there has been a need for rapid development of diagnostic tests that will efficiently detect COVID-19 infection. Diagnostic test studies evaluating the performance of a diagnostic test are still lacking, in particular when there is no perfect gold standard. To the best of our knowledge, we present the first study using Bayesian latent class models for the evaluation of COVID-19 diagnostics. This study was undertaken within the farmework of a cost action aiming to develop and expand the applicatzion of BLCM (https://harmony-net.eu/).
Access preprint here