Classification of single normal and Alzheimer's disease individuals from cortical sources of resting state EEG rhythms

Claudio Babiloni, Antonio Ivano Triggiani, Roberta Lizio, Susanna Cordone, Giacomo Tattoli, Vitoantonio Bevilacqua, Andrea Soricelli, Raffaele Ferri, Flavio Nobili, L. Gesualdo, José C. Millán-Calenti, Ana Buján, Rosanna Tortelli, Valentina Cardinali, Maria Rosaria Barulli, Antonio Giannini, Pantaleo Spagnolo, Silvia Armenise, Grazia Buenza, Gaetano ScianaticoGiancarlo Logroscino, Giovanni Battista Frisoni, Claudio Del Percio

Research output: Contribution to journalArticle

Abstract

Previous studies have shown abnormal power and functional connectivity of resting state electroencephalographic (EEG) rhythms in groups of Alzheimer's disease (AD) compared to healthy elderly (Nold) subjects. Here we tested the best classification rate of 120 AD patients and 100 matched Nold subjects using EEG markers based on cortical sources of power and functional connectivity of these rhythms. EEG data were recorded during resting state eyes-closed condition. Exact low-resolution brain electromagnetic tomography (eLORETA) estimated the power and functional connectivity of cortical sources in frontal, central, parietal, occipital, temporal, and limbic regions. Delta (2-4 Hz), theta (4-8 Hz), alpha 1 (8-10.5 Hz), alpha 2 (10.5-13 Hz), beta 1 (13-20 Hz), beta 2 (20-30 Hz), and gamma (30-40 Hz) were the frequency bands of interest. The classification rates of interest were those with an area under the receiver operating characteristic curve (AUROC) higher than 0.7 as a threshold for a moderate classification rate (i.e., 70%). Results showed that the following EEG markers overcame this threshold: (i) central, parietal, occipital, temporal, and limbic delta/alpha 1 current density; (ii) central, parietal, occipital temporal, and limbic delta/alpha 2 current density; (iii) frontal theta/alpha 1 current density; (iv) occipital delta/alpha 1 inter-hemispherical connectivity; (v) occipital-temporal theta/alpha 1 right and left intra-hemispherical connectivity; and (vi) parietal-limbic alpha 1 right intra-hemispherical connectivity. Occipital delta/alpha 1 current density showed the best classification rate (sensitivity of 73.3%, specificity of 78%, accuracy of 75.5%, and AUROC of 82%). These results suggest that EEG source markers can classify Nold and AD individuals with a moderate classification rate higher than 80%.

Original languageEnglish
Article number47
JournalFrontiers in Neuroscience
Volume10
Issue numberFEB
DOIs
Publication statusPublished - Feb 23 2016

Fingerprint

Alzheimer Disease
ROC Curve
Electric Power Supplies
Electromagnetic Phenomena
Temporal Lobe
Tomography
Sensitivity and Specificity
Brain
Power (Psychology)

Keywords

  • Alpha rhythms
  • Alzheimer's disease (AD)
  • Area under the receiver operating characteristic curve (AUROC)
  • Delta rhythms
  • Electroencephalography (EEG)
  • Exact low-resolution brain electromagnetic tomography (eLORETA)
  • Lagged linear connectivity
  • Spectral coherence

ASJC Scopus subject areas

  • Neuroscience(all)

Cite this

Classification of single normal and Alzheimer's disease individuals from cortical sources of resting state EEG rhythms. / Babiloni, Claudio; Triggiani, Antonio Ivano; Lizio, Roberta; Cordone, Susanna; Tattoli, Giacomo; Bevilacqua, Vitoantonio; Soricelli, Andrea; Ferri, Raffaele; Nobili, Flavio; Gesualdo, L.; Millán-Calenti, José C.; Buján, Ana; Tortelli, Rosanna; Cardinali, Valentina; Barulli, Maria Rosaria; Giannini, Antonio; Spagnolo, Pantaleo; Armenise, Silvia; Buenza, Grazia; Scianatico, Gaetano; Logroscino, Giancarlo; Frisoni, Giovanni Battista; Del Percio, Claudio.

In: Frontiers in Neuroscience, Vol. 10, No. FEB, 47, 23.02.2016.

