Biomarker assessment and combination with differential covariate effects and an unknown gold standard, with an application to alzheimer’s disease

Zheyu Wang, Xiao Hua Zhou

Research output: Contribution to journalArticle

Abstract

The continued efforts to evaluate biomarkers’ predictive abilities and identify optimal biomarker combinations are often challenged by the absence of a gold standard, that is, the true disease status. Current methods that address this issue are mostly developed for binary or ordinal diagnostic tests, which do not fully utilize information provided by continuous biomarkers, or require strong parametric assumptions. Moreover, limited methods exist to allow for the inclusion of covariates—despite their crucial role in facilitating the accurate evaluation of biomarkers. In this paper, we proposed a latent profile approach to evaluating diagnostic accuracy of biomarkers without a gold standard. The method allows for flexible biomarker distributions and incorporation of previous knowledge about risk factors while simultaneously permitting researchers to model paticipants’ characteristics that putatively affect biomarker levels, and therefore provides information needed to develop more personalized diagnostic procedures. Additionally, the proposed method presents a potential strategy for biomarker combination when gold standard information is unavailable, as it derives a composite risk score for the underlying disease status. The method is applied to evaluate different cerebral spinal fluid (CSF) biomarkers for Alzheimer’s disease (AD) detection. The results show that CSF biomarkers hold significant potential for facilitating early AD detection and for continuous disease monitoring. Furthermore, they call attention to biomarker variability in subgroups and reexamination of CSF biomarker distributions. Data used in preparation of this article were obtained from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database.

Original languageEnglish (US)
Pages (from-to)1204-1227
Number of pages24
JournalAnnals of Applied Statistics
Volume12
Issue number2
DOIs
StatePublished - Jun 1 2018

Fingerprint

Alzheimer's Disease
Biomarkers
Gold
Covariates
Unknown
Fluid
Fluids
Standards
Alzheimer's disease
Gold standard
Neuroimaging
Diagnostic Accuracy
Diagnostic Tests
Evaluate
Risk Factors
Preparation
Diagnostics
Inclusion
Composite

Keywords

  • Alzheimer’s disease
  • Diagnostic accuracy
  • Differential covariate effect
  • Finite mixture models
  • Identifiability
  • Latent profile model

ASJC Scopus subject areas

  • Statistics and Probability
  • Modeling and Simulation
  • Statistics, Probability and Uncertainty

Cite this

@article{d07e2ee8048d4b54ab22c724e77fd26d,
title = "Biomarker assessment and combination with differential covariate effects and an unknown gold standard, with an application to alzheimer’s disease",
abstract = "The continued efforts to evaluate biomarkers’ predictive abilities and identify optimal biomarker combinations are often challenged by the absence of a gold standard, that is, the true disease status. Current methods that address this issue are mostly developed for binary or ordinal diagnostic tests, which do not fully utilize information provided by continuous biomarkers, or require strong parametric assumptions. Moreover, limited methods exist to allow for the inclusion of covariates—despite their crucial role in facilitating the accurate evaluation of biomarkers. In this paper, we proposed a latent profile approach to evaluating diagnostic accuracy of biomarkers without a gold standard. The method allows for flexible biomarker distributions and incorporation of previous knowledge about risk factors while simultaneously permitting researchers to model paticipants’ characteristics that putatively affect biomarker levels, and therefore provides information needed to develop more personalized diagnostic procedures. Additionally, the proposed method presents a potential strategy for biomarker combination when gold standard information is unavailable, as it derives a composite risk score for the underlying disease status. The method is applied to evaluate different cerebral spinal fluid (CSF) biomarkers for Alzheimer’s disease (AD) detection. The results show that CSF biomarkers hold significant potential for facilitating early AD detection and for continuous disease monitoring. Furthermore, they call attention to biomarker variability in subgroups and reexamination of CSF biomarker distributions. Data used in preparation of this article were obtained from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database.",
keywords = "Alzheimer’s disease, Diagnostic accuracy, Differential covariate effect, Finite mixture models, Identifiability, Latent profile model",
author = "Zheyu Wang and Zhou, {Xiao Hua}",
year = "2018",
month = "6",
day = "1",
doi = "10.1214/17-AOAS1085",
language = "English (US)",
volume = "12",
pages = "1204--1227",
journal = "Annals of Applied Statistics",
issn = "1932-6157",
publisher = "Institute of Mathematical Statistics",
number = "2",

