Abstract
In this paper, we propose a network analysis–based approach to help experts in their analyses of subjects with mild cognitive impairment (hereafter, MCI) and Alzheimer’s disease (hereafter, AD) and to investigate the evolution of these subjects over time. The inputs of our approach are the electroencephalograms (hereafter, EEGs) of the patients to analyze, performed at a certain time and, again, 3 months later. Given an EEG of a subject, our approach constructs a network with nodes that represent the electrodes and edges that denote connections between electrodes. Then, it applies several network-based techniques allowing the investigation of subjects with MCI and AD and the analysis of their evolution over time. (i) A connection coefficient, supporting experts to distinguish patients with MCI from patients with AD; (ii) A conversion coefficient, supporting experts to verify if a subject with MCI is converting to AD; (iii) Some network motifs, i.e., network patterns very frequent in one kind of patient and absent, or very rare, in the other. Patients with AD, just by the very nature of their condition, cannot be forced to stay motionless while undergoing examinations for a long time. EEG is a non-invasive examination that can be easily done on them. Since AD and MCI, if prodromal to AD, are associated with a loss of cortical connections, the adoption of network analysis appears suitable to investigate the effects of the progression of the disease on EEG. This paper confirms the suitability of this idea
.
Similar content being viewed by others
Notes
At this moment, we do not make any assumptions about the subject whom eeg refers to. She/he could be a control subject, a patient with MCI or a patient with AD.
Recall that blue edges are the strongest ones, red edges have an intermediate weight, whereas green edges are the weakest ones.
Recall that a clique of dimension k in a network represents a completely connected subnetwork formed by k nodes.
We recall that a triad is a subnetwork consisting of three nodes. The totally connected triad is considered the most stable structure in network analysis. A totally connected triad can be considered as a clique of dimension 3.
Clearly, for derived motifs, noccM and noccA refer to the number of occurrences of motifs, instead of triads.
References
Achard S, Bullmore E (2007) Efficiency and cost of economical brain functional networks. PLoS Comput Biol 3(2):e17. Public Library of Science
Ahmadlou M, Adeli A, Bajo R, Adeli H (2014) Complexity of functional connectivity networks in mild cognitive impairment subjects during a working memory task. Clin Neurophysiol 125(4):694–702. Elsevier
Ahmadlou M, Adeli H (2010) Wavelet-synchronization methodology: a new approach for EEG-based diagnosis of ADHD. Clin EEG Neurosci 41(1):1–10. SAGE Publications
Ahmadlou M, Adeli H, Adeli A (2012) Improved visibility graph fractality with application for the diagnosis of autism spectrum disorder. Physica A: Stat Mech Appl 391(20):4720–4726. Elsevier
Ahuja RK (2017) Network flows: theory, algorithms, and applications. Pearson Education, Boston
Akar SA, Kara S, Latifoğlu F, Bilgiç V (2016) Analysis of the complexity measures in the EEG of schizophrenia patients. Int J Neural Syst 26(02):1650008. World Scientific
Alstott J, Breakspear M, Hagmann P, Cammoun L, Sporns O (2009) Modeling the impact of lesions in the human brain. PLoS Comput Biol 5(6):e1000408. Public Library of Science
Amezquita-Sanchez J, Adeli A, Adeli H (2016) A new methodology for automated diagnosis of mild cognitive impairment (MCI) using magnetoencephalography (MEG). Behav Brain Res 305:174–180. Elsevier
American Psychiatric Association (ed.) (2013) Diagnostic and statistical manual of mental disorders. 5th ed
Bandt C, Pompe B (2002) Permutation entropy: a natural complexity measure for time series. Physical Rev Lett 88(17):174102
Besthorn C, Sattel H, Geiger-Kabisch C, Zerfass R, Forstl H (1995) Parameters of EEG dimensional complexity in Alzheimer’s disease. Electroencephalogr Clin Neurophysiol 95(2):84–89. Elsevier
