MRI predictors of amyloid pathology

Results from the EMIF-AD Multimodal Biomarker Discovery study

Mara Ten Kate, Alberto Redolfi, Enrico Peira, Isabelle Bos, Stephanie J. Vos, Rik Vandenberghe, Silvy Gabel, Jolien Schaeverbeke, Philip Scheltens, Olivier Blin, Jill C. Richardson, Regis Bordet, Anders Wallin, Carl Eckerstrom, José Luis Molinuevo, Sebastiaan Engelborghs, Christine Van Broeckhoven, Pablo Martinez-Lage, Julius Popp, Magdalini Tsolaki & 17 others Frans R.J. Verhey, Alison L. Baird, Cristina Legido-Quigley, Lars Bertram, Valerija Dobricic, Henrik Zetterberg, Simon Lovestone, Johannes Streffer, Silvia Bianchetti, Gerald P. Novak, Jerome Revillard, Mark F. Gordon, Zhiyong Xie, Viktor Wottschel, Giovanni Frisoni, Pieter Jelle Visser, Frederik Barkhof

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Background: With the shift of research focus towards the pre-dementia stage of Alzheimer's disease (AD), there is an urgent need for reliable, non-invasive biomarkers to predict amyloid pathology. The aim of this study was to assess whether easily obtainable measures from structural MRI, combined with demographic data, cognitive data and apolipoprotein E (APOE) ϵ4 genotype, can be used to predict amyloid pathology using machine-learning classification. Methods: We examined 810 subjects with structural MRI data and amyloid markers from the European Medical Information Framework for Alzheimer's Disease Multimodal Biomarker Discovery study, including subjects with normal cognition (CN, n = 337, age 66.5 ± 7.2, 50% female, 27% amyloid positive), mild cognitive impairment (MCI, n = 375, age 69.1 ± 7.5, 53% female, 63% amyloid positive) and AD dementia (n = 98, age 67.0 ± 7.7, 48% female, 97% amyloid positive). Structural MRI scans were visually assessed and Freesurfer was used to obtain subcortical volumes, cortical thickness and surface area measures. We first assessed univariate associations between MRI measures and amyloid pathology using mixed models. Next, we developed and tested an automated classifier using demographic, cognitive, MRI and APOE ϵ4 information to predict amyloid pathology. A support vector machine (SVM) with nested 10-fold cross-validation was applied to identify a set of markers best discriminating between amyloid positive and amyloid negative subjects. Results: In univariate associations, amyloid pathology was associated with lower subcortical volumes and thinner cortex in AD-signature regions in CN and MCI. The multi-variable SVM classifier provided an area under the curve (AUC) of 0.81 ± 0.07 in MCI and an AUC of 0.74 ± 0.08 in CN. In CN, selected features for the classifier included APOE ϵ4, age, memory scores and several MRI measures such as hippocampus, amygdala and accumbens volumes and cortical thickness in temporal and parahippocampal regions. In MCI, the classifier including demographic and APOE ϵ4 information did not improve after additionally adding imaging measures. Conclusions: Amyloid pathology is associated with changes in structural MRI measures in CN and MCI. An automated classifier based on clinical, imaging and APOE ϵ4 data can identify the presence of amyloid pathology with a moderate level of accuracy. These results could be used in clinical trials to pre-screen subjects for anti-amyloid therapies.

Original languageEnglish
Article number100
JournalAlzheimer's Research and Therapy
Volume10
Issue number1
DOIs
Publication statusPublished - Sep 27 2018

Fingerprint

Amyloid
Alzheimer Disease
Biomarkers
Pathology
Apolipoprotein E4
Demography
Area Under Curve
Temporal Lobe
Amygdala
Cognition
Dementia
Hippocampus
Genotype
Magnetic Resonance Imaging
Clinical Trials

Keywords

  • Alzheimer's disease
  • Amyloid
  • Biomarkers
  • European Medical Information Framework for Alzheimer's Disease
  • Machine learning
  • Magnetic resonance imaging
  • Mild cognitive impairment
  • Support vector machine

ASJC Scopus subject areas

  • Neurology
  • Clinical Neurology
  • Cognitive Neuroscience

Cite this

MRI predictors of amyloid pathology : Results from the EMIF-AD Multimodal Biomarker Discovery study. / Ten Kate, Mara; Redolfi, Alberto; Peira, Enrico; Bos, Isabelle; Vos, Stephanie J.; Vandenberghe, Rik; Gabel, Silvy; Schaeverbeke, Jolien; Scheltens, Philip; Blin, Olivier; Richardson, Jill C.; Bordet, Regis; Wallin, Anders; Eckerstrom, Carl; Molinuevo, José Luis; Engelborghs, Sebastiaan; Van Broeckhoven, Christine; Martinez-Lage, Pablo; Popp, Julius; Tsolaki, Magdalini; Verhey, Frans R.J.; Baird, Alison L.; Legido-Quigley, Cristina; Bertram, Lars; Dobricic, Valerija; Zetterberg, Henrik; Lovestone, Simon; Streffer, Johannes; Bianchetti, Silvia; Novak, Gerald P.; Revillard, Jerome; Gordon, Mark F.; Xie, Zhiyong; Wottschel, Viktor; Frisoni, Giovanni; Visser, Pieter Jelle; Barkhof, Frederik.

