• Publication
  • 2013
  • Issue No. 1 - Jan.-Feb.
  • Abstract - The Receiver Operational Characteristic for Binary Classification with Multiple Indices and Its Application to the Neuroimaging Study of Alzheimer's Disease
 This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
The Receiver Operational Characteristic for Binary Classification with Multiple Indices and Its Application to the Neuroimaging Study of Alzheimer's Disease
Jan.-Feb. 2013 (vol. 10 no. 1)
pp. 173-180
Xia Wu, State Key Lab. of Cognitive Neurosci. & Learning, Beijing Normal Univ., Beijing, China
Juan Li, State Key Lab. of Cognitive Neurosci. & Learning, Beijing Normal Univ., Beijing, China
Napatkamon Ayutyanont, Banner Good Samaritan PET Center, Banner Alzheimer's Inst. (BAI), Phoenix, AZ, USA
Hillary Protas, Banner Good Samaritan PET Center, Banner Alzheimer's Inst. (BAI), Phoenix, AZ, USA
William Jagust, Sch. of Public Health, Univ. of California Berkeley, Berkeley, CA, USA
Adam Fleisher, Banner Good Samaritan PET Center, Banner Alzheimer's Inst. (BAI), Phoenix, AZ, USA
Eric Reiman, Banner Good Samaritan PET Center, Banner Alzheimer's Inst. (BAI), Phoenix, AZ, USA
Li Yao, State Key Lab. of Cognitive Neurosci. & Learning, Beijing Normal Univ., Beijing, China
Kewei Chen, Banner Good Samaritan PET Center, Banner Alzheimer's Inst. (BAI), Phoenix, AZ, USA
Given a single index, the receiver operational characteristic (ROC) curve analysis is routinely utilized for characterizing performances in distinguishing two conditions/groups in terms of sensitivity and specificity. Given the availability of multiple data sources (referred to as multi-indices), such as multimodal neuroimaging data sets, cognitive tests, and clinical ratings and genomic data in Alzheimer's disease (AD) studies, the single-index-based ROC underutilizes all available information. For a longtime, a number of algorithmic/analytic approaches combining multiple indices have been widely used to simultaneously incorporate multiple sources. In this study, we propose an alternative for combining multiple indices using logical operations, such as “AND,” “OR,” and “at least n” (where n is an integer), to construct multivariate ROC (multiV-ROC) and characterize the sensitivity and specificity statistically associated with the use of multiple indices. With and without the “leave-one-out” cross-validation, we used two data sets from AD studies to showcase the potentially increased sensitivity/specificity of the multiV-ROC in comparison to the single-index ROC and linear discriminant analysis (an analytic way of combining multi-indices). We conclude that, for the data sets we investigated, the proposed multiV-ROC approach is capable of providing a natural and practical alternative with improved classification accuracy as compared to univariate ROC and linear discriminant analysis.
Index Terms:
Indexes,Sensitivity and specificity,Alzheimer's disease,Human computer interaction,Neuroimaging,Accuracy,Biomarkers,receiver operational characteristic (ROC),Alzheimer's dementia (AD),multiple indices,multiV-ROC
Citation:
Xia Wu, Juan Li, Napatkamon Ayutyanont, Hillary Protas, William Jagust, Adam Fleisher, Eric Reiman, Li Yao, Kewei Chen, "The Receiver Operational Characteristic for Binary Classification with Multiple Indices and Its Application to the Neuroimaging Study of Alzheimer's Disease," IEEE/ACM Transactions on Computational Biology and Bioinformatics, vol. 10, no. 1, pp. 173-180, Jan.-Feb. 2013, doi:10.1109/TCBB.2012.141
Usage of this product signifies your acceptance of the Terms of Use.