ROC curve analysis for biomarkers based on pooled assessments

David Faraggi, Benjamin Reiser, Enrique F. Schisterman

Research output: Contribution to journalArticle

Abstract

Interleukin-6 is a biomarker of inflammation which has been suggested as having potential discriminatory ability for myocardial infarction. Because of its high assaying cost it is very expensive to evaluate this marker. In order to reduce this cost we propose pooling the specimens. In this paper we examine the efficiency of ROC curve analysis, specifically the estimation of the area under the ROC curve, when dealing with pooled data. We study the effect of pooling when there are only a fixed number of individuals available for testing and pooling is carried out to save on the number of assays. Alternatively we examine how many pooled assays of size g are necessary to provide essentially the same information as N individual assays. We measure loss of information by means of the change in root mean square error of the estimate of the area under the ROC curve and study the extent of this loss via a simulation study.

Original languageEnglish (US)
Pages (from-to)2515-2527
Number of pages13
JournalStatistics in Medicine
Volume22
Issue number15
DOIs
StatePublished - Aug 15 2003
Externally publishedYes

Fingerprint

Pooling
Receiver Operating Characteristic Curve
Biomarkers
ROC Curve
Area Under Curve
Interleukin
Inflammation
Myocardial Infarction
Costs
Costs and Cost Analysis
Mean square error
Roots
Simulation Study
Interleukin-6
Testing
Necessary
Evaluate
Estimate

Keywords

  • Area under the ROC
  • Gamma distribution
  • Normal distribution
  • Root mean square error

ASJC Scopus subject areas

  • Epidemiology

Cite this

Faraggi, D., Reiser, B., & Schisterman, E. F. (2003). ROC curve analysis for biomarkers based on pooled assessments. Statistics in Medicine, 22(15), 2515-2527. https://doi.org/10.1002/sim.1418

ROC curve analysis for biomarkers based on pooled assessments. / Faraggi, David; Reiser, Benjamin; Schisterman, Enrique F.

In: Statistics in Medicine, Vol. 22, No. 15, 15.08.2003, p. 2515-2527.

Research output: Contribution to journalArticle

Faraggi, D, Reiser, B & Schisterman, EF 2003, 'ROC curve analysis for biomarkers based on pooled assessments', Statistics in Medicine, vol. 22, no. 15, pp. 2515-2527. https://doi.org/10.1002/sim.1418
Faraggi, David ; Reiser, Benjamin ; Schisterman, Enrique F. / ROC curve analysis for biomarkers based on pooled assessments. In: Statistics in Medicine. 2003 ; Vol. 22, No. 15. pp. 2515-2527.
@article{7f1132ac66214184a8edd129378f2138,
title = "ROC curve analysis for biomarkers based on pooled assessments",
abstract = "Interleukin-6 is a biomarker of inflammation which has been suggested as having potential discriminatory ability for myocardial infarction. Because of its high assaying cost it is very expensive to evaluate this marker. In order to reduce this cost we propose pooling the specimens. In this paper we examine the efficiency of ROC curve analysis, specifically the estimation of the area under the ROC curve, when dealing with pooled data. We study the effect of pooling when there are only a fixed number of individuals available for testing and pooling is carried out to save on the number of assays. Alternatively we examine how many pooled assays of size g are necessary to provide essentially the same information as N individual assays. We measure loss of information by means of the change in root mean square error of the estimate of the area under the ROC curve and study the extent of this loss via a simulation study.",
keywords = "Area under the ROC, Gamma distribution, Normal distribution, Root mean square error",
author = "David Faraggi and Benjamin Reiser and Schisterman, {Enrique F.}",
year = "2003",
month = "8",
day = "15",
doi = "10.1002/sim.1418",
language = "English (US)",
volume = "22",
pages = "2515--2527",
journal = "Statistics in Medicine",
issn = "0277-6715",
publisher = "John Wiley and Sons Ltd",
number = "15",

}

TY - JOUR

T1 - ROC curve analysis for biomarkers based on pooled assessments

AU - Faraggi, David

AU - Reiser, Benjamin

AU - Schisterman, Enrique F.

PY - 2003/8/15

Y1 - 2003/8/15

N2 - Interleukin-6 is a biomarker of inflammation which has been suggested as having potential discriminatory ability for myocardial infarction. Because of its high assaying cost it is very expensive to evaluate this marker. In order to reduce this cost we propose pooling the specimens. In this paper we examine the efficiency of ROC curve analysis, specifically the estimation of the area under the ROC curve, when dealing with pooled data. We study the effect of pooling when there are only a fixed number of individuals available for testing and pooling is carried out to save on the number of assays. Alternatively we examine how many pooled assays of size g are necessary to provide essentially the same information as N individual assays. We measure loss of information by means of the change in root mean square error of the estimate of the area under the ROC curve and study the extent of this loss via a simulation study.

AB - Interleukin-6 is a biomarker of inflammation which has been suggested as having potential discriminatory ability for myocardial infarction. Because of its high assaying cost it is very expensive to evaluate this marker. In order to reduce this cost we propose pooling the specimens. In this paper we examine the efficiency of ROC curve analysis, specifically the estimation of the area under the ROC curve, when dealing with pooled data. We study the effect of pooling when there are only a fixed number of individuals available for testing and pooling is carried out to save on the number of assays. Alternatively we examine how many pooled assays of size g are necessary to provide essentially the same information as N individual assays. We measure loss of information by means of the change in root mean square error of the estimate of the area under the ROC curve and study the extent of this loss via a simulation study.

KW - Area under the ROC

KW - Gamma distribution

KW - Normal distribution

KW - Root mean square error

UR - http://www.scopus.com/inward/record.url?scp=0043136517&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0043136517&partnerID=8YFLogxK

U2 - 10.1002/sim.1418

DO - 10.1002/sim.1418

M3 - Article

C2 - 12872306

AN - SCOPUS:0043136517

VL - 22

SP - 2515

EP - 2527

JO - Statistics in Medicine

JF - Statistics in Medicine

SN - 0277-6715

IS - 15

ER -