In: Alzheimer's Research and Therapy, Vol. 10, No. 1, 100, 27.09.2018.

Research output: Contribution to journalArticle

Ten Kate, M, Redolfi, A, Peira, E, Bos, I, Vos, SJ, Vandenberghe, R, Gabel, S, Schaeverbeke, J, Scheltens, P, Blin, O, Richardson, JC, Bordet, R, Wallin, A, Eckerstrom, C, Molinuevo, JL, Engelborghs, S, Van Broeckhoven, C, Martinez-Lage, P, Popp, J, Tsolaki, M, Verhey, FRJ, Baird, AL, Legido-Quigley, C, Bertram, L, Dobricic, V, Zetterberg, H, Lovestone, S, Streffer, J, Bianchetti, S, Novak, GP, Revillard, J, Gordon, MF, Xie, Z, Wottschel, V, Frisoni, G, Visser, PJ & Barkhof, F 2018, 'MRI predictors of amyloid pathology: Results from the EMIF-AD Multimodal Biomarker Discovery study', Alzheimer's Research and Therapy, vol. 10, no. 1, 100. https://doi.org/10.1186/s13195-018-0428-1
Ten Kate, Mara ; Redolfi, Alberto ; Peira, Enrico ; Bos, Isabelle ; Vos, Stephanie J. ; Vandenberghe, Rik ; Gabel, Silvy ; Schaeverbeke, Jolien ; Scheltens, Philip ; Blin, Olivier ; Richardson, Jill C. ; Bordet, Regis ; Wallin, Anders ; Eckerstrom, Carl ; Molinuevo, José Luis ; Engelborghs, Sebastiaan ; Van Broeckhoven, Christine ; Martinez-Lage, Pablo ; Popp, Julius ; Tsolaki, Magdalini ; Verhey, Frans R.J. ; Baird, Alison L. ; Legido-Quigley, Cristina ; Bertram, Lars ; Dobricic, Valerija ; Zetterberg, Henrik ; Lovestone, Simon ; Streffer, Johannes ; Bianchetti, Silvia ; Novak, Gerald P. ; Revillard, Jerome ; Gordon, Mark F. ; Xie, Zhiyong ; Wottschel, Viktor ; Frisoni, Giovanni ; Visser, Pieter Jelle ; Barkhof, Frederik. / MRI predictors of amyloid pathology : Results from the EMIF-AD Multimodal Biomarker Discovery study. In: Alzheimer's Research and Therapy. 2018 ; Vol. 10, No. 1.
@article{03ab59b333f04d4b823403622d8d4ca7,
title = "MRI predictors of amyloid pathology: Results from the EMIF-AD Multimodal Biomarker Discovery study",
abstract = "Background: With the shift of research focus towards the pre-dementia stage of Alzheimer's disease (AD), there is an urgent need for reliable, non-invasive biomarkers to predict amyloid pathology. The aim of this study was to assess whether easily obtainable measures from structural MRI, combined with demographic data, cognitive data and apolipoprotein E (APOE) ϵ4 genotype, can be used to predict amyloid pathology using machine-learning classification. Methods: We examined 810 subjects with structural MRI data and amyloid markers from the European Medical Information Framework for Alzheimer's Disease Multimodal Biomarker Discovery study, including subjects with normal cognition (CN, n = 337, age 66.5 ± 7.2, 50{\%} female, 27{\%} amyloid positive), mild cognitive impairment (MCI, n = 375, age 69.1 ± 7.5, 53{\%} female, 63{\%} amyloid positive) and AD dementia (n = 98, age 67.0 ± 7.7, 48{\%} female, 97{\%} amyloid positive). Structural MRI scans were visually assessed and Freesurfer was used to obtain subcortical volumes, cortical thickness and surface area measures. We first assessed univariate associations between MRI measures and amyloid pathology using mixed models. Next, we developed and tested an automated classifier using demographic, cognitive, MRI and APOE ϵ4 information to predict amyloid pathology. A support vector machine (SVM) with nested 10-fold cross-validation was applied to identify a set of markers best discriminating between amyloid positive and amyloid negative subjects. Results: In univariate associations, amyloid pathology was associated with lower subcortical volumes and thinner cortex in AD-signature regions in CN and MCI. The multi-variable SVM classifier provided an area under the curve (AUC) of 0.81 ± 0.07 in MCI and an AUC of 0.74 ± 0.08 in CN. In CN, selected features for the classifier included APOE ϵ4, age, memory scores and several MRI measures such as hippocampus, amygdala and accumbens volumes and cortical thickness in temporal and parahippocampal regions. In MCI, the classifier including demographic and APOE ϵ4 information did not improve after additionally adding imaging measures. Conclusions: Amyloid pathology is associated with changes in structural MRI measures in CN and MCI. An automated classifier based on clinical, imaging and APOE ϵ4 data can identify the presence of amyloid pathology with a moderate level of accuracy. These results could be used in clinical trials to pre-screen subjects for anti-amyloid therapies.",
keywords = "Alzheimer's disease, Amyloid, Biomarkers, European Medical Information Framework for Alzheimer's Disease, Machine learning, Magnetic resonance imaging, Mild cognitive impairment, Support vector machine",
author = "{Ten Kate}, Mara and Alberto Redolfi and Enrico Peira and Isabelle Bos and Vos, {Stephanie J.} and Rik Vandenberghe and Silvy Gabel and Jolien Schaeverbeke and Philip Scheltens and Olivier Blin and Richardson, {Jill C.} and Regis Bordet and Anders Wallin and Carl Eckerstrom and Molinuevo, {Jos{\'e} Luis} and Sebastiaan Engelborghs and {Van Broeckhoven}, Christine and Pablo Martinez-Lage and Julius Popp and Magdalini Tsolaki and Verhey, {Frans R.J.} and Baird, {Alison L.} and Cristina Legido-Quigley and Lars Bertram and Valerija Dobricic and Henrik Zetterberg and Simon Lovestone and Johannes Streffer and Silvia Bianchetti and Novak, {Gerald P.} and Jerome Revillard and Gordon, {Mark F.} and Zhiyong Xie and Viktor Wottschel and Giovanni Frisoni and Visser, {Pieter Jelle} and Frederik Barkhof",
year = "2018",
month = "9",
day = "27",
doi = "10.1186/s13195-018-0428-1",
language = "English",
volume = "10",
journal = "Alzheimer's Research and Therapy",
issn = "1758-9193",
publisher = "BioMed Central Ltd.",
number = "1",

