Routine magnetoencephalography in memory clinic patients: A machine learning approach

Alida A Gouw; Arjan Hillebrand; Deborah N Schoonhoven; Matteo Demuru; Peterjan Ris; Philip Scheltens; Cornelis J Stam

doi:https://doi.org/10.1002/dad2.12227

Routine magnetoencephalography in memory clinic patients: A machine learning approach

Alida A Gouw, Arjan Hillebrand, Deborah N Schoonhoven, Matteo Demuru, Peterjan Ris, Philip Scheltens, Cornelis J Stam

Research output: Contribution to journal › Article › Academic › peer-review

Abstract

Introduction: We report the routine application of magnetoencephalography (MEG) in a memory clinic, and its value in the discrimination of patients with Alzheimer's disease (AD) dementia from controls.

Methods: Three hundred sixty-six patients visiting our memory clinic underwent MEG recording. Source-reconstructed MEG data were visually assessed and evaluated in the context of clinical findings and other diagnostic markers. We analyzed the diagnostic accuracy of MEG spectral measures in the discrimination of individual AD dementia patients (n = 40) from subjective cognitive decline (SCD) patients (n = 40) using random forest models.

Results: Best discrimination was obtained using a combination of relative theta and delta power (accuracy 0.846, sensitivity 0.855, specificity 0.837). The results were validated in an independent cohort. Hippocampal and thalamic regions, besides temporal-occipital lobes, contributed considerably to the model.

Discussion: MEG has been implemented successfully in the workup of memory clinic patients and has value in diagnostic decision-making.

Original language	English
Pages (from-to)	e12227
Journal	Alzheimer's & Dementia: Diagnosis, Assessment & Disease Monitoring
Volume	13
Issue number	1
DOIs	https://doi.org/10.1002/dad2.12227
Publication status	Published - Oct 2021

Access to Document

https://doi.org/10.1002/dad2.12227

Cite this

@article{209bc2b72fb849f58d638ecbfc25ac4d,

title = "Routine magnetoencephalography in memory clinic patients: A machine learning approach",

abstract = "Introduction: We report the routine application of magnetoencephalography (MEG) in a memory clinic, and its value in the discrimination of patients with Alzheimer's disease (AD) dementia from controls.Methods: Three hundred sixty-six patients visiting our memory clinic underwent MEG recording. Source-reconstructed MEG data were visually assessed and evaluated in the context of clinical findings and other diagnostic markers. We analyzed the diagnostic accuracy of MEG spectral measures in the discrimination of individual AD dementia patients (n = 40) from subjective cognitive decline (SCD) patients (n = 40) using random forest models.Results: Best discrimination was obtained using a combination of relative theta and delta power (accuracy 0.846, sensitivity 0.855, specificity 0.837). The results were validated in an independent cohort. Hippocampal and thalamic regions, besides temporal-occipital lobes, contributed considerably to the model.Discussion: MEG has been implemented successfully in the workup of memory clinic patients and has value in diagnostic decision-making.",

author = "Gouw, {Alida A} and Arjan Hillebrand and Schoonhoven, {Deborah N} and Matteo Demuru and Peterjan Ris and Philip Scheltens and Stam, {Cornelis J}",

note = "{\textcopyright} 2021 The Authors. Alzheimer's & Dementia: Diagnosis, Assessment & Disease Monitoring published by Wiley Periodicals, LLC on behalf of Alzheimer's Association.",

year = "2021",

month = oct,

doi = "https://doi.org/10.1002/dad2.12227",

language = "English",

volume = "13",

pages = "e12227",

journal = "Alzheimer's & Dementia: Diagnosis, Assessment & Disease Monitoring",

issn = "2352-8729",

publisher = "Elsevier BV",

number = "1",

}

TY - JOUR

T1 - Routine magnetoencephalography in memory clinic patients

T2 - A machine learning approach

AU - Gouw, Alida A

AU - Hillebrand, Arjan

AU - Schoonhoven, Deborah N

AU - Demuru, Matteo

AU - Ris, Peterjan

AU - Scheltens, Philip

AU - Stam, Cornelis J

PY - 2021/10

Y1 - 2021/10

N2 - Introduction: We report the routine application of magnetoencephalography (MEG) in a memory clinic, and its value in the discrimination of patients with Alzheimer's disease (AD) dementia from controls.Methods: Three hundred sixty-six patients visiting our memory clinic underwent MEG recording. Source-reconstructed MEG data were visually assessed and evaluated in the context of clinical findings and other diagnostic markers. We analyzed the diagnostic accuracy of MEG spectral measures in the discrimination of individual AD dementia patients (n = 40) from subjective cognitive decline (SCD) patients (n = 40) using random forest models.Results: Best discrimination was obtained using a combination of relative theta and delta power (accuracy 0.846, sensitivity 0.855, specificity 0.837). The results were validated in an independent cohort. Hippocampal and thalamic regions, besides temporal-occipital lobes, contributed considerably to the model.Discussion: MEG has been implemented successfully in the workup of memory clinic patients and has value in diagnostic decision-making.

AB - Introduction: We report the routine application of magnetoencephalography (MEG) in a memory clinic, and its value in the discrimination of patients with Alzheimer's disease (AD) dementia from controls.Methods: Three hundred sixty-six patients visiting our memory clinic underwent MEG recording. Source-reconstructed MEG data were visually assessed and evaluated in the context of clinical findings and other diagnostic markers. We analyzed the diagnostic accuracy of MEG spectral measures in the discrimination of individual AD dementia patients (n = 40) from subjective cognitive decline (SCD) patients (n = 40) using random forest models.Results: Best discrimination was obtained using a combination of relative theta and delta power (accuracy 0.846, sensitivity 0.855, specificity 0.837). The results were validated in an independent cohort. Hippocampal and thalamic regions, besides temporal-occipital lobes, contributed considerably to the model.Discussion: MEG has been implemented successfully in the workup of memory clinic patients and has value in diagnostic decision-making.

U2 - https://doi.org/10.1002/dad2.12227

DO - https://doi.org/10.1002/dad2.12227

M3 - Article

C2 - 34568539

SN - 2352-8729

VL - 13

SP - e12227

JO - Alzheimer's & Dementia: Diagnosis, Assessment & Disease Monitoring

JF - Alzheimer's & Dementia: Diagnosis, Assessment & Disease Monitoring

IS - 1

ER -