Mining Time-Resolved Functional Brain Graphs to an EEG-Based Chronnectomic Brain Aged Index (CBAI)

The brain at rest consists of spatially and temporal distributed but functionally connected regions that called intrinsic connectivity networks (ICNs). Resting state electroencephalography (rs-EEG) is a way to characterize brain networks without confounds associated with task EEG such as task difficulty and performance. A novel framework of how to study dynamic functional connectivity under the notion of functional connectivity microstates (FCμstates) and symbolic dynamics is further discussed. Furthermore, we introduced a way to construct a single integrated dynamic functional connectivity graph (IDFCG) that preserves both the strength of the connections between every pair of sensors but also the type of dominant intrinsic coupling modes (DICM). The whole methodology is demonstrated in a significant and unexplored task for EEG which is the definition of an objective Chronnectomic Brain Aged index (CBAI) extracted from resting-state data (N = 94 subjects) with both eyes-open and eyes-closed conditions. Novel features have been defined based on symbolic dynamics and the notion of DICM and FCμstates. The transition rate of FCμstates, the symbolic dynamics based on the evolution of FCμstates (the Markovian Entropy, the complexity index), the probability distribution of DICM, the novel Flexibility Index that captures the dynamic reconfiguration of DICM per pair of EEG sensors and the relative signal power constitute a valuable pool of features that can build the proposed CBAI. Here we applied a feature selection technique and Extreme Learning Machine (ELM) classifier to discriminate young adults from middle-aged and a Support Vector Regressor to build a linear model of the actual age based on EEG-based spatio-temporal features. The most significant type of features for both prediction of age and discrimination of young vs. adults age groups was the dynamic reconfiguration of dominant coupling modes derived from a subset of EEG sensor pairs. Specifically, our results revealed a very high prediction of age for eyes-open (R2 = 0.60; y = 0.79x + 8.03) and lower for eyes-closed (R2 = 0.48; y = 0.71x + 10.91) while we succeeded to correctly classify young vs. middle-age group with 97.8% accuracy in eyes-open and 87.2% for eyes-closed. Our results were reproduced also in a second dataset for further external validation of the whole analysis. The proposed methodology proved valuable for the characterization of the intrinsic properties of dynamic functional connectivity through the age untangling developmental differences using EEG resting-state recordings.

[1]  Panagiotis G. Simos,et al.  Greater Repertoire and Temporal Variability of Cross-Frequency Coupling (CFC) Modes in Resting-State Neuromagnetic Recordings among Children with Reading Difficulties , 2016, Front. Hum. Neurosci..

[2]  Lena S. Geiger,et al.  Dynamic brain network reconfiguration as a potential schizophrenia genetic risk mechanism modulated by NMDA receptor function , 2016, Proceedings of the National Academy of Sciences.

[3]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[4]  Massimo Silvetti,et al.  Value and Prediction Error in Medial Frontal Cortex: Integrating the Single-Unit and Systems Levels of Analysis , 2011, Front. Hum. Neurosci..

[5]  Joaquín Goñi,et al.  Changes in structural and functional connectivity among resting-state networks across the human lifespan , 2014, NeuroImage.

[6]  Michael W. Cole,et al.  Activity flow over resting-state networks shapes cognitive task activations , 2016, Nature Neuroscience.

[7]  Salome Kurth,et al.  Sleep and Early Cortical Development , 2015, Current Sleep Medicine Reports.

[8]  Thomas M. Cover,et al.  The entropy of Markov trajectories , 1993, IEEE Trans. Inf. Theory.

[9]  S. Rombouts,et al.  Consistent resting-state networks across healthy subjects , 2006, Proceedings of the National Academy of Sciences.

[10]  Deng Cai,et al.  Laplacian Score for Feature Selection , 2005, NIPS.

[11]  György Buzsáki,et al.  Neural Syntax: Cell Assemblies, Synapsembles, and Readers , 2010, Neuron.

[12]  Xi-Nian Zuo,et al.  Reliable intrinsic connectivity networks: Test–retest evaluation using ICA and dual regression approach , 2010, NeuroImage.

[13]  Manolis Tsiknakis,et al.  Synchronization coupling investigation using ICA cluster analysis in resting MEG signals in reading difficulties , 2013, 13th IEEE International Conference on BioInformatics and BioEngineering.

[14]  Arnaud Delorme,et al.  EEGLAB: an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis , 2004, Journal of Neuroscience Methods.