}

TY - JOUR

T1 - MRI predictors of amyloid pathology

T2 - Results from the EMIF-AD Multimodal Biomarker Discovery study

AU - Ten Kate, Mara

AU - Redolfi, Alberto

AU - Peira, Enrico

AU - Bos, Isabelle

AU - Vos, Stephanie J.

AU - Vandenberghe, Rik

AU - Gabel, Silvy

AU - Schaeverbeke, Jolien

AU - Scheltens, Philip

AU - Blin, Olivier

AU - Richardson, Jill C.

AU - Bordet, Regis

AU - Wallin, Anders

AU - Eckerstrom, Carl

AU - Molinuevo, José Luis

AU - Engelborghs, Sebastiaan

AU - Van Broeckhoven, Christine

AU - Martinez-Lage, Pablo

AU - Popp, Julius

AU - Tsolaki, Magdalini

AU - Verhey, Frans R.J.

AU - Baird, Alison L.

AU - Legido-Quigley, Cristina

AU - Bertram, Lars

AU - Dobricic, Valerija

AU - Zetterberg, Henrik

AU - Lovestone, Simon

AU - Streffer, Johannes

AU - Bianchetti, Silvia

AU - Novak, Gerald P.

AU - Revillard, Jerome

AU - Gordon, Mark F.