Besthorn C, Zerfass R, Geiger-Kabisch C, Sattel H, Daniel S, Schreiter-Gasser U, Forstl H (1997) Discrimination of Alzheimer’s disease and normal aging by EEG data. Electroencephalogr Clin Neurophysiol 103 (2):241–248. Elsevier
Bollobas B (2013) Modern graph theory (graduate texts in mathematics). Salmon Tower Building. Springer, New York
Buscema M, Grossi E, Capriotti M, Babiloni C, Rossini P (2010) The IFAST model allows the prediction of conversion to Alzheimer disease in patients with mild cognitive impairment with high degree of accuracy. Curr Alzheimer Res 7(2):173–187. Bentham Science Publishers
Chyzhyk D, Graña M, Öngür D, Shinn AK (2015) Discrimination of schizophrenia auditory hallucinators by machine learning of resting-state functional MRI. Int J Neural Syst 25(03):1550007. World Scientific
Czigler B, Csikós D, Hidasi Z, Gaál Z, Csibri E, Kiss E, Salacz P, Molnár M (2008) Quantitative EEG in early Alzheimer’s disease patients’ power spectrum and complexity features. Int J Psychophysiol 68(1):75–80. Elsevier
Dauwels J, Vialatte F, Cichocki A (2010) Diagnosis of Alzheimer’s disease from EEG signals: where are we standing? Curr Alzheimer Res 7(6):487–505. Bentham Science Publishers
Dauwels J, Vialatte F, Cichocki A (2011) On the early diagnosis of Alzheimer’s disease from EEG signals: a mini-review. In: Advances in cognitive neurodynamics (II). Springer, pp 709–716
Dauwels J, Vialatte F, Musha T, Cichocki A (2010) A comparative study of synchrony measures for the early diagnosis of Alzheimer’s disease based on EEG. NeuroImage 49(1):668–693
Davatzikos C, Bhatt P, Shaw LM, Batmanghelich KN, Trojanowski JQ (2011) Prediction of MCI to AD conversion, via MRI, CSF biomarkers, and pattern classification. Neurobiol Aging 32(12):2322–e19. Elsevier
de Haan W, Pijnenburg YA, Strijers RL, van der Made Y, van der Flier W, Scheltens P, Stam CJ (2009) Functional neural network analysis in frontotemporal dementia and Alzheimer’s disease using EEG and graph theory. BMC Neuroscience 10(1):1. BioMed Central
Delorme A, Makeig S (2004) EEGLAB: an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis. J Neurosci Methods 134:9–21
Deo N (2016) Graph theory with applications to engineering and computer science. Mineola. Dover Publications, New York
Fraga FJ, Falk TH, Kanda PA, Anghinah R (2013) Characterizing Alzheimer’s disease severity via resting-awake EEG amplitude modulation analysis. PloS one 8(8):e72240. Public Library of Science
Lo Giudice P, Ursino D, Mammone N, Morabito FC, Aguglia U, Cianci V, Ferlazzo E, Gasparini S (2019) A network analysis based approach to characterizing periodic sharp wave complexes in electroencephalograms of patients with sporadic CJD. Int J Med Inform 121:19–29. Elsevier
Gouw AA, Alsema AM, Tijms BM, Borta A, Scheltens P, Stam CJ, van der Flier WM (2017) EEG spectral analysis as a putative early prognostic biomarker in nondemented, amyloid positive subjects. Neurobiol Aging 57:133–142. Elsevier
Gross JL, Yellen J (2005) Graph theory and its applications. Chapman and Hall/CRC, New York
Hagmann P, Cammoun L, Gigandet X, Meuli R, Honey CJ, Wedeen JV, Sporns O (2008) Mapping the structural core of human cerebral cortex. PLoS Comput Biol 6(7):e159. Public Library of Science
Han J, Kamber M (2006) Data Mining: concepts and techniques - second edition. Morgan Kaufmann Notes
Hatz F, Hardmeier M, Benz N, Ehrensperger M, Gschwandtner U, Rüegg S, Schindler C, Monsch AU, Fuhr P (2015) Microstate connectivity alterations in patients with early Alzheimer’s disease. Alzheimers Res Ther 7(1):78. BioMed Central
He Y, Chen ZJ, Evans AC (2007) Small-world anatomical networks in the human brain revealed by cortical thickness from MRI. Cerebral Cortex 17(10):2407–2419
Hebert L, Weuve J, Scherr P, Evans D (2013) Alzheimer disease in the United States (2010–2050) estimated using the 2010 census. Neurology 80(19):1778–1783. AAN Enterprises
Hirschauer TJ, Adeli H, Buford JA (2015) Computer-aided diagnosis of Parkinson’s disease using enhanced probabilistic neural network. J Med Syst 39(11):179. Springer