[15]  Marcello Pelillo,et al.  Dominant Sets and Pairwise Clustering , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  A. Engel,et al.  Intrinsic Coupling Modes: Multiscale Interactions in Ongoing Brain Activity , 2013, Neuron.

[17]  Nitish Thakor,et al.  Cognitive Workload Assessment Based on the Tensorial Treatment of EEG Estimates of Cross-Frequency Phase Interactions , 2014, Annals of Biomedical Engineering.

[18]  Gary H. Glover,et al.  Default-mode function and task-induced deactivation have overlapping brain substrates in children , 2008, NeuroImage.

[19]  V. Calhoun,et al.  Multisubject Independent Component Analysis of fMRI: A Decade of Intrinsic Networks, Default Mode, and Neurodiagnostic Discovery , 2012, IEEE Reviews in Biomedical Engineering.

[20]  Hiroki Sayama,et al.  Developmental changes in spontaneous electrocortical activity and network organization from early to late childhood , 2015, NeuroImage.

[21]  Nadja Schott,et al.  Cognitive-Motor Interference during Walking in Older Adults with Probable Mild Cognitive Impairment , 2017, Front. Aging Neurosci..

[22]  Viktor K. Jirsa,et al.  Cross-frequency coupling in real and virtual brain networks , 2013, Front. Comput. Neurosci..

[23]  Nitish V. Thakor,et al.  Causal Interactions between Frontalθ – Parieto-Occipitalα2 Predict Performance on a Mental Arithmetic Task , 2016, Front. Hum. Neurosci..

[24]  Michael Vourkas,et al.  Tracking brain dynamics via time-dependent network analysis , 2010, Journal of Neuroscience Methods.

[25]  Kaustubh Supekar,et al.  Development of Large-Scale Functional Brain Networks in Children , 2009, NeuroImage.

[26]  Ioannis Tarnanas,et al.  A novel biomarker of amnestic MCI based on dynamic cross-frequency coupling patterns during cognitive brain responses , 2015, Front. Neurosci..

[27]  N. Turk-Browne.  Functional Interactions as Big Data in the Human Brain , 2013, Science.

[28]  Patrice Séébold,et al.  Proof of a conjecture on word complexity , 2001 .

[29]  V. Calhoun,et al.  The Chronnectome: Time-Varying Connectivity Networks as the Next Frontier in fMRI Data Discovery , 2014, Neuron.

[30]  N. Birbaumer,et al.  BCI2000: a general-purpose brain-computer interface (BCI) system , 2004, IEEE Transactions on Biomedical Engineering.

[31]  Elgar Fleisch,et al.  Mnemonic strategy training of the elderly at risk for dementia enhances integration of information processing via cross-frequency coupling , 2016, Alzheimer's & dementia.

[32]  Michael Vourkas,et al.  A novel symbolization scheme for multichannel recordings with emphasis on phase information and its application to differentiate EEG activity from different mental tasks , 2011, Cognitive Neurodynamics.

[33]  Maria L. Rizzo,et al.  Partial Distance Correlation with Methods for Dissimilarities , 2013, 1310.2926.

[34]  Archana Venkataraman,et al.  Intrinsic functional connectivity as a tool for human connectomics: theory, properties, and optimization. , 2010, Journal of neurophysiology.

[35]  Guang-Bin Huang,et al.  What are Extreme Learning Machines? Filling the Gap Between Frank Rosenblatt’s Dream and John von Neumann’s Puzzle , 2015, Cognitive Computation.

[36]  David E. J. Linden,et al.  Classifying children with reading difficulties from non-impaired readers via symbolic dynamics and complexity analysis of MEG resting-state data , 2016, 2016 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT).

[37]  Alexander J. Smola,et al.  Support Vector Regression Machines , 1996, NIPS.

[38]  Mary E. Meyerand,et al.  Characterizing Functional Connectivity Differences in Aging Adults using Machine Learning on Resting State fMRI Data , 2013, Front. Comput. Neurosci..

[39]  Mary E. Meyerand,et al.  Support vector machine classification and characterization of age-related reorganization of functional brain networks , 2012, NeuroImage.

[40]  Jason Weston,et al.  A user's guide to support vector machines. , 2010, Methods in molecular biology.

[41]  Svante Janson,et al.  On the average sequence complexity , 2004, Data Compression Conference, 2004. Proceedings. DCC 2004.