Research output: Contribution to journalArticle

Babiloni, C, Triggiani, AI, Lizio, R, Cordone, S, Tattoli, G, Bevilacqua, V, Soricelli, A, Ferri, R, Nobili, F, Gesualdo, L, Millán-Calenti, JC, Buján, A, Tortelli, R, Cardinali, V, Barulli, MR, Giannini, A, Spagnolo, P, Armenise, S, Buenza, G, Scianatico, G, Logroscino, G, Frisoni, GB & Del Percio, C 2016, 'Classification of single normal and Alzheimer's disease individuals from cortical sources of resting state EEG rhythms', Frontiers in Neuroscience, vol. 10, no. FEB, 47. https://doi.org/10.3389/fnins.2016.00047
Babiloni, Claudio ; Triggiani, Antonio Ivano ; Lizio, Roberta ; Cordone, Susanna ; Tattoli, Giacomo ; Bevilacqua, Vitoantonio ; Soricelli, Andrea ; Ferri, Raffaele ; Nobili, Flavio ; Gesualdo, L. ; Millán-Calenti, José C. ; Buján, Ana ; Tortelli, Rosanna ; Cardinali, Valentina ; Barulli, Maria Rosaria ; Giannini, Antonio ; Spagnolo, Pantaleo ; Armenise, Silvia ; Buenza, Grazia ; Scianatico, Gaetano ; Logroscino, Giancarlo ; Frisoni, Giovanni Battista ; Del Percio, Claudio. / Classification of single normal and Alzheimer's disease individuals from cortical sources of resting state EEG rhythms. In: Frontiers in Neuroscience. 2016 ; Vol. 10, No. FEB.
@article{8e979d54584f44c6bd6969f3ab6fd0f3,
title = "Classification of single normal and Alzheimer's disease individuals from cortical sources of resting state EEG rhythms",
abstract = "Previous studies have shown abnormal power and functional connectivity of resting state electroencephalographic (EEG) rhythms in groups of Alzheimer's disease (AD) compared to healthy elderly (Nold) subjects. Here we tested the best classification rate of 120 AD patients and 100 matched Nold subjects using EEG markers based on cortical sources of power and functional connectivity of these rhythms. EEG data were recorded during resting state eyes-closed condition. Exact low-resolution brain electromagnetic tomography (eLORETA) estimated the power and functional connectivity of cortical sources in frontal, central, parietal, occipital, temporal, and limbic regions. Delta (2-4 Hz), theta (4-8 Hz), alpha 1 (8-10.5 Hz), alpha 2 (10.5-13 Hz), beta 1 (13-20 Hz), beta 2 (20-30 Hz), and gamma (30-40 Hz) were the frequency bands of interest. The classification rates of interest were those with an area under the receiver operating characteristic curve (AUROC) higher than 0.7 as a threshold for a moderate classification rate (i.e., 70{\%}). Results showed that the following EEG markers overcame this threshold: (i) central, parietal, occipital, temporal, and limbic delta/alpha 1 current density; (ii) central, parietal, occipital temporal, and limbic delta/alpha 2 current density; (iii) frontal theta/alpha 1 current density; (iv) occipital delta/alpha 1 inter-hemispherical connectivity; (v) occipital-temporal theta/alpha 1 right and left intra-hemispherical connectivity; and (vi) parietal-limbic alpha 1 right intra-hemispherical connectivity. Occipital delta/alpha 1 current density showed the best classification rate (sensitivity of 73.3{\%}, specificity of 78{\%}, accuracy of 75.5{\%}, and AUROC of 82{\%}). These results suggest that EEG source markers can classify Nold and AD individuals with a moderate classification rate higher than 80{\%}.",
keywords = "Alpha rhythms, Alzheimer's disease (AD), Area under the receiver operating characteristic curve (AUROC), Delta rhythms, Electroencephalography (EEG), Exact low-resolution brain electromagnetic tomography (eLORETA), Lagged linear connectivity, Spectral coherence",
author = "Claudio Babiloni and Triggiani, {Antonio Ivano} and Roberta Lizio and Susanna Cordone and Giacomo Tattoli and Vitoantonio Bevilacqua and Andrea Soricelli and Raffaele Ferri and Flavio Nobili and L. Gesualdo and Mill{\'a}n-Calenti, {Jos{\'e} C.} and Ana Buj{\'a}n and Rosanna Tortelli and Valentina Cardinali and Barulli, {Maria Rosaria} and Antonio Giannini and Pantaleo Spagnolo and Silvia Armenise and Grazia Buenza and Gaetano Scianatico and Giancarlo Logroscino and Frisoni, {Giovanni Battista} and {Del Percio}, Claudio",
year = "2016",
month = "2",
day = "23",
doi = "10.3389/fnins.2016.00047",
language = "English",
volume = "10",
journal = "Frontiers in Neuroscience",
issn = "1662-4548",
publisher = "Frontiers Media S.A.",
number = "FEB",

}

TY - JOUR

T1 - Classification of single normal and Alzheimer's disease individuals from cortical sources of resting state EEG rhythms

AU - Babiloni, Claudio

AU - Triggiani, Antonio Ivano

AU - Lizio, Roberta

AU - Cordone, Susanna

AU - Tattoli, Giacomo

AU - Bevilacqua, Vitoantonio

AU - Soricelli, Andrea

AU - Ferri, Raffaele

AU - Nobili, Flavio

AU - Gesualdo, L.

