Semi-parametric area under the curve regression method for diagnostic studies with ordinal data

Kumar Rajan, Xiao Hua Zhou

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

The classification accuracy of new diagnostic tests is based on receiver operating characteristic (ROC) curves. The area under the ROC curve (AUC) is one of the well-accepted summary measures for describing the accuracy of diagnostic tests. The AUC summary measure can vary by patient and testing characteristics. Thus, the performance of the test may be different in certain subpopulation of patients and readers. For this purpose, we propose a direct semi-parametric regression model for the non-parametric AUC measure for ordinal data while accounting for discrete and continuous covariates. The proposed method can be used to estimate the AUC value under degenerate data where certain rating categories are not observed. We will discuss the non-standard asymptotic theory, since the estimating functions were based on cross-correlated random variables. Simulation studies based on different classification models showed that the proposed model worked reasonably well with small percent bias and percent mean-squared error. The proposed method was applied to the prostate cancer study to estimate the AUC for four readers, and the carotid vessel study with age, gender, history of previous stroke, and total number of risk factors as covariates, to estimate the accuracy of the diagnostic test in the presence of subject-level covariates.

Original languageEnglish (US)
Pages (from-to)143-156
Number of pages14
JournalBiometrical Journal
Volume54
Issue number1
DOIs
StatePublished - Jan 1 2012
Externally publishedYes

Fingerprint

Ordinal Data
Receiver Operating Characteristic Curve
ROC Curve
Area Under Curve
Diagnostics
Regression
Regression Analysis
Curve
Diagnostic Tests
Routine Diagnostic Tests
Covariates
Percent
Estimate
Semiparametric Regression Model
Estimating Function
Prostate Cancer
Asymptotic Theory
Risk Factors
Stroke
Mean Squared Error

Keywords

  • Area under the curve
  • Diagnostic markers
  • Regression for ordinal data

ASJC Scopus subject areas

  • Statistics and Probability
  • Medicine(all)
  • Statistics, Probability and Uncertainty

Cite this

Semi-parametric area under the curve regression method for diagnostic studies with ordinal data. / Rajan, Kumar; Zhou, Xiao Hua.

In: Biometrical Journal, Vol. 54, No. 1, 01.01.2012, p. 143-156.

Research output: Contribution to journalArticle

@article{94e6001bb7c448e28de47022d1439ab6,
title = "Semi-parametric area under the curve regression method for diagnostic studies with ordinal data",
abstract = "The classification accuracy of new diagnostic tests is based on receiver operating characteristic (ROC) curves. The area under the ROC curve (AUC) is one of the well-accepted summary measures for describing the accuracy of diagnostic tests. The AUC summary measure can vary by patient and testing characteristics. Thus, the performance of the test may be different in certain subpopulation of patients and readers. For this purpose, we propose a direct semi-parametric regression model for the non-parametric AUC measure for ordinal data while accounting for discrete and continuous covariates. The proposed method can be used to estimate the AUC value under degenerate data where certain rating categories are not observed. We will discuss the non-standard asymptotic theory, since the estimating functions were based on cross-correlated random variables. Simulation studies based on different classification models showed that the proposed model worked reasonably well with small percent bias and percent mean-squared error. The proposed method was applied to the prostate cancer study to estimate the AUC for four readers, and the carotid vessel study with age, gender, history of previous stroke, and total number of risk factors as covariates, to estimate the accuracy of the diagnostic test in the presence of subject-level covariates.",
keywords = "Area under the curve, Diagnostic markers, Regression for ordinal data",
author = "Kumar Rajan and Zhou, {Xiao Hua}",
year = "2012",
month = "1",
day = "1",
doi = "10.1002/bimj.201100025",
language = "English (US)",
volume = "54",
pages = "143--156",
journal = "Biometrical Journal",
issn = "0323-3847",
publisher = "Wiley-VCH Verlag",
number = "1",

}

TY - JOUR

T1 - Semi-parametric area under the curve regression method for diagnostic studies with ordinal data

AU - Rajan, Kumar

AU - Zhou, Xiao Hua

PY - 2012/1/1

Y1 - 2012/1/1

N2 - The classification accuracy of new diagnostic tests is based on receiver operating characteristic (ROC) curves. The area under the ROC curve (AUC) is one of the well-accepted summary measures for describing the accuracy of diagnostic tests. The AUC summary measure can vary by patient and testing characteristics. Thus, the performance of the test may be different in certain subpopulation of patients and readers. For this purpose, we propose a direct semi-parametric regression model for the non-parametric AUC measure for ordinal data while accounting for discrete and continuous covariates. The proposed method can be used to estimate the AUC value under degenerate data where certain rating categories are not observed. We will discuss the non-standard asymptotic theory, since the estimating functions were based on cross-correlated random variables. Simulation studies based on different classification models showed that the proposed model worked reasonably well with small percent bias and percent mean-squared error. The proposed method was applied to the prostate cancer study to estimate the AUC for four readers, and the carotid vessel study with age, gender, history of previous stroke, and total number of risk factors as covariates, to estimate the accuracy of the diagnostic test in the presence of subject-level covariates.

AB - The classification accuracy of new diagnostic tests is based on receiver operating characteristic (ROC) curves. The area under the ROC curve (AUC) is one of the well-accepted summary measures for describing the accuracy of diagnostic tests. The AUC summary measure can vary by patient and testing characteristics. Thus, the performance of the test may be different in certain subpopulation of patients and readers. For this purpose, we propose a direct semi-parametric regression model for the non-parametric AUC measure for ordinal data while accounting for discrete and continuous covariates. The proposed method can be used to estimate the AUC value under degenerate data where certain rating categories are not observed. We will discuss the non-standard asymptotic theory, since the estimating functions were based on cross-correlated random variables. Simulation studies based on different classification models showed that the proposed model worked reasonably well with small percent bias and percent mean-squared error. The proposed method was applied to the prostate cancer study to estimate the AUC for four readers, and the carotid vessel study with age, gender, history of previous stroke, and total number of risk factors as covariates, to estimate the accuracy of the diagnostic test in the presence of subject-level covariates.

KW - Area under the curve

KW - Diagnostic markers

KW - Regression for ordinal data

UR - http://www.scopus.com/inward/record.url?scp=84862950764&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84862950764&partnerID=8YFLogxK

U2 - 10.1002/bimj.201100025

DO - 10.1002/bimj.201100025

M3 - Article

VL - 54

SP - 143

EP - 156

JO - Biometrical Journal

JF - Biometrical Journal

SN - 0323-3847

IS - 1

ER -