Classification of Healthy Subjects and Alzheimer’s Disease Patients with Dementia from Cortical Sources of Resting State EEG Rhythms: Comparing Different Approaches

C. Del Percio, V. Bevilacqua, A. Brunetti, R. Lizio, A. Soricelli, R. Ferri, F. Nobili, L. Gesualdo, G. Logroscino, M. De Tommaso, A. I. Triggiani, G. B. Frisoni, C. Babiloni

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Here, we tested that healthy elderly (Nold) and Alzheimer’s disease (AD) individuals can be discriminated with a moderate accuracy using resting state eyes-closed electroencephalographic (rsEEG) markers. Eyes-closed rsEEG data were collected in 100 Nold and 120 AD subjects. eLORETA freeware estimated the source current density (SCD) and functional connectivity (lagged linear connectivity, LLC) in frontal, central, parietal, occipital, temporal, and limbic regions. Delta (2–4 Hz), theta (4–8 Hz), alpha 1 (8–10.5 Hz), and alpha 2 (10.5–13 Hz) were the frequency bands of interest. Univariate (i.e., single rsEEG marker with receiver operating characteristic, ROC, curve) and multivariate (i.e., multiple rsEEG markers with artificial neural networks, ANNs) classifiers were used. The best accuracy was of 76% with univariate classifiers and 77% with multiple classifiers. The present results suggest that both univariate and multivariate rsEEG classifiers allowed a moderate classification rate between Nold and AD individuals. Interestingly, the accuracy based on multiple rsEEG markers as inputs to ANNs was similar to that obtained with a single rsEEG marker, unveiling their information redundancy for classification purposes. In future AD studies, multiple rsEEG markers should also include other classes of independent linear (i.e. directed transfer function) and nonlinear (i.e. entropy) variables to improve the classification.

LanguageEnglish
Title of host publicationBiosystems and Biorobotics
PublisherSpringer International Publishing AG
Pages977-981
Number of pages5
DOIs
Publication statusPublished - Jan 1 2019

Publication series

NameBiosystems and Biorobotics
Volume21
ISSN (Print)2195-3562
ISSN (Electronic)2195-3570

Fingerprint

Electroencephalography
Classifiers
Neural networks
Frequency bands
Transfer functions
Redundancy
Current density
Entropy

ASJC Scopus subject areas

  • Biomedical Engineering
  • Mechanical Engineering
  • Artificial Intelligence

Cite this

Classification of Healthy Subjects and Alzheimer’s Disease Patients with Dementia from Cortical Sources of Resting State EEG Rhythms : Comparing Different Approaches. / Del Percio, C.; Bevilacqua, V.; Brunetti, A.; Lizio, R.; Soricelli, A.; Ferri, R.; Nobili, F.; Gesualdo, L.; Logroscino, G.; De Tommaso, M.; Triggiani, A. I.; Frisoni, G. B.; Babiloni, C.

Biosystems and Biorobotics. Springer International Publishing AG, 2019. p. 977-981 (Biosystems and Biorobotics; Vol. 21).

Research output: Chapter in Book/Report/Conference proceedingChapter

Del Percio, C, Bevilacqua, V, Brunetti, A, Lizio, R, Soricelli, A, Ferri, R, Nobili, F, Gesualdo, L, Logroscino, G, De Tommaso, M, Triggiani, AI, Frisoni, GB & Babiloni, C 2019, Classification of Healthy Subjects and Alzheimer’s Disease Patients with Dementia from Cortical Sources of Resting State EEG Rhythms: Comparing Different Approaches. in Biosystems and Biorobotics. Biosystems and Biorobotics, vol. 21, Springer International Publishing AG, pp. 977-981. https://doi.org/10.1007/978-3-030-01845-0_196
Del Percio, C. ; Bevilacqua, V. ; Brunetti, A. ; Lizio, R. ; Soricelli, A. ; Ferri, R. ; Nobili, F. ; Gesualdo, L. ; Logroscino, G. ; De Tommaso, M. ; Triggiani, A. I. ; Frisoni, G. B. ; Babiloni, C. / Classification of Healthy Subjects and Alzheimer’s Disease Patients with Dementia from Cortical Sources of Resting State EEG Rhythms : Comparing Different Approaches. Biosystems and Biorobotics. Springer International Publishing AG, 2019. pp. 977-981 (Biosystems and Biorobotics).
@inbook{d3054d5bc92047c79d769c1411f3d9e0,
title = "Classification of Healthy Subjects and Alzheimer’s Disease Patients with Dementia from Cortical Sources of Resting State EEG Rhythms: Comparing Different Approaches",
abstract = "Here, we tested that healthy elderly (Nold) and Alzheimer’s disease (AD) individuals can be discriminated with a moderate accuracy using resting state eyes-closed electroencephalographic (rsEEG) markers. Eyes-closed rsEEG data were collected in 100 Nold and 120 AD subjects. eLORETA freeware estimated the source current density (SCD) and functional connectivity (lagged linear connectivity, LLC) in frontal, central, parietal, occipital, temporal, and limbic regions. Delta (2–4 Hz), theta (4–8 Hz), alpha 1 (8–10.5{\^A} Hz), and alpha 2 (10.5–13 Hz) were the frequency bands of interest. Univariate (i.e., single rsEEG marker with receiver operating characteristic, ROC, curve) and multivariate (i.e., multiple rsEEG markers with artificial neural networks, ANNs) classifiers were used. The best accuracy was of 76{\%} with univariate classifiers and 77{\%} with multiple classifiers. The present results suggest that both univariate and multivariate rsEEG classifiers allowed a moderate classification rate between Nold and AD individuals. Interestingly, the accuracy based on multiple rsEEG markers as inputs to ANNs was similar to that obtained with a single rsEEG marker, unveiling their information redundancy for classification purposes. In future AD studies, multiple rsEEG markers should also include other classes of independent linear (i.e. directed transfer function) and nonlinear (i.e. entropy) variables to improve the classification.",
author = "{Del Percio}, C. and V. Bevilacqua and A. Brunetti and R. Lizio and A. Soricelli and R. Ferri and F. Nobili and L. Gesualdo and G. Logroscino and {De Tommaso}, M. and Triggiani, {A. I.} and Frisoni, {G. B.} and C. Babiloni",
year = "2019",
month = "1",
day = "1",
doi = "10.1007/978-3-030-01845-0_196",
language = "English",
series = "Biosystems and Biorobotics",
publisher = "Springer International Publishing AG",
pages = "977--981",
booktitle = "Biosystems and Biorobotics",
address = "Switzerland",

