TY - JOUR
T1 - Network-level permutation entropy of resting-state MEG recordings
T2 - A novel biomarker for early-stage Alzheimer’s disease?
AU - Scheijbeler, Elliz P.
AU - van Nifterick, Anne M.
AU - Stam, Cornelis J.
AU - Hillebrand, Arjan
AU - Gouw, Alida A.
AU - Haan, Willem de
N1 - Funding Information: The authors would like to thank the participants of the Amsterdam Dementia Cohort for their contribution. Research of Amsterdam Alzheimer Center is part of the neurodegeneration program of Amsterdam Neuroscience. The Amsterdam Alzheimer Center is supported by Alzheimer Nederland and Stichting VUmc funds. The authors thank technicians P. J. Ris, C. H. Plugge, N. Sijsma, N. C. Akemann, N. Zwagerman, and M.C. Alting Siberg for acquisition of the MEG data. Publisher Copyright: © MIT Press Journals. All rights reserved.
PY - 2022/6/1
Y1 - 2022/6/1
N2 - Increasing evidence suggests that measures of signal variability and complexity could present promising biomarkers for Alzheimer’s disease (AD). Earlier studies have however been limited to the characterization of local activity. Here, we investigate whether a network version of permutation entropy could serve as a novel biomarker for early-stage AD. Resting-state source-space magnetoencephalography was recorded in 18 subjects with subjective cognitive decline (SCD) and 18 subjects with mild cognitive impairment (MCI). Local activity was characterized by permutation entropy (PE). Network-level interactions were studied using the inverted joint permutation entropy ( JPEinv ), corrected for volume conduction. The JPEinv showed a reduction of nonlinear connectivity in MCI subjects in the theta and alpha band. Local PE showed increased theta band entropy. Between-group differences were widespread across brain regions. Receiver operating characteristic (ROC) analysis of classification of MCI versus SCD subjects revealed that a logistic regression model trained on JPEinv features (78.4% [62.5–93.3%]) slightly outperformed PE (76.9% [60.3–93.4%]) and relative theta power–based models (76.9% [60.4–93.3%]). Classification performance of theta JPEinv was at least as good as the relative theta power benchmark. The JPEinv is therefore a potential biomarker for early-stage AD that should be explored in larger studies.
AB - Increasing evidence suggests that measures of signal variability and complexity could present promising biomarkers for Alzheimer’s disease (AD). Earlier studies have however been limited to the characterization of local activity. Here, we investigate whether a network version of permutation entropy could serve as a novel biomarker for early-stage AD. Resting-state source-space magnetoencephalography was recorded in 18 subjects with subjective cognitive decline (SCD) and 18 subjects with mild cognitive impairment (MCI). Local activity was characterized by permutation entropy (PE). Network-level interactions were studied using the inverted joint permutation entropy ( JPEinv ), corrected for volume conduction. The JPEinv showed a reduction of nonlinear connectivity in MCI subjects in the theta and alpha band. Local PE showed increased theta band entropy. Between-group differences were widespread across brain regions. Receiver operating characteristic (ROC) analysis of classification of MCI versus SCD subjects revealed that a logistic regression model trained on JPEinv features (78.4% [62.5–93.3%]) slightly outperformed PE (76.9% [60.3–93.4%]) and relative theta power–based models (76.9% [60.4–93.3%]). Classification performance of theta JPEinv was at least as good as the relative theta power benchmark. The JPEinv is therefore a potential biomarker for early-stage AD that should be explored in larger studies.
KW - Biomarker
KW - Early-stage Alzheimer’s
KW - Functional brain networks
KW - Joint permutation entropy
KW - Magnetoencephalography
UR - http://www.scopus.com/inward/record.url?scp=85131257764&partnerID=8YFLogxK
U2 - https://doi.org/10.1162/netn_a_00224
DO - https://doi.org/10.1162/netn_a_00224
M3 - Article
C2 - 35733433
SN - 2472-1751
VL - 6
SP - 382
EP - 400
JO - Network Neuroscience
JF - Network Neuroscience
IS - 2
ER -