AU - Millán-Calenti, José C.

AU - Buján, Ana

AU - Tortelli, Rosanna

AU - Cardinali, Valentina

AU - Barulli, Maria Rosaria

AU - Giannini, Antonio

AU - Spagnolo, Pantaleo

AU - Armenise, Silvia

AU - Buenza, Grazia

AU - Scianatico, Gaetano

AU - Logroscino, Giancarlo

AU - Frisoni, Giovanni Battista

AU - Del Percio, Claudio

PY - 2016/2/23

Y1 - 2016/2/23

N2 - Previous studies have shown abnormal power and functional connectivity of resting state electroencephalographic (EEG) rhythms in groups of Alzheimer's disease (AD) compared to healthy elderly (Nold) subjects. Here we tested the best classification rate of 120 AD patients and 100 matched Nold subjects using EEG markers based on cortical sources of power and functional connectivity of these rhythms. EEG data were recorded during resting state eyes-closed condition. Exact low-resolution brain electromagnetic tomography (eLORETA) estimated the power and functional connectivity of cortical sources in frontal, central, parietal, occipital, temporal, and limbic regions. Delta (2-4 Hz), theta (4-8 Hz), alpha 1 (8-10.5 Hz), alpha 2 (10.5-13 Hz), beta 1 (13-20 Hz), beta 2 (20-30 Hz), and gamma (30-40 Hz) were the frequency bands of interest. The classification rates of interest were those with an area under the receiver operating characteristic curve (AUROC) higher than 0.7 as a threshold for a moderate classification rate (i.e., 70%). Results showed that the following EEG markers overcame this threshold: (i) central, parietal, occipital, temporal, and limbic delta/alpha 1 current density; (ii) central, parietal, occipital temporal, and limbic delta/alpha 2 current density; (iii) frontal theta/alpha 1 current density; (iv) occipital delta/alpha 1 inter-hemispherical connectivity; (v) occipital-temporal theta/alpha 1 right and left intra-hemispherical connectivity; and (vi) parietal-limbic alpha 1 right intra-hemispherical connectivity. Occipital delta/alpha 1 current density showed the best classification rate (sensitivity of 73.3%, specificity of 78%, accuracy of 75.5%, and AUROC of 82%). These results suggest that EEG source markers can classify Nold and AD individuals with a moderate classification rate higher than 80%.

AB - Previous studies have shown abnormal power and functional connectivity of resting state electroencephalographic (EEG) rhythms in groups of Alzheimer's disease (AD) compared to healthy elderly (Nold) subjects. Here we tested the best classification rate of 120 AD patients and 100 matched Nold subjects using EEG markers based on cortical sources of power and functional connectivity of these rhythms. EEG data were recorded during resting state eyes-closed condition. Exact low-resolution brain electromagnetic tomography (eLORETA) estimated the power and functional connectivity of cortical sources in frontal, central, parietal, occipital, temporal, and limbic regions. Delta (2-4 Hz), theta (4-8 Hz), alpha 1 (8-10.5 Hz), alpha 2 (10.5-13 Hz), beta 1 (13-20 Hz), beta 2 (20-30 Hz), and gamma (30-40 Hz) were the frequency bands of interest. The classification rates of interest were those with an area under the receiver operating characteristic curve (AUROC) higher than 0.7 as a threshold for a moderate classification rate (i.e., 70%). Results showed that the following EEG markers overcame this threshold: (i) central, parietal, occipital, temporal, and limbic delta/alpha 1 current density; (ii) central, parietal, occipital temporal, and limbic delta/alpha 2 current density; (iii) frontal theta/alpha 1 current density; (iv) occipital delta/alpha 1 inter-hemispherical connectivity; (v) occipital-temporal theta/alpha 1 right and left intra-hemispherical connectivity; and (vi) parietal-limbic alpha 1 right intra-hemispherical connectivity. Occipital delta/alpha 1 current density showed the best classification rate (sensitivity of 73.3%, specificity of 78%, accuracy of 75.5%, and AUROC of 82%). These results suggest that EEG source markers can classify Nold and AD individuals with a moderate classification rate higher than 80%.

KW - Alpha rhythms

KW - Alzheimer's disease (AD)

KW - Area under the receiver operating characteristic curve (AUROC)

KW - Delta rhythms

KW - Electroencephalography (EEG)

KW - Exact low-resolution brain electromagnetic tomography (eLORETA)

KW - Lagged linear connectivity

KW - Spectral coherence

UR - http://www.scopus.com/inward/record.url?scp=84964378023&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84964378023&partnerID=8YFLogxK

U2 - 10.3389/fnins.2016.00047

DO - 10.3389/fnins.2016.00047

M3 - Article

VL - 10

JO - Frontiers in Neuroscience

JF - Frontiers in Neuroscience

SN - 1662-4548

IS - FEB

M1 - 47

ER -