[42]  B. Biswal,et al.  The resting brain: unconstrained yet reliable. , 2009, Cerebral cortex.

[43]  Andreas A. Ioannides,et al.  Exploratory data analysis of evoked response single trials based on minimal spanning tree , 2001, Clinical Neurophysiology.

[44]  Michael Vourkas,et al.  An EEG study of brain connectivity dynamics at the resting state. , 2012, Nonlinear dynamics, psychology, and life sciences.

[45]  J. Morton,et al.  Tracking the Brain's Functional Coupling Dynamics over Development , 2015, The Journal of Neuroscience.

[46]  N. A. Laskaris,et al.  Transition dynamics of EEG-based network microstates during mental arithmetic and resting wakefulness reflects task-related modulations and developmental changes , 2015, Cognitive Neurodynamics.

[47]  A. Burgess,et al.  Short duration synchronization of human theta rhythm during recognition memory , 1997, Neuroreport.

[48]  Ioannis Tarnanas,et al.  Topological Filtering of Dynamic Functional Brain Networks Unfolds Informative Chronnectomics: A Novel Data-Driven Thresholding Scheme Based on Orthogonal Minimal Spanning Trees (OMSTs) , 2017, Front. Neuroinform..

[49]  Nikolaos A. Laskaris,et al.  NNMF connectivity microstates : A new approach to represent the dynamic brain coordination , 2016 .

[50]  D. Hu,et al.  Predicting individual brain maturity using dynamic functional connectivity , 2015, Front. Hum. Neurosci..

[51]  B. Biswal,et al.  Functional connectivity in the motor cortex of resting human brain using echo‐planar mri , 1995, Magnetic resonance in medicine.

[52]  G. Rees,et al.  Predicting the Stream of Consciousness from Activity in Human Visual Cortex , 2005, Current Biology.

[53]  Panagiotis G. Simos,et al.  Altered temporal correlations in resting-state connectivity fluctuations in children with reading difficulties detected via MEG , 2013, NeuroImage.

[54]  Dewen Hu,et al.  Discriminative analysis of resting-state functional connectivity patterns of schizophrenia using low dimensional embedding of fMRI , 2010, NeuroImage.

[55]  G. Buzsáki,et al.  Neuronal Oscillations in Cortical Networks , 2004, Science.

[56]  R Cameron Craddock,et al.  Disease state prediction from resting state functional connectivity , 2009, Magnetic resonance in medicine.

[57]  N. A. Laskaris,et al.  On the Quantization of Time-Varying Phase Synchrony Patterns into Distinct Functional Connectivity Microstates (FCμstates) in a Multi-trial Visual ERP Paradigm , 2013, Brain Topography.

[58]  N. Logothetis,et al.  Scaling Brain Size, Keeping Timing: Evolutionary Preservation of Brain Rhythms , 2013, Neuron.

[59]  Robert Oostenveld,et al.  FieldTrip: Open Source Software for Advanced Analysis of MEG, EEG, and Invasive Electrophysiological Data , 2010, Comput. Intell. Neurosci..

[60]  Marcello Pelillo,et al.  Dominant Sets and Pairwise Clustering , 2007 .

[61]  Scott T. Grafton,et al.  Dynamic reconfiguration of human brain networks during learning , 2010, Proceedings of the National Academy of Sciences.

[62]  Anthony Widjaja,et al.  Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond , 2003, IEEE Transactions on Neural Networks.

[63]  Jonathan D. Power,et al.  Prediction of Individual Brain Maturity Using fMRI , 2010, Science.

[64]  Russell A. Poldrack,et al.  Decoding Continuous Variables from Neuroimaging Data: Basic and Clinical Applications , 2011, Front. Neurosci..

[65]  J. Richman,et al.  Physiological time-series analysis using approximate entropy and sample entropy. , 2000, American journal of physiology. Heart and circulatory physiology.

[66]  Luz María Alonso-Valerdi,et al.  Python Executable Script for Estimating Two Effective Parameters to Individualize Brain-Computer Interfaces: Individual Alpha Frequency and Neurophysiological Predictor , 2016, Front. Neuroinform..

[67]  Thomas Martinetz,et al.  'Neural-gas' network for vector quantization and its application to time-series prediction , 1993, IEEE Trans. Neural Networks.

[68]  Mary E. Meyerand,et al.  Age-Related Differences in Test-Retest Reliability in Resting-State Brain Functional Connectivity , 2012, PloS one.