Honey CJ, Sporns O, Cammoun L, Gigandet X, Thiran JP, Meuli R, Hagmann P (2009) Predicting human resting-state functional connectivity from structural connectivity. Proc Natl Acad Sci 106(6):2035–2040. National Academy of Sciences
Hornero R, Abásolo D, Escudero J, Gómez C (2009) Nonlinear analysis of electroencephalogram and magnetoencephalogram recordings in patients with Alzheimer’s disease. Philosophical Transactions of the Royal Society of London A: Mathematical, Physical and Engineering Sciences 367(1887):317–336. The Royal Society
Jalili M (2017) Graph theoretical analysis of Alzheimer’s disease: discrimination of AD patients from healthy subjects. Inform Sci 384:145–156. Elsevier
Jeong J (2004) EEG dynamics in patients with Alzheimer’s disease. Clin Neurophysiol 115(7):1490–1505. Elsevier
Kasabov N, Capecci E (2015) Spiking neural network methodology for modelling, classification and understanding of EEG spatio-temporal data measuring cognitive processes. Inform Sci 294:565–575. Elsevier
Knyazeva M, Jalili M, Brioschi A, Bourquin I, Fornari E, Hasler M, Meuli R, Maeder P, Ghika J (2010) Topography of EEG multivariate phase synchronization in early Alzheimer’s disease. Neurobiol Aging 31(7):1132–1144. Elsevier
Koppert M, Kalitzin S, Velis D, Lopes Da Silva F, Viergever MA (2016) Preventive and abortive strategies for stimulation based control of epilepsy: a computational model study. Int J Neural Syst 26(08):1650028. World Scientific
Labate D, La Foresta F, Morabito G, Palamara I, Morabito FC (2013) Entropic measures of EEG complexity in Alzheimer’s disease through a multivariate multiscale approach. IEEE Sensors J 13(9):3284–3292
Mammone N, Bonanno L, De Salvo S, Marino S, Bramanti P, Bramanti A, Morabito FC (2017) Permutation disalignment index as an indirect, EEG-based, measure of brain connectivity in MCI and AD patients. Int J Neural Syst 27(05):1750020. World Scientific
Milo R, Shen-Orr S, Itzkovitz S, Kashtan N, Chklovskii D, Alon U (2002) Network motifs: simple building blocks of complex networks. Science 298(5594):824–827. American Association for the Advancement of Science
Miraglia F, Vecchio F, Rossini P (2017) Searching for signs of aging and dementia in EEG through network analysis. Behav Brain Res 317:292–300. Elsevier
Morabito FC, Campolo M, Labate D, Morabito G, Bonanno L, Bramanti A, De Salvo S, Marra A, Bramanti P (2015) A longitudinal EEG study of Alzheimer’s disease progression based on a complex network approach. Int J Neural Syst 25(02):1550005. World Scientific
Morabito FC, Labate D, Bramanti A, La Foresta F, Morabito G, Palamara I, Szu H (2013) Enhanced compressibility of EEG signal in Alzheimer’s disease patients. IEEE Sensors J 13(9):3255–3262. IEEE
Morabito FC, Labate D, Morabito G, Palamara I, Szu H (2013) Monitoring and diagnosis of Alzheimer’s disease using noninvasive compressive sensing EEG. In: SPIE defense, security, and sensing. International Society for Optics and Photonics, pp 87500Y–87500Y
Moretti DV (2015) Association of EEG, MRI, and regional blood flow biomarkers is predictive of prodromal Alzheimer’s disease. Neuropsychiatr Dis Treat 11:2779. Dove Press
Newman MEJ (2003) The structure and function of complex networks. SIAM Rev 45.2:167–256
Onnela JP, Saramäki J, Kertész J, Kaski K (2005) Intensity and coherence of motifs in weighted complex networks. Phys Rev E 71(6):065103. APS
Parvinnia E, Sabeti M, Jahromi M, Boostani R (2014) Classification of EEG Signals using adaptive weighted distance nearest neighbor algorithm. Journal of King Saud University-Computer and Information Sciences 26(1):1–6. Elsevier
Petersen R (2004) Mild cognitive impairment as a diagnostic entity. J Intern Med 256(3):183–194. Wiley Online Library
Poil SS, De Haan W, van der Flier WM, Mansvelder HD, Scheltens P, Linkenkaer-Hansen K (2013) Integrative EEG biomarkers predict progression to Alzheimer’s disease at the MCI stage. Front Aging Neurosci 5:58. Frontiers
