Molecular neuropsychology: Creation of test-specific blood biomarker algorithms

Sid E. O'Bryant, Guanghua Xiao, Robert Barber, C. Munro Cullum, Myron Weiner, James Hall, Melissa Edwards, Paula Grammas, Kirk Wilhelmsen, Rachelle Doody, Ramon Diaz-Arrastia

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Background: Prior work on the link between blood-based biomarkers and cognitive status has largely been based on dichotomous classifications rather than detailed neuropsychological functioning. The current project was designed to create serum-based biomarker algorithms that predict neuropsychological test performance. Methods: A battery of neuropsychological measures was administered. Random forest analyses were utilized to create neuropsychological test-specific biomarker risk scores in a training set that were entered into linear regression models predicting the respective test scores in the test set. Serum multiplex biomarker data were analyzed on 108 proteins from 395 participants (197 Alzheimer patients and 198 controls) from the Texas Alzheimer's Research and Care Consortium. Results: The biomarker risk scores were significant predictors (p < 0.05) of scores on all neuropsychological tests. With the exception of premorbid intellectual status (6.6%), the biomarker risk scores alone accounted for a minimum of 12.9% of the variance in neuropsychological scores. Biomarker algorithms (biomarker risk scores and demographics) accounted for substantially more variance in scores. Review of the variable importance plots indicated differential patterns of biomarker significance for each test, suggesting the possibility of domain-specific biomarker algorithms. Conclusions: Our findings provide proof of concept for a novel area of scientific discovery, which we term 'molecular neuropsychology'.

Original languageEnglish
Pages (from-to)45-57
Number of pages13
JournalDementia and Geriatric Cognitive Disorders
Volume37
Issue number1-2
DOIs
StatePublished - 1 Feb 2014

Fingerprint

Neuropsychology
Hematologic Tests
Biomarkers
Neuropsychological Tests
Linear Models
Serum
Demography

Keywords

  • Algorithms
  • Biomarkers
  • Molecular markers
  • Neuropsychology
  • Psychology

Cite this

O'Bryant, Sid E. ; Xiao, Guanghua ; Barber, Robert ; Cullum, C. Munro ; Weiner, Myron ; Hall, James ; Edwards, Melissa ; Grammas, Paula ; Wilhelmsen, Kirk ; Doody, Rachelle ; Diaz-Arrastia, Ramon. / Molecular neuropsychology : Creation of test-specific blood biomarker algorithms. In: Dementia and Geriatric Cognitive Disorders. 2014 ; Vol. 37, No. 1-2. pp. 45-57.
@article{6a5669e3d720433f8e22a507b81dede0,
title = "Molecular neuropsychology: Creation of test-specific blood biomarker algorithms",
abstract = "Background: Prior work on the link between blood-based biomarkers and cognitive status has largely been based on dichotomous classifications rather than detailed neuropsychological functioning. The current project was designed to create serum-based biomarker algorithms that predict neuropsychological test performance. Methods: A battery of neuropsychological measures was administered. Random forest analyses were utilized to create neuropsychological test-specific biomarker risk scores in a training set that were entered into linear regression models predicting the respective test scores in the test set. Serum multiplex biomarker data were analyzed on 108 proteins from 395 participants (197 Alzheimer patients and 198 controls) from the Texas Alzheimer's Research and Care Consortium. Results: The biomarker risk scores were significant predictors (p < 0.05) of scores on all neuropsychological tests. With the exception of premorbid intellectual status (6.6{\%}), the biomarker risk scores alone accounted for a minimum of 12.9{\%} of the variance in neuropsychological scores. Biomarker algorithms (biomarker risk scores and demographics) accounted for substantially more variance in scores. Review of the variable importance plots indicated differential patterns of biomarker significance for each test, suggesting the possibility of domain-specific biomarker algorithms. Conclusions: Our findings provide proof of concept for a novel area of scientific discovery, which we term 'molecular neuropsychology'.",
keywords = "Algorithms, Biomarkers, Molecular markers, Neuropsychology, Psychology",
author = "O'Bryant, {Sid E.} and Guanghua Xiao and Robert Barber and Cullum, {C. Munro} and Myron Weiner and James Hall and Melissa Edwards and Paula Grammas and Kirk Wilhelmsen and Rachelle Doody and Ramon Diaz-Arrastia",
year = "2014",
month = "2",
day = "1",
doi = "10.1159/000345605",
language = "English",
volume = "37",
pages = "45--57",
journal = "Dementia and Geriatric Cognitive Disorders",
issn = "1420-8008",
publisher = "S. Karger AG",
number = "1-2",

