Integration of cognitive tests and resting state fMRI for the individual identification of mild cognitive impairment

Leandro Beltrachini, Matteo De Marco, Zeike A. Taylor, Jyrki Lötjönen, Alejandro F. Frangi, Annalena Venneri

Research output: Contribution to journalArticleScientificpeer-review

10 Citations (Scopus)

Abstract

Resting-state functional magnetic resonance imaging (RS-fMRI) appears as a promising imaging technique to identify early biomarkers of Alzheimer type neurodegeneration, which can be more sensitive to detect the earliest stages of this disease than structural alterations. Recent findings have highlighted interesting patterns of alteration in resting-state activity at the mild cognitive impairment (MCI) prodromal stage of Alzheimer's disease. However, it has not been established whether RS-fMRI alterations may be of any diagnostic use at the individual patient level and whether parameters derived from RS-fMRI images add any quantitative predictive/classificatory value to standard cognitive tests (CTs). Methods: We computed a set of 444 features based on RS-fMRI and used 21 variables obtained from a neuropsychological assessment battery of tests in 29 MCI patients and 21 healthy controls. We used these indices to evaluate their impact on MCI/healthy control classification using machine learning algorithms and a 10-fold cross validation analysis. Results: A classification accuracy (sensitivity/ specificity/area under curve/positive predictive value/negative predictive value) of 0.9559 (0.9620/0.9470/ 0.9517/0.9720/0.9628) was achieved when using both sets of indices. There was a statistically significant improvement over the use of CTs only, highlighting the superior classificatory role of RS-fMRI. Conclusions: RS-fMRI provides complementary information to CTs for MCI-patient/healthy control individual classification.
Original languageEnglish
Pages (from-to)592-603
JournalCurrent Alzheimer Research
Volume12
Issue number6
DOIs
Publication statusPublished - 2015
MoE publication typeA1 Journal article-refereed

Fingerprint

Magnetic Resonance Imaging
Prodromal Symptoms
Area Under Curve
Cognitive Dysfunction
Alzheimer Disease
Biomarkers
Sensitivity and Specificity

Keywords

  • accuracy
  • AD
  • biomarker
  • classification
  • mild cognitive impairment
  • MCI
  • neurodeneration

Cite this

Beltrachini, Leandro ; De Marco, Matteo ; Taylor, Zeike A. ; Lötjönen, Jyrki ; Frangi, Alejandro F. ; Venneri, Annalena. / Integration of cognitive tests and resting state fMRI for the individual identification of mild cognitive impairment. In: Current Alzheimer Research. 2015 ; Vol. 12, No. 6. pp. 592-603.
@article{088a436148e342b19cb29f405cfb272a,
title = "Integration of cognitive tests and resting state fMRI for the individual identification of mild cognitive impairment",
abstract = "Resting-state functional magnetic resonance imaging (RS-fMRI) appears as a promising imaging technique to identify early biomarkers of Alzheimer type neurodegeneration, which can be more sensitive to detect the earliest stages of this disease than structural alterations. Recent findings have highlighted interesting patterns of alteration in resting-state activity at the mild cognitive impairment (MCI) prodromal stage of Alzheimer's disease. However, it has not been established whether RS-fMRI alterations may be of any diagnostic use at the individual patient level and whether parameters derived from RS-fMRI images add any quantitative predictive/classificatory value to standard cognitive tests (CTs). Methods: We computed a set of 444 features based on RS-fMRI and used 21 variables obtained from a neuropsychological assessment battery of tests in 29 MCI patients and 21 healthy controls. We used these indices to evaluate their impact on MCI/healthy control classification using machine learning algorithms and a 10-fold cross validation analysis. Results: A classification accuracy (sensitivity/ specificity/area under curve/positive predictive value/negative predictive value) of 0.9559 (0.9620/0.9470/ 0.9517/0.9720/0.9628) was achieved when using both sets of indices. There was a statistically significant improvement over the use of CTs only, highlighting the superior classificatory role of RS-fMRI. Conclusions: RS-fMRI provides complementary information to CTs for MCI-patient/healthy control individual classification.",
keywords = "accuracy, AD, biomarker, classification, mild cognitive impairment, MCI, neurodeneration",
author = "Leandro Beltrachini and {De Marco}, Matteo and Taylor, {Zeike A.} and Jyrki L{\"o}tj{\"o}nen and Frangi, {Alejandro F.} and Annalena Venneri",
note = "Project code: 100745",
year = "2015",
doi = "10.2174/156720501206150716120332",
language = "English",
volume = "12",
pages = "592--603",
journal = "Current Alzheimer Research",
issn = "1567-2050",
number = "6",

