On the problem of ROC analysis without truth: The EM algorithm and the information matrix.

被引：24

作者：

Beiden, SV ^{[1
]}

Campbell, G ^{[1
]}

Meier, KL ^{[1
]}

Wagner, RF ^{[1
]}

机构：

[1] US FDA, Ctr Devices & Radiol Hlth, Off Sci & Technol, Rockville, MD 20857 USA

来源：

MEDICAL IMAGING 2000: IMAGE PERCEPTION AND PERFORMANCE | 2000年 / 3981卷

关键词：

D O I：

10.1117/12.383099

中图分类号：

R318 [生物医学工程];

学科分类号：

0831 ;

摘要：

Henkelman, Kay, and Bronskill (HKB) showed that although the problem of ROC analysis without truth is underconstrained and thus not uniquely solvable in one dimension (one diagnostic test), it is in principle solvable in two or more dimensions. However, they gave no analysis of the resulting uncertainties. The present work provides a maximum-likelihood solution using the EM (expectation-maximization) algorithm for the two-dimensional case. We also provide an analysis of uncertainties in terms of Monte Carlo simulations as well as estimates based on Fisher Information Matrices for the complete- and the missing-data problem. We find that the number of patients required for a given precision of estimate for the truth-unknown problem is a very large multiple of that required for the corresponding truth-known case.

引用

页码：126 / 134

页数：9

共 12 条

[1]

[Anonymous], MULTIPLE REGRESSION

[2] CONSENSUS DIAGNOSES AND GOLD STANDARDS - COMMENTARY [J].

BEGG, CB ;

METZ, CE .

MEDICAL DECISION MAKING, 1990, 10 (01) :29-30

[3] MAXIMUM LIKELIHOOD FROM INCOMPLETE DATA VIA EM ALGORITHM [J].

DEMPSTER, AP ;

LAIRD, NM ;

RUBIN, DB .

JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-METHODOLOGICAL, 1977, 39 (01) :1-38

[4] MAXIMUM LIKELIHOOD ESTIMATION FOR MIXTURES OF 2 NORMAL DISTRIBUTIONS [J].

DICK, NP ;

BOWDEN, DC .

BIOMETRICS, 1973, 29 (04) :781-790

[5] RECEIVER OPERATOR CHARACTERISTIC (ROC) ANALYSIS WITHOUT TRUTH [J].

HENKELMAN, RM ;

KAY, I ;

BRONSKILL, MJ .

MEDICAL DECISION MAKING, 1990, 10 (01) :24-29

[6]

Louis T. A., 1982, J R STAT SOC B, V44, P98

[7]

Metz C.Z., 1984, INFORMATION PROCESSI, P432

[8]

Tanner M.A., 1993, TOOLS STAT INFERENCE, V2nd

[9]

Titterington D.M., 1985, Statistical analysis of finite mixture distributions

[10]

Zhou X H, 1998, Stat Methods Med Res, V7, P337, DOI 10.1191/096228098676485370

← 1 2 →