Evaluation of the Accuracy of Diagnostic Tests using Latent Class Analysis

Janeiro 2007

The latent class model (LCM) is a common alternative to the classical approach (CA) to evaluate the accuracy of diagnostic tests in the absence of a true gold standard. LCM has become popular to simultaneously estimate and compare accuracy measures (like sensitivities and specificities) of all the diagnostic tests as well as the prevalence of a disease or infection in the absence of a gold standard. In this paper, we propose a latent class model with constraints to compare the accuracy of some diagnostic tests for canine leishmania infection. The mathematical constraints considered in the LCM take into account information about parasitological tests, namely specificity equal to 1. Additionally, we present a simulation study to better understand the effect of some particular observations in the measures estimated by LCM and CA.

Autores da comunidade :

• 

  M

  Maria do Rosário De Oliveira Silva

  ist12954

  Afiliações e fontes

  IST > DM

  Departamento de Matemática

  De: orcid

  ID: 126634437

  De: cienciavitae

  ID: 2910666

• 

  A

  Ana Filipa Vieira da Encarnação Louzeiro

  ist149991

VoR - Versão publicada

Communications in Dependability and Quality Management

33

40

10

1

mathematics - Matemática

eng - Inglês