Ponten SC, Douw L, Bartolomei F, Reijneveld JC, Stam CJ (2009) Indications for network regularization during absence seizures: weighted and unweighted graph theoretical analyses. Exp Neurol 217(1):197–204. Elsevier
Ramirez J, Gorriz J, Salas-Gonzalez D, Romero A, Lopez M, Alvarez I, Gomez-Rio M (2013) Computer-aided diagnosis of Alzheimer’s type dementia combining support vector machines and discriminant set of features. Inform Sci 237:59–72. Elsevier
Rubinov M, Sporns O (2010) Complex network measures of brain connectivity: uses and interpretations. Neuroimage 52(3):1059–1069. Elsevier
Sakkalis V (2011) Review of advanced techniques for the estimation of brain connectivity measured with EEG/MEG. Comput Biol Med 41(12):1110–1117. Elsevier
Sankari Z, Adeli H, Adeli A (2011) Intrahemispheric, interhemispheric, and distal EEG coherence in Alzheimer’s disease. Clin Neurophysiol 122(5):897–906. Elsevier
Sporns O, Kötter RR (2004) Motifs in brain networks. PLoS Comput Biol 2(11):e369. Public Library of Science
Stam CJ, Jones B, Nolte G, Breakspear M, Scheltens P (2007) Small-world networks and functional connectivity in Alzheimer’s disease. Cereb Cortex 17(1):92–99. Oxford Univ Press
Su F, Wang J, Deng B, Wei XL, Chen YY, Liu C, Li HY (2015) Adaptive control of Parkinson’s state based on a nonlinear computational model with unknown parameters. Int J Neural Syst 25(01):1450030. World Scientific
Vecchio F, Miraglia F, Marra C, Quaranta D, Vita M, Bramanti P, Rossini P (2014) Human brain networks in cognitive decline: a graph theoretical analysis of cortical connectivity from EEG data. J Alzheimers Dis 41(1):113–127. IOS Press
Vialatte F, Cichocki A, Dreyfus G, Musha T, Shishkin SL, Gervais R (2005) Early detection of Alzheimer’s disease by blind source separation, time frequency representation, and bump modeling of EEG signals. In: Proc. of the international conference on artificial neural networks (ICANN’05). Lecture Notes in Computer Science, Springer, Warsaw, pp 683–692
Villar JR, Vergara P, Menéndez M, de la Cal E, González VM, Sedano J (2016) Generalized Models for the classification of abnormal movements in daily life and its applicability to epilepsy convulsion recognition . Int J Neural Syst 26(06):1650037. World Scientific
Wang L, Zhu C, He Y, Zang Y, Cao Q, Zhang H, Zhong Q, Wang Y (2009) Altered small-world brain functional networks in children with attention-deficit/hyperactivity disorder. Hum Brain Mapp 30 (2):638–649. Wiley Online Library
Wang R, Wang J, Yu H, Wei X, Yang C, Deng B (2015) Power spectral density and coherence analysis of Alzheimer’s EEG. Cogn Neurodyn 9(3):291–304. Springer
Watts DJ, Strogatz SH (1998) Collective dynamics of ‘small-world’ networks. Nature 393(6684):440–442. Nature Publishing Group
Yan JZ (2005) Abnormal cortical functional connections in Alzheimer’s disease: analysis of inter-and intra-hemispheric EEG coherence. J Zhejiang Univ Sci B 6(4):259–264. Springer
Yu M, Gouw A, Hillebrand A, Tijms B, Stam C, van Straaten E, Pijnenburg Y (2016) Different functional connectivity and network topology in behavioral variant of frontotemporal dementia and Alzheimer’s disease: an EEG study. Neurobiol Aging 42:150–162. Elsevier
Funding
This work was partially funded by the Italian Ministry of Health, Project Code GR-2011-02351397, and by the Department of Information Engineering at the Polytechnic University of Marche under the project “A network-based approach to uniformly extract knowledge and support decision making in heterogeneous application contexts” (RSAB 2018).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix
Appendix
1.1 A.1 Permutation disalignment index
Given an EEG window under analysis and two EEG channels, two time series x and y are identified. Given a time t, an embedding dimension m and a time lag L [10], starting from the samples x(t) and y(t), two m-dimensional vectors Xt and Yt can be constructed:
and
A visual explanation of the methodology is provided assuming m = 3 (Fig. 6). When m = 3, Xt, and Yt are 3-dimensional vectors.