AU - Xie, Zhiyong

AU - Wottschel, Viktor

AU - Frisoni, Giovanni

AU - Visser, Pieter Jelle

AU - Barkhof, Frederik

PY - 2018/9/27

Y1 - 2018/9/27

N2 - Background: With the shift of research focus towards the pre-dementia stage of Alzheimer's disease (AD), there is an urgent need for reliable, non-invasive biomarkers to predict amyloid pathology. The aim of this study was to assess whether easily obtainable measures from structural MRI, combined with demographic data, cognitive data and apolipoprotein E (APOE) ϵ4 genotype, can be used to predict amyloid pathology using machine-learning classification. Methods: We examined 810 subjects with structural MRI data and amyloid markers from the European Medical Information Framework for Alzheimer's Disease Multimodal Biomarker Discovery study, including subjects with normal cognition (CN, n = 337, age 66.5 ± 7.2, 50% female, 27% amyloid positive), mild cognitive impairment (MCI, n = 375, age 69.1 ± 7.5, 53% female, 63% amyloid positive) and AD dementia (n = 98, age 67.0 ± 7.7, 48% female, 97% amyloid positive). Structural MRI scans were visually assessed and Freesurfer was used to obtain subcortical volumes, cortical thickness and surface area measures. We first assessed univariate associations between MRI measures and amyloid pathology using mixed models. Next, we developed and tested an automated classifier using demographic, cognitive, MRI and APOE ϵ4 information to predict amyloid pathology. A support vector machine (SVM) with nested 10-fold cross-validation was applied to identify a set of markers best discriminating between amyloid positive and amyloid negative subjects. Results: In univariate associations, amyloid pathology was associated with lower subcortical volumes and thinner cortex in AD-signature regions in CN and MCI. The multi-variable SVM classifier provided an area under the curve (AUC) of 0.81 ± 0.07 in MCI and an AUC of 0.74 ± 0.08 in CN. In CN, selected features for the classifier included APOE ϵ4, age, memory scores and several MRI measures such as hippocampus, amygdala and accumbens volumes and cortical thickness in temporal and parahippocampal regions. In MCI, the classifier including demographic and APOE ϵ4 information did not improve after additionally adding imaging measures. Conclusions: Amyloid pathology is associated with changes in structural MRI measures in CN and MCI. An automated classifier based on clinical, imaging and APOE ϵ4 data can identify the presence of amyloid pathology with a moderate level of accuracy. These results could be used in clinical trials to pre-screen subjects for anti-amyloid therapies.

AB - Background: With the shift of research focus towards the pre-dementia stage of Alzheimer's disease (AD), there is an urgent need for reliable, non-invasive biomarkers to predict amyloid pathology. The aim of this study was to assess whether easily obtainable measures from structural MRI, combined with demographic data, cognitive data and apolipoprotein E (APOE) ϵ4 genotype, can be used to predict amyloid pathology using machine-learning classification. Methods: We examined 810 subjects with structural MRI data and amyloid markers from the European Medical Information Framework for Alzheimer's Disease Multimodal Biomarker Discovery study, including subjects with normal cognition (CN, n = 337, age 66.5 ± 7.2, 50% female, 27% amyloid positive), mild cognitive impairment (MCI, n = 375, age 69.1 ± 7.5, 53% female, 63% amyloid positive) and AD dementia (n = 98, age 67.0 ± 7.7, 48% female, 97% amyloid positive). Structural MRI scans were visually assessed and Freesurfer was used to obtain subcortical volumes, cortical thickness and surface area measures. We first assessed univariate associations between MRI measures and amyloid pathology using mixed models. Next, we developed and tested an automated classifier using demographic, cognitive, MRI and APOE ϵ4 information to predict amyloid pathology. A support vector machine (SVM) with nested 10-fold cross-validation was applied to identify a set of markers best discriminating between amyloid positive and amyloid negative subjects. Results: In univariate associations, amyloid pathology was associated with lower subcortical volumes and thinner cortex in AD-signature regions in CN and MCI. The multi-variable SVM classifier provided an area under the curve (AUC) of 0.81 ± 0.07 in MCI and an AUC of 0.74 ± 0.08 in CN. In CN, selected features for the classifier included APOE ϵ4, age, memory scores and several MRI measures such as hippocampus, amygdala and accumbens volumes and cortical thickness in temporal and parahippocampal regions. In MCI, the classifier including demographic and APOE ϵ4 information did not improve after additionally adding imaging measures. Conclusions: Amyloid pathology is associated with changes in structural MRI measures in CN and MCI. An automated classifier based on clinical, imaging and APOE ϵ4 data can identify the presence of amyloid pathology with a moderate level of accuracy. These results could be used in clinical trials to pre-screen subjects for anti-amyloid therapies.

KW - Alzheimer's disease

KW - Amyloid

KW - Biomarkers

KW - European Medical Information Framework for Alzheimer's Disease

KW - Machine learning

KW - Magnetic resonance imaging

KW - Mild cognitive impairment

KW - Support vector machine

UR - http://www.scopus.com/inward/record.url?scp=85054093241&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85054093241&partnerID=8YFLogxK

U2 - 10.1186/s13195-018-0428-1

DO - 10.1186/s13195-018-0428-1

M3 - Article

VL - 10

JO - Alzheimer's Research and Therapy

JF - Alzheimer's Research and Therapy

SN - 1758-9193

IS - 1

M1 - 100

ER -