©1996-2009 All Rights Reserved. Online Journal of Bioinformatics . You may not store
these pages in any form except for your own personal use. All other usage or
distribution is illegal under international copyright treaties. Permission to
use any of these pages in any other way besides the
before mentioned must be gained in writing from the publisher. This
article is exclusively copyrighted in its entirety to OJB publications. This
article may be copied once but may not be, reproduced or
re-transmitted without the express permission of the editors. This journal satisfies the refereeing requirements
(DEST) for the Higher Education Research Data Collection (Australia). Linking:To link to this page or any pages linking to this page you must link
directly to this page only here rather than put up your own page.
OJB®
Online Journal of Bioinformatics ©
7 (1) : 22-31, 2006
Classification of incipient Alzheimer patients
using gene expression data:
Dealing with potential misdiagnosis
Robbins K1,
Joseph S1, Zhang W1, Rekaya R1,2, Bertrand JK1
1Department of Animal and Dairy Science, 2Department of
ABSTRACT
Robbins K, Joseph S, Zhang W, Rekaya R, Bertrand JK, Classification of incipient
Alzheimer patients using gene expression data: Dealing with potential
misdiagnosis, Online J Bioinformatics 7 (1) : 22-31, 2006.
A latent-threshold model and misclassification
algorithm were implemented to predict the Alzheimer’s disease (AD) status of 16
subjects using gene expression data. Each of the 16 subjects was initially
classified as healthy or incipient AD using clinical tests. To examine possible
age effects on the diagnosis of incipient AD, two datasets were created
containing the age unadjusted (D1) and age adjusted (D2) expression of the 100
most informative genes. Control and incipient subjects were clustered into old
and young age classes which were then used for age adjustments. Results
obtained without invoking the misclassification algorithm showed limited
predictive power of the model using either D1 or D2. When the misclassification
algorithm was invoked, four subjects were identified as being potentially
misdiagnosed. Results obtained after adjustment of the AD status (switching of
the binary status) of these four samples showed a significant increase in the
model’s predictive ability. Further examination of the misdiagnosed samples,
using plots and 
tests,
showed that the gene expression of these samples agreed more with the new than
the initial classification. Similar results were obtained using either D1 or
D2. Interestingly, all of the misdiagnosed subjects were originally classified
as either an old control or a young incipient. These results suggest that gene
expression can be used to improve AD diagnosis by identifying potentially
misdiagnosed subjects in the training set. Moreover, it was found that age may
have little influence on genes highly correlated with AD status, but it could
affect diagnosis based on clinical tests.
Key words: Latent-threshold model, Misclassification
algorithm, Alzheimer’s disease