Bayesian semi-parametric joint modeling of biomarker data with a latent changepoint: Assessing the temporal performance of Enzyme-Linked Immunosorbent Assay (ELISA) testing for paratuberculosis

Michelle Norris, Wesley O. Johnson, Ian Gardner

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

In this paper, we develop a class of semi-parametric statistical models that can be used for the important problem of analyzing longitudinal biomarker data with the purpose of quantifying their diagnostic capabilities, as a function of time from infection. We focus on the complicated problem where there is no gold standard assessment of the actual timing of infection/disease onset (our change point), which provides additional motivation for considering a second, binary test, in order to make it easier to estimate the change points for individuals that become diseased. An important additional feature of our model is its nonparametric part, which allows for distinct biomarker responses to the insult of infection/disease. In our case, the model allows for the possibility of an unknown number of clusters of individuals, each with distinct slopes corresponding to distinct biological reactions. Clusters with steeper slopes would correspond to individuals that could be diagnosed sooner than those with more gradual slopes.

Original languageEnglish (US)
Pages (from-to)417-438
Number of pages22
JournalStatistics and its Interface
Volume7
Issue number4
DOIs
StatePublished - Jan 1 2014
Externally publishedYes

Fingerprint

Parametric Modeling
Enzyme-linked Immunosorbent Assay
Joint Modeling
Change Point
Biomarkers
Infection
Assays
Slope
Enzymes
Distinct
Testing
Semiparametric Model
Number of Clusters
Gold
Statistical Model
Timing
Diagnostics
Binary
Unknown
Model

Keywords

  • Bayesian semi-parametric approach
  • Change point model
  • Dirichlet process mixture
  • Imperfect reference standard
  • Johne's disease
  • Longitudinal data
  • Random effects

ASJC Scopus subject areas

  • Statistics and Probability
  • Applied Mathematics

Cite this

@article{f6c9986a483f40cc99b3832ec56f8ffe,
title = "Bayesian semi-parametric joint modeling of biomarker data with a latent changepoint: Assessing the temporal performance of Enzyme-Linked Immunosorbent Assay (ELISA) testing for paratuberculosis",
abstract = "In this paper, we develop a class of semi-parametric statistical models that can be used for the important problem of analyzing longitudinal biomarker data with the purpose of quantifying their diagnostic capabilities, as a function of time from infection. We focus on the complicated problem where there is no gold standard assessment of the actual timing of infection/disease onset (our change point), which provides additional motivation for considering a second, binary test, in order to make it easier to estimate the change points for individuals that become diseased. An important additional feature of our model is its nonparametric part, which allows for distinct biomarker responses to the insult of infection/disease. In our case, the model allows for the possibility of an unknown number of clusters of individuals, each with distinct slopes corresponding to distinct biological reactions. Clusters with steeper slopes would correspond to individuals that could be diagnosed sooner than those with more gradual slopes.",
keywords = "Bayesian semi-parametric approach, Change point model, Dirichlet process mixture, Imperfect reference standard, Johne's disease, Longitudinal data, Random effects",
author = "Michelle Norris and Johnson, {Wesley O.} and Ian Gardner",
year = "2014",
month = "1",
day = "1",
doi = "10.4310/SII.2014.v7.n4.a1",
language = "English (US)",
volume = "7",
pages = "417--438",
journal = "Statistics and its Interface",
issn = "1938-7989",
publisher = "International Press of Boston, Inc.",
number = "4",

}

TY - JOUR

T1 - Bayesian semi-parametric joint modeling of biomarker data with a latent changepoint

T2 - Assessing the temporal performance of Enzyme-Linked Immunosorbent Assay (ELISA) testing for paratuberculosis

AU - Norris, Michelle

AU - Johnson, Wesley O.

AU - Gardner, Ian

PY - 2014/1/1

Y1 - 2014/1/1

N2 - In this paper, we develop a class of semi-parametric statistical models that can be used for the important problem of analyzing longitudinal biomarker data with the purpose of quantifying their diagnostic capabilities, as a function of time from infection. We focus on the complicated problem where there is no gold standard assessment of the actual timing of infection/disease onset (our change point), which provides additional motivation for considering a second, binary test, in order to make it easier to estimate the change points for individuals that become diseased. An important additional feature of our model is its nonparametric part, which allows for distinct biomarker responses to the insult of infection/disease. In our case, the model allows for the possibility of an unknown number of clusters of individuals, each with distinct slopes corresponding to distinct biological reactions. Clusters with steeper slopes would correspond to individuals that could be diagnosed sooner than those with more gradual slopes.

AB - In this paper, we develop a class of semi-parametric statistical models that can be used for the important problem of analyzing longitudinal biomarker data with the purpose of quantifying their diagnostic capabilities, as a function of time from infection. We focus on the complicated problem where there is no gold standard assessment of the actual timing of infection/disease onset (our change point), which provides additional motivation for considering a second, binary test, in order to make it easier to estimate the change points for individuals that become diseased. An important additional feature of our model is its nonparametric part, which allows for distinct biomarker responses to the insult of infection/disease. In our case, the model allows for the possibility of an unknown number of clusters of individuals, each with distinct slopes corresponding to distinct biological reactions. Clusters with steeper slopes would correspond to individuals that could be diagnosed sooner than those with more gradual slopes.

KW - Bayesian semi-parametric approach

KW - Change point model

KW - Dirichlet process mixture

KW - Imperfect reference standard

KW - Johne's disease

KW - Longitudinal data

KW - Random effects

UR - http://www.scopus.com/inward/record.url?scp=84920086454&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84920086454&partnerID=8YFLogxK

U2 - 10.4310/SII.2014.v7.n4.a1

DO - 10.4310/SII.2014.v7.n4.a1

M3 - Article

AN - SCOPUS:84920086454

VL - 7

SP - 417

EP - 438

JO - Statistics and its Interface

JF - Statistics and its Interface

SN - 1938-7989

IS - 4

ER -