The absolute values of the elements of Xt and Yt are discarded and only their relative amplitude (low, medium, high) are taken into account. If 3 levels are considered, 6 ordinal sequences (Motifs) are possible [10]. Motifs are denoted with the symbol πi (where i = 1,..., 6).
At the tth iteration, the algorithm detects which motif occurs in Xt and in Yt. For instance, in Fig. 6, motif π4 occurred in both X(t) and Y (t). Therefore, the algorithm increments ηX, Y(π4), that is the number of the simultaneous occurrences of π4 in time series x and y.
Then, the algorithm moves to the next sample x(t + 1), two new vectors Xt+ 1 and Yt+ 1 are constructed, and the procedure is reiterated.
Once the two time series have been fully processed, the algorithm estimates the overall probability that every motif πi (with i = 1,..., 6) simultaneously occurs in x and y, by normalizing the number of occurrences ηX, Y(πi) against the number of iterations:
The PDI between x and y is, finally, defined as:
The more coupled x and y are, the lower PDI is expected to be [42]. The parameter α can tune the sensitivity of PDI to sub-Gaussianity or super-Gaussianity of time series. In this work, it was set to 2, to ensure a balanced sensitivity to either sub-Gaussian or super-Gaussian distributions. Details of this algorithm can be found in [42].
1.2 A.2 Pseudo-code for the construction of a clique network
The pseudo-code for the construction of a clique network is reported in Algorithm 1. Function ConstructCliqueNetwork receives a colored network \({\mathcal {N}}_{\pi }\) and returns a clique network \({\mathcal {C}N}\). First, it constructs an empty network \({\mathcal {C}N}\). Then, it computes all the cliques of \({\mathcal {N}}_{\pi }\). After this, for each clique, it identifies the nodes composing it and, for each node, verifies if it is already present in \({\mathcal {C}N}\). In the affirmative case, it increases the corresponding weight. In the negative case, it adds this node to \({\mathcal {C}N}\) with the corresponding weight set to 1. Finally, for each clique of \({\mathcal {N}}_{\pi }\), it considers the corresponding edges. If an edge is already present in \({\mathcal {C}N}\), it increments the corresponding weight; otherwise, it adds this edge to \({\mathcal {C}N}\) with the corresponding weight set to 1.
1.3 A.3 Pseudo-code for the computation of motifs
The pseudo-code for the computation of motifs is reported in Algorithm 2. Function DeriveMotifs receives the list T of the triads of EEGSet and the list N of the networks in which the presence of the triads of T must be verified. First, for each triad t of T, it computes how many times t is present in patients with MCI and in patients with AD. Then, it verifies conditions (1) and (2) and, on the basis of this verification, it possibly adds t to \({\mathcal {M}}_{M}\) or \({\mathcal {M}}_{A}\). At the end of these activities, basic motifs have been computed and the construction of derived motifs can start. For this purpose, DeriveMotifs first considers the motifs of \({\mathcal {M}}_{M}\). For each motif mi of \({\mathcal {M}}_{M}\), it verifies if mi has at least one node in common with another motif mj. In the affirmative case, it constructs a candidate derived motif mij by merging mi and mj. After this, it evaluates conditions (1) and (2) for mij and, if one of them is valid, adds mij to \({\mathcal {M}}_{M}\). In an analogous way, DeriveMotifs proceeds for the construction of the derived motifs of \({\mathcal {M}}_{A}\). Finally, it returns \({\mathcal {M}}_{M}\) and \({\mathcal {M}}_{A}\).
Rights and permissions
About this article
Cite this article
Lo Giudice, P., Mammone, N., Morabito, F.C. et al. Leveraging network analysis to support experts in their analyses of subjects with MCI and AD. Med Biol Eng Comput 57, 1961–1983 (2019). https://doi.org/10.1007/s11517-019-02004-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11517-019-02004-y