A serum protein-based algorithm for the detection of Alzheimer disease

Sid E. O'Bryant, Guanghua Xiao, Robert Barber, Joan Reisch, Rachelle Doody, Thomas Fairchild, Perrie Adams, Steven Waring, Ramon Diaz-Arrastia

Research output: Contribution to journalArticle

160 Citations (Scopus)

Abstract

Objective: To develop an algorithm that separates patients with Alzheimer disease (AD) from controls. Design: Longitudinal case-control study. Setting: The Texas Alzheimer's Research Consortium project. Patients: We analyzed serum protein-based multiplex biomarker data from 197 patients diagnosed with AD and 203 controls. Main Outcome Measure: The total sample was randomized equally into training and test sets and random forest methods were applied to the training set to create a biomarker risk score. Results: The biomarker risk score had a sensitivity and specificity of 0.80 and 0.91, respectively, and an area under the curve of 0.91 in detecting AD. When age, sex, education, and APOE status were added to the algorithm, the sensitivity, specificity, and area under the curve were 0.94, 0.84, and 0.95, respectively. Conclusions: These initial data suggest that serum protein-based biomarkers can be combined with clinical information to accurately classify AD. A disproportionate number of inflammatory and vascular markers were weighted most heavily in the analyses. Additionally, these markers consistently distinguished cases from controls in significant analysis of microarray, logistic regression, and Wilcoxon analyses, suggesting the existence of an inflammatory-related endophenotype of AD that may provide targeted therapeutic opportunities for this subset of patients.

Original languageEnglish
Pages (from-to)1077-1081
Number of pages5
JournalArchives of Neurology
Volume67
Issue number9
DOIs
StatePublished - Sep 2010

Fingerprint

Blood Proteins
Alzheimer Disease
Biomarkers
Area Under Curve
Endophenotypes
Sensitivity and Specificity
Sex Education
Microarray Analysis
Blood Vessels
Case-Control Studies
Logistic Models
Regression Analysis
Outcome Assessment (Health Care)
Protein
Alzheimer's Disease
Research
Specificity
Therapeutics

Cite this

O'Bryant, Sid E. ; Xiao, Guanghua ; Barber, Robert ; Reisch, Joan ; Doody, Rachelle ; Fairchild, Thomas ; Adams, Perrie ; Waring, Steven ; Diaz-Arrastia, Ramon. / A serum protein-based algorithm for the detection of Alzheimer disease. In: Archives of Neurology. 2010 ; Vol. 67, No. 9. pp. 1077-1081.
@article{e67fc8f8555d4fd394531308069febcd,
title = "A serum protein-based algorithm for the detection of Alzheimer disease",
abstract = "Objective: To develop an algorithm that separates patients with Alzheimer disease (AD) from controls. Design: Longitudinal case-control study. Setting: The Texas Alzheimer's Research Consortium project. Patients: We analyzed serum protein-based multiplex biomarker data from 197 patients diagnosed with AD and 203 controls. Main Outcome Measure: The total sample was randomized equally into training and test sets and random forest methods were applied to the training set to create a biomarker risk score. Results: The biomarker risk score had a sensitivity and specificity of 0.80 and 0.91, respectively, and an area under the curve of 0.91 in detecting AD. When age, sex, education, and APOE status were added to the algorithm, the sensitivity, specificity, and area under the curve were 0.94, 0.84, and 0.95, respectively. Conclusions: These initial data suggest that serum protein-based biomarkers can be combined with clinical information to accurately classify AD. A disproportionate number of inflammatory and vascular markers were weighted most heavily in the analyses. Additionally, these markers consistently distinguished cases from controls in significant analysis of microarray, logistic regression, and Wilcoxon analyses, suggesting the existence of an inflammatory-related endophenotype of AD that may provide targeted therapeutic opportunities for this subset of patients.",
author = "O'Bryant, {Sid E.} and Guanghua Xiao and Robert Barber and Joan Reisch and Rachelle Doody and Thomas Fairchild and Perrie Adams and Steven Waring and Ramon Diaz-Arrastia",
year = "2010",
month = "9",
doi = "10.1001/archneurol.2010.215",
language = "English",
volume = "67",
pages = "1077--1081",
journal = "Archives of Neurology",
issn = "0003-9942",
publisher = "American Medical Association",
number = "9",

