An additive selection of markers to improve diagnostic accuracy based on a discriminatory measure

Liansheng Larry Tang, Le Kang, Chunling Liu, Enrique F. Schisterman, Aiyi Liu

Research output: Contribution to journalArticle

Abstract

Rationale and Objectives: The estimation of the area under the receiver operating characteristic (ROC) curve (AUC) often relies on the assumption that the truly positive population tends to have higher marker results than the truly negative population. The authors propose a discriminatory measure to relax such an assumption and apply the measure to identify the appropriate set of markers for combination. Materials and Methods: The proposed measure is based on the maximum of the AUC and 1-AUC. The existing methods are applied toestimate the measure. The subset of markers is selected using a combination method that maximizes a function of the proposed discriminatory score with the number of markers as a penalty in the function. Results: The properties of the estimators for the proposed measure were studied through large-scale simulation studies. The application was illustrated through a real example to identify the set of markers to combine. Conclusion: Simulation results showed excellent small-sample performance of the estimators for the proposed measure. The application in the example yielded a reasonable subset of markers for combination.

Original languageEnglish (US)
Pages (from-to)854-862
Number of pages9
JournalAcademic Radiology
Volume20
Issue number7
DOIs
StatePublished - Jul 2013
Externally publishedYes

Fingerprint

Area Under Curve
ROC Curve
Population

Keywords

  • Area under the ROC curves (AUC)
  • Box-Cox transformation
  • Discriminatory score
  • Receiver operating characteristic (ROC)

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging

Cite this

An additive selection of markers to improve diagnostic accuracy based on a discriminatory measure. / Tang, Liansheng Larry; Kang, Le; Liu, Chunling; Schisterman, Enrique F.; Liu, Aiyi.

In: Academic Radiology, Vol. 20, No. 7, 07.2013, p. 854-862.

Research output: Contribution to journalArticle

Tang, Liansheng Larry ; Kang, Le ; Liu, Chunling ; Schisterman, Enrique F. ; Liu, Aiyi. / An additive selection of markers to improve diagnostic accuracy based on a discriminatory measure. In: Academic Radiology. 2013 ; Vol. 20, No. 7. pp. 854-862.
@article{5abb669a4edf4a5886df00fbc929a9e7,
title = "An additive selection of markers to improve diagnostic accuracy based on a discriminatory measure",
abstract = "Rationale and Objectives: The estimation of the area under the receiver operating characteristic (ROC) curve (AUC) often relies on the assumption that the truly positive population tends to have higher marker results than the truly negative population. The authors propose a discriminatory measure to relax such an assumption and apply the measure to identify the appropriate set of markers for combination. Materials and Methods: The proposed measure is based on the maximum of the AUC and 1-AUC. The existing methods are applied toestimate the measure. The subset of markers is selected using a combination method that maximizes a function of the proposed discriminatory score with the number of markers as a penalty in the function. Results: The properties of the estimators for the proposed measure were studied through large-scale simulation studies. The application was illustrated through a real example to identify the set of markers to combine. Conclusion: Simulation results showed excellent small-sample performance of the estimators for the proposed measure. The application in the example yielded a reasonable subset of markers for combination.",
keywords = "Area under the ROC curves (AUC), Box-Cox transformation, Discriminatory score, Receiver operating characteristic (ROC)",
author = "Tang, {Liansheng Larry} and Le Kang and Chunling Liu and Schisterman, {Enrique F.} and Aiyi Liu",
year = "2013",
month = "7",
doi = "10.1016/j.acra.2013.02.009",
language = "English (US)",
volume = "20",
pages = "854--862",
journal = "Academic Radiology",
issn = "1076-6332",
publisher = "Elsevier USA",
number = "7",

}

TY - JOUR

T1 - An additive selection of markers to improve diagnostic accuracy based on a discriminatory measure

AU - Tang, Liansheng Larry

AU - Kang, Le

AU - Liu, Chunling

AU - Schisterman, Enrique F.

AU - Liu, Aiyi

PY - 2013/7

Y1 - 2013/7

N2 - Rationale and Objectives: The estimation of the area under the receiver operating characteristic (ROC) curve (AUC) often relies on the assumption that the truly positive population tends to have higher marker results than the truly negative population. The authors propose a discriminatory measure to relax such an assumption and apply the measure to identify the appropriate set of markers for combination. Materials and Methods: The proposed measure is based on the maximum of the AUC and 1-AUC. The existing methods are applied toestimate the measure. The subset of markers is selected using a combination method that maximizes a function of the proposed discriminatory score with the number of markers as a penalty in the function. Results: The properties of the estimators for the proposed measure were studied through large-scale simulation studies. The application was illustrated through a real example to identify the set of markers to combine. Conclusion: Simulation results showed excellent small-sample performance of the estimators for the proposed measure. The application in the example yielded a reasonable subset of markers for combination.

AB - Rationale and Objectives: The estimation of the area under the receiver operating characteristic (ROC) curve (AUC) often relies on the assumption that the truly positive population tends to have higher marker results than the truly negative population. The authors propose a discriminatory measure to relax such an assumption and apply the measure to identify the appropriate set of markers for combination. Materials and Methods: The proposed measure is based on the maximum of the AUC and 1-AUC. The existing methods are applied toestimate the measure. The subset of markers is selected using a combination method that maximizes a function of the proposed discriminatory score with the number of markers as a penalty in the function. Results: The properties of the estimators for the proposed measure were studied through large-scale simulation studies. The application was illustrated through a real example to identify the set of markers to combine. Conclusion: Simulation results showed excellent small-sample performance of the estimators for the proposed measure. The application in the example yielded a reasonable subset of markers for combination.

KW - Area under the ROC curves (AUC)

KW - Box-Cox transformation

KW - Discriminatory score

KW - Receiver operating characteristic (ROC)

UR - http://www.scopus.com/inward/record.url?scp=84878950765&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84878950765&partnerID=8YFLogxK

U2 - 10.1016/j.acra.2013.02.009

DO - 10.1016/j.acra.2013.02.009

M3 - Article

C2 - 23611438

AN - SCOPUS:84878950765

VL - 20

SP - 854

EP - 862

JO - Academic Radiology

JF - Academic Radiology

SN - 1076-6332

IS - 7

ER -