}

Integration of cognitive tests and resting state fMRI for the individual identification of mild cognitive impairment. / Beltrachini, Leandro; De Marco, Matteo; Taylor, Zeike A.; Lötjönen, Jyrki; Frangi, Alejandro F.; Venneri, Annalena.

In: Current Alzheimer Research, Vol. 12, No. 6, 2015, p. 592-603.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Integration of cognitive tests and resting state fMRI for the individual identification of mild cognitive impairment

AU - Beltrachini, Leandro

AU - De Marco, Matteo

AU - Taylor, Zeike A.

AU - Lötjönen, Jyrki

AU - Frangi, Alejandro F.

AU - Venneri, Annalena

N1 - Project code: 100745

PY - 2015

Y1 - 2015

N2 - Resting-state functional magnetic resonance imaging (RS-fMRI) appears as a promising imaging technique to identify early biomarkers of Alzheimer type neurodegeneration, which can be more sensitive to detect the earliest stages of this disease than structural alterations. Recent findings have highlighted interesting patterns of alteration in resting-state activity at the mild cognitive impairment (MCI) prodromal stage of Alzheimer's disease. However, it has not been established whether RS-fMRI alterations may be of any diagnostic use at the individual patient level and whether parameters derived from RS-fMRI images add any quantitative predictive/classificatory value to standard cognitive tests (CTs). Methods: We computed a set of 444 features based on RS-fMRI and used 21 variables obtained from a neuropsychological assessment battery of tests in 29 MCI patients and 21 healthy controls. We used these indices to evaluate their impact on MCI/healthy control classification using machine learning algorithms and a 10-fold cross validation analysis. Results: A classification accuracy (sensitivity/ specificity/area under curve/positive predictive value/negative predictive value) of 0.9559 (0.9620/0.9470/ 0.9517/0.9720/0.9628) was achieved when using both sets of indices. There was a statistically significant improvement over the use of CTs only, highlighting the superior classificatory role of RS-fMRI. Conclusions: RS-fMRI provides complementary information to CTs for MCI-patient/healthy control individual classification.

AB - Resting-state functional magnetic resonance imaging (RS-fMRI) appears as a promising imaging technique to identify early biomarkers of Alzheimer type neurodegeneration, which can be more sensitive to detect the earliest stages of this disease than structural alterations. Recent findings have highlighted interesting patterns of alteration in resting-state activity at the mild cognitive impairment (MCI) prodromal stage of Alzheimer's disease. However, it has not been established whether RS-fMRI alterations may be of any diagnostic use at the individual patient level and whether parameters derived from RS-fMRI images add any quantitative predictive/classificatory value to standard cognitive tests (CTs). Methods: We computed a set of 444 features based on RS-fMRI and used 21 variables obtained from a neuropsychological assessment battery of tests in 29 MCI patients and 21 healthy controls. We used these indices to evaluate their impact on MCI/healthy control classification using machine learning algorithms and a 10-fold cross validation analysis. Results: A classification accuracy (sensitivity/ specificity/area under curve/positive predictive value/negative predictive value) of 0.9559 (0.9620/0.9470/ 0.9517/0.9720/0.9628) was achieved when using both sets of indices. There was a statistically significant improvement over the use of CTs only, highlighting the superior classificatory role of RS-fMRI. Conclusions: RS-fMRI provides complementary information to CTs for MCI-patient/healthy control individual classification.

KW - accuracy

KW - AD

KW - biomarker

KW - classification

KW - mild cognitive impairment

KW - MCI

KW - neurodeneration

U2 - 10.2174/156720501206150716120332

DO - 10.2174/156720501206150716120332

M3 - Article

VL - 12

SP - 592

EP - 603

JO - Current Alzheimer Research

JF - Current Alzheimer Research

SN - 1567-2050

IS - 6

ER -