}

O'Bryant, SE, Xiao, G, Barber, R, Reisch, J, Doody, R, Fairchild, T, Adams, P, Waring, S & Diaz-Arrastia, R 2010, 'A serum protein-based algorithm for the detection of Alzheimer disease', Archives of Neurology, vol. 67, no. 9, pp. 1077-1081. https://doi.org/10.1001/archneurol.2010.215

A serum protein-based algorithm for the detection of Alzheimer disease. / O'Bryant, Sid E.; Xiao, Guanghua; Barber, Robert; Reisch, Joan; Doody, Rachelle; Fairchild, Thomas; Adams, Perrie; Waring, Steven; Diaz-Arrastia, Ramon.

In: Archives of Neurology, Vol. 67, No. 9, 09.2010, p. 1077-1081.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A serum protein-based algorithm for the detection of Alzheimer disease

AU - O'Bryant, Sid E.

AU - Xiao, Guanghua

AU - Barber, Robert

AU - Reisch, Joan

AU - Doody, Rachelle

AU - Fairchild, Thomas

AU - Adams, Perrie

AU - Waring, Steven

AU - Diaz-Arrastia, Ramon

PY - 2010/9

Y1 - 2010/9

N2 - Objective: To develop an algorithm that separates patients with Alzheimer disease (AD) from controls. Design: Longitudinal case-control study. Setting: The Texas Alzheimer's Research Consortium project. Patients: We analyzed serum protein-based multiplex biomarker data from 197 patients diagnosed with AD and 203 controls. Main Outcome Measure: The total sample was randomized equally into training and test sets and random forest methods were applied to the training set to create a biomarker risk score. Results: The biomarker risk score had a sensitivity and specificity of 0.80 and 0.91, respectively, and an area under the curve of 0.91 in detecting AD. When age, sex, education, and APOE status were added to the algorithm, the sensitivity, specificity, and area under the curve were 0.94, 0.84, and 0.95, respectively. Conclusions: These initial data suggest that serum protein-based biomarkers can be combined with clinical information to accurately classify AD. A disproportionate number of inflammatory and vascular markers were weighted most heavily in the analyses. Additionally, these markers consistently distinguished cases from controls in significant analysis of microarray, logistic regression, and Wilcoxon analyses, suggesting the existence of an inflammatory-related endophenotype of AD that may provide targeted therapeutic opportunities for this subset of patients.

AB - Objective: To develop an algorithm that separates patients with Alzheimer disease (AD) from controls. Design: Longitudinal case-control study. Setting: The Texas Alzheimer's Research Consortium project. Patients: We analyzed serum protein-based multiplex biomarker data from 197 patients diagnosed with AD and 203 controls. Main Outcome Measure: The total sample was randomized equally into training and test sets and random forest methods were applied to the training set to create a biomarker risk score. Results: The biomarker risk score had a sensitivity and specificity of 0.80 and 0.91, respectively, and an area under the curve of 0.91 in detecting AD. When age, sex, education, and APOE status were added to the algorithm, the sensitivity, specificity, and area under the curve were 0.94, 0.84, and 0.95, respectively. Conclusions: These initial data suggest that serum protein-based biomarkers can be combined with clinical information to accurately classify AD. A disproportionate number of inflammatory and vascular markers were weighted most heavily in the analyses. Additionally, these markers consistently distinguished cases from controls in significant analysis of microarray, logistic regression, and Wilcoxon analyses, suggesting the existence of an inflammatory-related endophenotype of AD that may provide targeted therapeutic opportunities for this subset of patients.

UR - http://www.scopus.com/inward/record.url?scp=77957066281&partnerID=8YFLogxK

U2 - 10.1001/archneurol.2010.215

DO - 10.1001/archneurol.2010.215

M3 - Article

C2 - 20837851

AN - SCOPUS:77957066281

VL - 67

SP - 1077

EP - 1081

JO - Archives of Neurology

JF - Archives of Neurology

SN - 0003-9942

IS - 9

ER -