Variable selection using the optimal ROC curve: An application to a traditional Chinese medicine study on osteoporosis disease

X. H. Zhou, B. Chen, Y. M. Xie, F. Tian, H. Liu, X. Liang

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

In biomedical studies, there are multiple sources of information available of which only a small number of them are associated with the diseases. It is of importance to select and combine these factors that are associated with the disease in order to predict the disease status of a new subject. The receiving operating characteristic (ROC) technique has been widely used in disease classification, and the classification accuracy can be measured with area under the ROC curve (AUC). In this article, we combine recent variable selection methods with AUC methods to optimize diagnostic accuracy of multiple risk factors. We first describe one new and some recent AUC-based methods for effectively combining multiple risk factors for disease classification. We then apply them to analyze the data from a new clinical study, investigating whether a combination of traditional Chinese medicine symptoms and standard Western medicine risk factors can increase discriminative accuracy in diagnosing osteoporosis (OP). Based on the results, we conclude that we can make a better diagnosis of primary OP by combining traditional Chinese medicine symptoms with Western medicine risk factors.

Original languageEnglish (US)
Pages (from-to)628-635
Number of pages8
JournalStatistics in Medicine
Volume31
Issue number7
DOIs
StatePublished - Mar 30 2012

Fingerprint

Osteoporosis
Traditional Chinese Medicine
Characteristic Curve
Operating Characteristics
Chinese Traditional Medicine
Variable Selection
Risk Factors
Receiver Operating Characteristic Curve
ROC Curve
Medicine
Area Under Curve
Diagnostic Accuracy
Optimise
Predict

Keywords

  • AUC
  • Classification
  • ROC
  • Variable selection

ASJC Scopus subject areas

  • Epidemiology
  • Statistics and Probability

Cite this

Variable selection using the optimal ROC curve : An application to a traditional Chinese medicine study on osteoporosis disease. / Zhou, X. H.; Chen, B.; Xie, Y. M.; Tian, F.; Liu, H.; Liang, X.

In: Statistics in Medicine, Vol. 31, No. 7, 30.03.2012, p. 628-635.

Research output: Contribution to journalArticle

Zhou, X. H. ; Chen, B. ; Xie, Y. M. ; Tian, F. ; Liu, H. ; Liang, X. / Variable selection using the optimal ROC curve : An application to a traditional Chinese medicine study on osteoporosis disease. In: Statistics in Medicine. 2012 ; Vol. 31, No. 7. pp. 628-635.
@article{544972f91cea4619bdc842007af4607f,
title = "Variable selection using the optimal ROC curve: An application to a traditional Chinese medicine study on osteoporosis disease",
abstract = "In biomedical studies, there are multiple sources of information available of which only a small number of them are associated with the diseases. It is of importance to select and combine these factors that are associated with the disease in order to predict the disease status of a new subject. The receiving operating characteristic (ROC) technique has been widely used in disease classification, and the classification accuracy can be measured with area under the ROC curve (AUC). In this article, we combine recent variable selection methods with AUC methods to optimize diagnostic accuracy of multiple risk factors. We first describe one new and some recent AUC-based methods for effectively combining multiple risk factors for disease classification. We then apply them to analyze the data from a new clinical study, investigating whether a combination of traditional Chinese medicine symptoms and standard Western medicine risk factors can increase discriminative accuracy in diagnosing osteoporosis (OP). Based on the results, we conclude that we can make a better diagnosis of primary OP by combining traditional Chinese medicine symptoms with Western medicine risk factors.",
keywords = "AUC, Classification, ROC, Variable selection",
author = "Zhou, {X. H.} and B. Chen and Xie, {Y. M.} and F. Tian and H. Liu and X. Liang",
year = "2012",
month = "3",
day = "30",
doi = "10.1002/sim.3980",
language = "English (US)",
volume = "31",
pages = "628--635",
journal = "Statistics in Medicine",
issn = "0277-6715",
publisher = "John Wiley and Sons Ltd",
number = "7",

}

TY - JOUR

T1 - Variable selection using the optimal ROC curve

T2 - An application to a traditional Chinese medicine study on osteoporosis disease

AU - Zhou, X. H.

AU - Chen, B.

AU - Xie, Y. M.

AU - Tian, F.

AU - Liu, H.

AU - Liang, X.

PY - 2012/3/30

Y1 - 2012/3/30

N2 - In biomedical studies, there are multiple sources of information available of which only a small number of them are associated with the diseases. It is of importance to select and combine these factors that are associated with the disease in order to predict the disease status of a new subject. The receiving operating characteristic (ROC) technique has been widely used in disease classification, and the classification accuracy can be measured with area under the ROC curve (AUC). In this article, we combine recent variable selection methods with AUC methods to optimize diagnostic accuracy of multiple risk factors. We first describe one new and some recent AUC-based methods for effectively combining multiple risk factors for disease classification. We then apply them to analyze the data from a new clinical study, investigating whether a combination of traditional Chinese medicine symptoms and standard Western medicine risk factors can increase discriminative accuracy in diagnosing osteoporosis (OP). Based on the results, we conclude that we can make a better diagnosis of primary OP by combining traditional Chinese medicine symptoms with Western medicine risk factors.

AB - In biomedical studies, there are multiple sources of information available of which only a small number of them are associated with the diseases. It is of importance to select and combine these factors that are associated with the disease in order to predict the disease status of a new subject. The receiving operating characteristic (ROC) technique has been widely used in disease classification, and the classification accuracy can be measured with area under the ROC curve (AUC). In this article, we combine recent variable selection methods with AUC methods to optimize diagnostic accuracy of multiple risk factors. We first describe one new and some recent AUC-based methods for effectively combining multiple risk factors for disease classification. We then apply them to analyze the data from a new clinical study, investigating whether a combination of traditional Chinese medicine symptoms and standard Western medicine risk factors can increase discriminative accuracy in diagnosing osteoporosis (OP). Based on the results, we conclude that we can make a better diagnosis of primary OP by combining traditional Chinese medicine symptoms with Western medicine risk factors.

KW - AUC

KW - Classification

KW - ROC

KW - Variable selection

UR - http://www.scopus.com/inward/record.url?scp=84863229386&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84863229386&partnerID=8YFLogxK

U2 - 10.1002/sim.3980

DO - 10.1002/sim.3980

M3 - Article

C2 - 21290404

AN - SCOPUS:84863229386

VL - 31

SP - 628

EP - 635

JO - Statistics in Medicine

JF - Statistics in Medicine

SN - 0277-6715

IS - 7

ER -