Cargando…

Statistical models for quantifying diagnostic accuracy with multiple lesions per patient

We propose random-effects models to summarize and quantify the accuracy of the diagnosis of multiple lesions on a single image without assuming independence between lesions. The number of false-positive lesions was assumed to be distributed as a Poisson mixture, and the proportion of true-positive l...

Descripción completa

Detalles Bibliográficos
Autores principales: Zwinderman, Aeilko H., Glas, Afina S., Bossuyt, Patrick M., Florie, Jasper, Bipat, Shandra, Stoker, Jaap
Formato: Texto
Lenguaje:English
Publicado: Oxford University Press 2008
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2430771/
https://www.ncbi.nlm.nih.gov/pubmed/18204044
http://dx.doi.org/10.1093/biostatistics/kxm052
Descripción
Sumario:We propose random-effects models to summarize and quantify the accuracy of the diagnosis of multiple lesions on a single image without assuming independence between lesions. The number of false-positive lesions was assumed to be distributed as a Poisson mixture, and the proportion of true-positive lesions was assumed to be distributed as a binomial mixture. We considered univariate and bivariate, both parametric and nonparametric mixture models. We applied our tools to simulated data and data of a study assessing diagnostic accuracy of virtual colonography with computed tomography in 200 patients suspected of having one or more polyps.