}

TY - CHAP

T1 - Classification of Healthy Subjects and Alzheimer’s Disease Patients with Dementia from Cortical Sources of Resting State EEG Rhythms

T2 - Comparing Different Approaches

AU - Del Percio, C.

AU - Bevilacqua, V.

AU - Brunetti, A.

AU - Lizio, R.

AU - Soricelli, A.

AU - Ferri, R.

AU - Nobili, F.

AU - Gesualdo, L.

AU - Logroscino, G.

AU - De Tommaso, M.

AU - Triggiani, A. I.

AU - Frisoni, G. B.

AU - Babiloni, C.

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Here, we tested that healthy elderly (Nold) and Alzheimer’s disease (AD) individuals can be discriminated with a moderate accuracy using resting state eyes-closed electroencephalographic (rsEEG) markers. Eyes-closed rsEEG data were collected in 100 Nold and 120 AD subjects. eLORETA freeware estimated the source current density (SCD) and functional connectivity (lagged linear connectivity, LLC) in frontal, central, parietal, occipital, temporal, and limbic regions. Delta (2–4 Hz), theta (4–8 Hz), alpha 1 (8–10.5 Hz), and alpha 2 (10.5–13 Hz) were the frequency bands of interest. Univariate (i.e., single rsEEG marker with receiver operating characteristic, ROC, curve) and multivariate (i.e., multiple rsEEG markers with artificial neural networks, ANNs) classifiers were used. The best accuracy was of 76% with univariate classifiers and 77% with multiple classifiers. The present results suggest that both univariate and multivariate rsEEG classifiers allowed a moderate classification rate between Nold and AD individuals. Interestingly, the accuracy based on multiple rsEEG markers as inputs to ANNs was similar to that obtained with a single rsEEG marker, unveiling their information redundancy for classification purposes. In future AD studies, multiple rsEEG markers should also include other classes of independent linear (i.e. directed transfer function) and nonlinear (i.e. entropy) variables to improve the classification.

AB - Here, we tested that healthy elderly (Nold) and Alzheimer’s disease (AD) individuals can be discriminated with a moderate accuracy using resting state eyes-closed electroencephalographic (rsEEG) markers. Eyes-closed rsEEG data were collected in 100 Nold and 120 AD subjects. eLORETA freeware estimated the source current density (SCD) and functional connectivity (lagged linear connectivity, LLC) in frontal, central, parietal, occipital, temporal, and limbic regions. Delta (2–4 Hz), theta (4–8 Hz), alpha 1 (8–10.5 Hz), and alpha 2 (10.5–13 Hz) were the frequency bands of interest. Univariate (i.e., single rsEEG marker with receiver operating characteristic, ROC, curve) and multivariate (i.e., multiple rsEEG markers with artificial neural networks, ANNs) classifiers were used. The best accuracy was of 76% with univariate classifiers and 77% with multiple classifiers. The present results suggest that both univariate and multivariate rsEEG classifiers allowed a moderate classification rate between Nold and AD individuals. Interestingly, the accuracy based on multiple rsEEG markers as inputs to ANNs was similar to that obtained with a single rsEEG marker, unveiling their information redundancy for classification purposes. In future AD studies, multiple rsEEG markers should also include other classes of independent linear (i.e. directed transfer function) and nonlinear (i.e. entropy) variables to improve the classification.

UR - http://www.scopus.com/inward/record.url?scp=85055322294&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85055322294&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-01845-0_196

DO - 10.1007/978-3-030-01845-0_196

M3 - Chapter

T3 - Biosystems and Biorobotics

SP - 977

EP - 981

BT - Biosystems and Biorobotics

PB - Springer International Publishing AG

ER -