Evaluating Screening Tests for Chlamydia trachomatis in the Absence of a Gold Standard Test

• Activity Number: 253
• Type: Contributed
• Date/Time: Monday, August 2, 2010 : 2:00 PM to 3:50 PM
• Sponsor: Section on Statistics in Epidemiology
• Author(s): Alula Hadgu*+ and Liangliang Wang and Nandini Dendukuri
• Companies: CDC and The University of British Columbia and McGill University
• Keywords: sensitivity ; specificity ; biased estimation ; latent class models ; multiple latent variable model

Abstract

Evaluation of new diagnostic tests in the absence of a gold-standard test is complicated. Two approaches that have been used for this purpose include: i) the patient infected status algorithm and ii) the composite reference standard approach. Using simulations and algebra we illustrate the drawbacks of these ad-hoc approaches. In addition, we describe the application of a novel multiple latent variable model which recognizes that tests based on different biological mechanisms in fact measure different latent variables. These in turn may be proxy measures of the latent disease status. We apply this model to evaluate screening tests for detecting Chlamydia trachomatis.