Comparing areas under receiver operating characteristic curves: Potential impact of the "last" experimentally measured operating point

被引：14

作者：

Gur, David ^{[1
]}

Bandos, Andriy I. ^{[2
]}

Rockette, Howard E. ^{[2
]}

机构：

[1] Univ Pittsburgh, Dept Radiol, Grad Sch Publ Hlth, Pittsburgh, PA 15213 USA

[2] Univ Pittsburgh, Dept Biostat, Grad Sch Publ Hlth, Pittsburgh, PA 15213 USA

来源：

RADIOLOGY | 2008年 / 247卷 / 01期

关键词：

D O I：

10.1148/radiol.2471071321

中图分类号：

R8 [特种医学]; R445 [影像诊断学];

学科分类号：

1002 [临床医学]; 100207 [影像医学与核医学]; 1009 [特种医学];

摘要：

A specific issue related to the selection of the analytic tool used when comparing the estimated performance of systems within the receiver operating characteristic (ROC) paradigm is reviewed. This issue is related to the possible effect of the last experimentally ascertained ROC data point in terms of highest true-positive and false-positive fractions. An example of a case is presented where the selection of a specific analysis approach could affect the study conclusion from being not statistically significant for parametric analysis and significant for nonparametric analysis. This is followed by recommendations that should help prevent misinterpretation of results. (c) RSNA, 2008.

引用

页码：12 / 15

页数：4

共 26 条

[1]

A permutation test sensitive to differences in areas for comparing ROC curves from a paired design [J].

Bandos, AI ;

Rockette, HE ;

Gur, D .

STATISTICS IN MEDICINE, 2005, 24 (18) :2873-2893

[2]

Components-of-variance models and multiple-bootstrap experiments: An alternative method for random-effects, receiver operating characteristic analysis [J].

Beiden, SV ;

Wagner, RF ;

Campbell, G .

ACADEMIC RADIOLOGY, 2000, 7 (05) :341-349

[3]

CAMPBELL G, 1988, COMPUT CARDIOL, P267

[4]

COMPARING THE AREAS UNDER 2 OR MORE CORRELATED RECEIVER OPERATING CHARACTERISTIC CURVES - A NONPARAMETRIC APPROACH [J].

DELONG, ER ;

DELONG, DM ;

CLARKEPEARSON, DI .

BIOMETRICS, 1988, 44 (03) :837-845

[5]

A contaminated binormal model for ROC data - Part I. Some interesting examples of binormal degeneracy [J].

Dorfman, DD ;

Berbaum, KS ;

Brandser, EA .

ACADEMIC RADIOLOGY, 2000, 7 (06) :420-426

[6]

RECEIVER OPERATING CHARACTERISTIC RATING ANALYSIS - GENERALIZATION TO THE POPULATION OF READERS AND PATIENTS WITH THE JACKKNIFE METHOD [J].

DORFMAN, DD ;

BERBAUM, KS ;

METZ, CE .

INVESTIGATIVE RADIOLOGY, 1992, 27 (09) :723-731

[7]

Influence of computer-aided detection on performance of screening mammography [J].

Fenton, Joshua J. ;

Taplin, Stephen H. ;

Carney, Patricia A. ;

Abraham, Linn ;

Sickles, Edward A. ;

D'Orsi, Carl ;

Berns, Eric A. ;

Cutter, Gary ;

Hendrick, R. Edward ;

Barlow, William E. ;

Elmore, Joann G. .

NEW ENGLAND JOURNAL OF MEDICINE, 2007, 356 (14) :1399-1409

[8]

Two-modality mammography may confer an advantage over either full-field digital mammography or screen-film mammography [J].

Glueck, Deborah H. ;

Lamb, Molly M. ;

Lewin, John M. ;

Pisano, Etta D. .

ACADEMIC RADIOLOGY, 2007, 14 (06) :670-676

[9]

Prevalence effect in a laboratory environment [J].

Gur, D ;

Rockette, HE ;

Armfield, DR ;

Blachar, A ;

Bogan, JK ;

Brancatelli, G ;

Britton, CA ;

Brown, ML ;

Davis, PL ;

Ferris, JV ;

Fuhrman, CR ;

Golla, SK ;

Katyal, S ;

Lacomis, JM ;

McCook, BM ;

Thaete, FL ;

Warfel, TE .

RADIOLOGY, 2003, 228 (01) :10-14

[10]

"Binary" and "non-binary" detection tasks: Are current performance measures optimal? [J].

Gur, David ;

Rockette, Howard E. ;

Bandos, Andriy I. .

ACADEMIC RADIOLOGY, 2007, 14 (07) :871-876

← 1 2 3 →