STARD-BLCM: Standards for the Reporting of Diagnostic accuracy studies that use Bayesian Latent Class Models

摘要: The Standards for the Reporting of Diagnostic Accuracy (STARD) statement, which was recently updated to STARD2015 developed encourage complete and transparent reporting test accuracy studies. Although STARD principles apply broadly, checklist is limited studies designed evaluate tests when disease status determined from a perfect reference procedure or an imperfect one with known measures accuracy. However, standard does not always exist, especially in case infectious diseases long latent period. In such cases, valid alternative classical evaluation involves use class models that do require priori knowledge status. Latent have been successfully implemented Bayesian framework over 20 years. objective this work identify items modification develop modified version analysis estimate diagnostic absence standard. Examples elaborations each are provided. new guidelines, termed STARD-BLCM (Standards Class Models), will facilitate improved quality on design, conduct results models.