TY - GEN
T1 - Classification of healthy, Alzheimer's disease, and Parkinson's disease individuals with cortical generators of rsEEG rhythms
AU - Del Percio, C.
AU - Bonanni, L.
AU - Stocchi, F.
AU - Babiloni, C.
AU - Lizio, R.
AU - Pascarelli, M. T.
AU - Noce, G.
AU - Soricelli, A.
AU - Ferri, R.
AU - Nobili, F. M.
AU - Giubilei, R.
AU - De Lena, C.
PY - 2019/10
Y1 - 2019/10
N2 - In the present study, we verified the working hypothesis that cortical generators of resting state eyes-closed electroencephalographic (rsEEG) rhythms could classify with good performance (area under receiver operating characteristic, AUROC > 0.8) healthy elderly (Nold), Alzheimer's disease (AD) and Parkinson's disease (PD) individuals. rsEEG recordings were performed in 110 AD, 110 PD, and 75 Nold patients. Individual delta, theta, low-frequency alpha, and high-frequency bands were measured. Fixed low-frequency beta and high-frequency beta were also evaluated. eLORETA freeware measured cortical generators of rsEEG rhythms from posterior sources. Classification analysis was performed with the ROC curve. Cortical generators of posterior rsEEG rhythms at delta, theta, low-frequency alpha, high-frequency alpha, low-frequency beta, and high-frequency beta allowed a good performance (AUROC > 0.8) in the classification between healthy and neurodegenerative (i.e., AD and PD) individuals. Moreover, cortical generators of posterior rsEEG rhythms at low-frequency alpha permitted only a moderate performance (AUROC > 0.75) in the classification between AD and PD individuals. Future prospective cross-validation studies will have to test these candidate rsEEG markers for clinical applications and drug discovery.
AB - In the present study, we verified the working hypothesis that cortical generators of resting state eyes-closed electroencephalographic (rsEEG) rhythms could classify with good performance (area under receiver operating characteristic, AUROC > 0.8) healthy elderly (Nold), Alzheimer's disease (AD) and Parkinson's disease (PD) individuals. rsEEG recordings were performed in 110 AD, 110 PD, and 75 Nold patients. Individual delta, theta, low-frequency alpha, and high-frequency bands were measured. Fixed low-frequency beta and high-frequency beta were also evaluated. eLORETA freeware measured cortical generators of rsEEG rhythms from posterior sources. Classification analysis was performed with the ROC curve. Cortical generators of posterior rsEEG rhythms at delta, theta, low-frequency alpha, high-frequency alpha, low-frequency beta, and high-frequency beta allowed a good performance (AUROC > 0.8) in the classification between healthy and neurodegenerative (i.e., AD and PD) individuals. Moreover, cortical generators of posterior rsEEG rhythms at low-frequency alpha permitted only a moderate performance (AUROC > 0.75) in the classification between AD and PD individuals. Future prospective cross-validation studies will have to test these candidate rsEEG markers for clinical applications and drug discovery.
UR - http://www.scopus.com/inward/record.url?scp=85076749668&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85076749668&partnerID=8YFLogxK
U2 - 10.1109/SMC.2019.8913952
DO - 10.1109/SMC.2019.8913952
M3 - Conference contribution
AN - SCOPUS:85076749668
T3 - Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics
SP - 1270
EP - 1275
BT - 2019 IEEE International Conference on Systems, Man and Cybernetics, SMC 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2019 IEEE International Conference on Systems, Man and Cybernetics, SMC 2019
Y2 - 6 October 2019 through 9 October 2019
ER -