}

O'Bryant, SE, Xiao, G, Barber, R, Cullum, CM, Weiner, M, Hall, J, Edwards, M, Grammas, P, Wilhelmsen, K, Doody, R & Diaz-Arrastia, R 2014, 'Molecular neuropsychology: Creation of test-specific blood biomarker algorithms', Dementia and Geriatric Cognitive Disorders, vol. 37, no. 1-2, pp. 45-57. https://doi.org/10.1159/000345605

Molecular neuropsychology : Creation of test-specific blood biomarker algorithms. / O'Bryant, Sid E.; Xiao, Guanghua; Barber, Robert; Cullum, C. Munro; Weiner, Myron; Hall, James; Edwards, Melissa; Grammas, Paula; Wilhelmsen, Kirk; Doody, Rachelle; Diaz-Arrastia, Ramon.

In: Dementia and Geriatric Cognitive Disorders, Vol. 37, No. 1-2, 01.02.2014, p. 45-57.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Molecular neuropsychology

T2 - Creation of test-specific blood biomarker algorithms

AU - O'Bryant, Sid E.

AU - Xiao, Guanghua

AU - Barber, Robert

AU - Cullum, C. Munro

AU - Weiner, Myron

AU - Hall, James

AU - Edwards, Melissa

AU - Grammas, Paula

AU - Wilhelmsen, Kirk

AU - Doody, Rachelle

AU - Diaz-Arrastia, Ramon

PY - 2014/2/1

Y1 - 2014/2/1

N2 - Background: Prior work on the link between blood-based biomarkers and cognitive status has largely been based on dichotomous classifications rather than detailed neuropsychological functioning. The current project was designed to create serum-based biomarker algorithms that predict neuropsychological test performance. Methods: A battery of neuropsychological measures was administered. Random forest analyses were utilized to create neuropsychological test-specific biomarker risk scores in a training set that were entered into linear regression models predicting the respective test scores in the test set. Serum multiplex biomarker data were analyzed on 108 proteins from 395 participants (197 Alzheimer patients and 198 controls) from the Texas Alzheimer's Research and Care Consortium. Results: The biomarker risk scores were significant predictors (p < 0.05) of scores on all neuropsychological tests. With the exception of premorbid intellectual status (6.6%), the biomarker risk scores alone accounted for a minimum of 12.9% of the variance in neuropsychological scores. Biomarker algorithms (biomarker risk scores and demographics) accounted for substantially more variance in scores. Review of the variable importance plots indicated differential patterns of biomarker significance for each test, suggesting the possibility of domain-specific biomarker algorithms. Conclusions: Our findings provide proof of concept for a novel area of scientific discovery, which we term 'molecular neuropsychology'.

AB - Background: Prior work on the link between blood-based biomarkers and cognitive status has largely been based on dichotomous classifications rather than detailed neuropsychological functioning. The current project was designed to create serum-based biomarker algorithms that predict neuropsychological test performance. Methods: A battery of neuropsychological measures was administered. Random forest analyses were utilized to create neuropsychological test-specific biomarker risk scores in a training set that were entered into linear regression models predicting the respective test scores in the test set. Serum multiplex biomarker data were analyzed on 108 proteins from 395 participants (197 Alzheimer patients and 198 controls) from the Texas Alzheimer's Research and Care Consortium. Results: The biomarker risk scores were significant predictors (p < 0.05) of scores on all neuropsychological tests. With the exception of premorbid intellectual status (6.6%), the biomarker risk scores alone accounted for a minimum of 12.9% of the variance in neuropsychological scores. Biomarker algorithms (biomarker risk scores and demographics) accounted for substantially more variance in scores. Review of the variable importance plots indicated differential patterns of biomarker significance for each test, suggesting the possibility of domain-specific biomarker algorithms. Conclusions: Our findings provide proof of concept for a novel area of scientific discovery, which we term 'molecular neuropsychology'.

KW - Algorithms

KW - Biomarkers

KW - Molecular markers

KW - Neuropsychology

KW - Psychology

UR - http://www.scopus.com/inward/record.url?scp=84896735501&partnerID=8YFLogxK

U2 - 10.1159/000345605

DO - 10.1159/000345605

M3 - Article

C2 - 24107792

AN - SCOPUS:84896735501

VL - 37

SP - 45

EP - 57

JO - Dementia and Geriatric Cognitive Disorders

JF - Dementia and Geriatric Cognitive Disorders

SN - 1420-8008

IS - 1-2

ER -