}

TY - JOUR

T1 - Biomarker assessment and combination with differential covariate effects and an unknown gold standard, with an application to alzheimer’s disease

AU - Wang, Zheyu

AU - Zhou, Xiao Hua

PY - 2018/6/1

Y1 - 2018/6/1

N2 - The continued efforts to evaluate biomarkers’ predictive abilities and identify optimal biomarker combinations are often challenged by the absence of a gold standard, that is, the true disease status. Current methods that address this issue are mostly developed for binary or ordinal diagnostic tests, which do not fully utilize information provided by continuous biomarkers, or require strong parametric assumptions. Moreover, limited methods exist to allow for the inclusion of covariates—despite their crucial role in facilitating the accurate evaluation of biomarkers. In this paper, we proposed a latent profile approach to evaluating diagnostic accuracy of biomarkers without a gold standard. The method allows for flexible biomarker distributions and incorporation of previous knowledge about risk factors while simultaneously permitting researchers to model paticipants’ characteristics that putatively affect biomarker levels, and therefore provides information needed to develop more personalized diagnostic procedures. Additionally, the proposed method presents a potential strategy for biomarker combination when gold standard information is unavailable, as it derives a composite risk score for the underlying disease status. The method is applied to evaluate different cerebral spinal fluid (CSF) biomarkers for Alzheimer’s disease (AD) detection. The results show that CSF biomarkers hold significant potential for facilitating early AD detection and for continuous disease monitoring. Furthermore, they call attention to biomarker variability in subgroups and reexamination of CSF biomarker distributions. Data used in preparation of this article were obtained from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database.

AB - The continued efforts to evaluate biomarkers’ predictive abilities and identify optimal biomarker combinations are often challenged by the absence of a gold standard, that is, the true disease status. Current methods that address this issue are mostly developed for binary or ordinal diagnostic tests, which do not fully utilize information provided by continuous biomarkers, or require strong parametric assumptions. Moreover, limited methods exist to allow for the inclusion of covariates—despite their crucial role in facilitating the accurate evaluation of biomarkers. In this paper, we proposed a latent profile approach to evaluating diagnostic accuracy of biomarkers without a gold standard. The method allows for flexible biomarker distributions and incorporation of previous knowledge about risk factors while simultaneously permitting researchers to model paticipants’ characteristics that putatively affect biomarker levels, and therefore provides information needed to develop more personalized diagnostic procedures. Additionally, the proposed method presents a potential strategy for biomarker combination when gold standard information is unavailable, as it derives a composite risk score for the underlying disease status. The method is applied to evaluate different cerebral spinal fluid (CSF) biomarkers for Alzheimer’s disease (AD) detection. The results show that CSF biomarkers hold significant potential for facilitating early AD detection and for continuous disease monitoring. Furthermore, they call attention to biomarker variability in subgroups and reexamination of CSF biomarker distributions. Data used in preparation of this article were obtained from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database.

KW - Alzheimer’s disease

KW - Diagnostic accuracy

KW - Differential covariate effect

KW - Finite mixture models

KW - Identifiability

KW - Latent profile model

UR - http://www.scopus.com/inward/record.url?scp=85050949082&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050949082&partnerID=8YFLogxK

U2 - 10.1214/17-AOAS1085

DO - 10.1214/17-AOAS1085

M3 - Article

AN - SCOPUS:85050949082

VL - 12

SP - 1204

EP - 1227

JO - Annals of Applied Statistics

JF - Annals of Applied Statistics

SN - 1932-6157

IS - 2

ER -