Early Indications of Future Cognitive Decline: Stable versus Declining Controls

Angela Rizk-Jackson, Philip Insel, Ronald Carl Petersen, Paul Aisen, Clifford R Jr. Jack, Michael Weiner

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

This study aimed to identify baseline features of normal subjects that are associated with subsequent cognitive decline. Publicly available data from the Alzheimer's Disease Neuroimaging Initiative was used to find differences in baseline clinical assessments (ADAScog, AVLT, FAQ) between cognitively healthy individuals who will suffer cognitive decline within 48 months and those who will remain stable for that period. Linear regression models indicated an individual's conversion status was significantly associated with certain baseline neuroimaging measures, including posterior cingulate glucose metabolism. Linear Discriminant Analysis models built with baseline features derived from MRI and FDG-PET measures were capable of successfully predicting whether an individual will convert to MCI within 48 months or remain cognitively stable. The findings from this study support the idea that there exist informative differences between normal people who will later develop cognitive impairments and those who will remain cognitively stable for up to four years. Further, the feasibility of developing predictive models that can detect early states of cognitive decline in seemingly normal individuals was demonstrated.

Original languageEnglish (US)
Article numbere74062
JournalPLoS One
Volume8
Issue number9
DOIs
StatePublished - Sep 9 2013

Fingerprint

Neuroimaging
Linear Models
Discriminant analysis
Alzheimer disease
Linear regression
Metabolism
discriminant analysis
Magnetic resonance imaging
Gyrus Cinguli
Discriminant Analysis
Glucose
Alzheimer Disease
glucose
metabolism
Cognitive Dysfunction

ASJC Scopus subject areas

  • Agricultural and Biological Sciences(all)
  • Biochemistry, Genetics and Molecular Biology(all)
  • Medicine(all)

Cite this

Early Indications of Future Cognitive Decline : Stable versus Declining Controls. / Rizk-Jackson, Angela; Insel, Philip; Petersen, Ronald Carl; Aisen, Paul; Jack, Clifford R Jr.; Weiner, Michael.

In: PLoS One, Vol. 8, No. 9, e74062, 09.09.2013.

Research output: Contribution to journalArticle

Rizk-Jackson, Angela ; Insel, Philip ; Petersen, Ronald Carl ; Aisen, Paul ; Jack, Clifford R Jr. ; Weiner, Michael. / Early Indications of Future Cognitive Decline : Stable versus Declining Controls. In: PLoS One. 2013 ; Vol. 8, No. 9.
@article{01d205faf35d48edab96c01732c8a88c,
title = "Early Indications of Future Cognitive Decline: Stable versus Declining Controls",
abstract = "This study aimed to identify baseline features of normal subjects that are associated with subsequent cognitive decline. Publicly available data from the Alzheimer's Disease Neuroimaging Initiative was used to find differences in baseline clinical assessments (ADAScog, AVLT, FAQ) between cognitively healthy individuals who will suffer cognitive decline within 48 months and those who will remain stable for that period. Linear regression models indicated an individual's conversion status was significantly associated with certain baseline neuroimaging measures, including posterior cingulate glucose metabolism. Linear Discriminant Analysis models built with baseline features derived from MRI and FDG-PET measures were capable of successfully predicting whether an individual will convert to MCI within 48 months or remain cognitively stable. The findings from this study support the idea that there exist informative differences between normal people who will later develop cognitive impairments and those who will remain cognitively stable for up to four years. Further, the feasibility of developing predictive models that can detect early states of cognitive decline in seemingly normal individuals was demonstrated.",
author = "Angela Rizk-Jackson and Philip Insel and Petersen, {Ronald Carl} and Paul Aisen and Jack, {Clifford R Jr.} and Michael Weiner",
year = "2013",
month = "9",
day = "9",
doi = "10.1371/journal.pone.0074062",
language = "English (US)",
volume = "8",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "9",

}

TY - JOUR

T1 - Early Indications of Future Cognitive Decline

T2 - Stable versus Declining Controls

AU - Rizk-Jackson, Angela

AU - Insel, Philip

AU - Petersen, Ronald Carl

AU - Aisen, Paul

AU - Jack, Clifford R Jr.

AU - Weiner, Michael

PY - 2013/9/9

Y1 - 2013/9/9

N2 - This study aimed to identify baseline features of normal subjects that are associated with subsequent cognitive decline. Publicly available data from the Alzheimer's Disease Neuroimaging Initiative was used to find differences in baseline clinical assessments (ADAScog, AVLT, FAQ) between cognitively healthy individuals who will suffer cognitive decline within 48 months and those who will remain stable for that period. Linear regression models indicated an individual's conversion status was significantly associated with certain baseline neuroimaging measures, including posterior cingulate glucose metabolism. Linear Discriminant Analysis models built with baseline features derived from MRI and FDG-PET measures were capable of successfully predicting whether an individual will convert to MCI within 48 months or remain cognitively stable. The findings from this study support the idea that there exist informative differences between normal people who will later develop cognitive impairments and those who will remain cognitively stable for up to four years. Further, the feasibility of developing predictive models that can detect early states of cognitive decline in seemingly normal individuals was demonstrated.

AB - This study aimed to identify baseline features of normal subjects that are associated with subsequent cognitive decline. Publicly available data from the Alzheimer's Disease Neuroimaging Initiative was used to find differences in baseline clinical assessments (ADAScog, AVLT, FAQ) between cognitively healthy individuals who will suffer cognitive decline within 48 months and those who will remain stable for that period. Linear regression models indicated an individual's conversion status was significantly associated with certain baseline neuroimaging measures, including posterior cingulate glucose metabolism. Linear Discriminant Analysis models built with baseline features derived from MRI and FDG-PET measures were capable of successfully predicting whether an individual will convert to MCI within 48 months or remain cognitively stable. The findings from this study support the idea that there exist informative differences between normal people who will later develop cognitive impairments and those who will remain cognitively stable for up to four years. Further, the feasibility of developing predictive models that can detect early states of cognitive decline in seemingly normal individuals was demonstrated.

UR - http://www.scopus.com/inward/record.url?scp=84883619455&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84883619455&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0074062

DO - 10.1371/journal.pone.0074062

M3 - Article

C2 - 24040166

AN - SCOPUS:84883619455

VL - 8

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 9

M1 - e74062

ER -