Whole-brain dynamical modelling for classification of Parkinson’s disease

Simulated whole-brain connectomes demonstrate an enhanced inter-individual variability depending on data processing and modeling approach. By considering the human brain connectome as an individualized attribute, we investigate how empirical and simulated whole-brain connectome-derived features can be utilized to classify patients with Parkinson’s disease against healthy controls in light of varying data processing and model validation. To this end, we applied simulated blood oxygenation level-dependent signals derived by a whole-brain dynamical model simulating electrical signals of neuronal populations to reveal differences between patients and controls. In addition to the widely used model validation via fitting the dynamical model to empirical neuroimaging data, we invented a model validation against behavioral data, such as subject classes, which we refer to as behavioral model fitting and show that it can be beneficial for Parkinsonian patient classification. Furthermore, the results of machine-learning reported in this study also demonstrated that performance of the patient classification can be improved when the empirical data are complemented by the simulation results. We also showed that temporal filtering of blood oxygenation level-dependent signals influences the prediction results, where the filtering in the low-frequency band is advisable for Parkinsonian patient classification. In addition, composing the feature space of empirical and simulated data from multiple brain parcellation schemes provided complementary features that improve prediction performance. Based on our findings, we suggest including the simulation results with empirical data is effective for inter-individual research and its clinical application.

[1]  Gwen van Der Wijk,et al.  High-resolution virtual brain modeling personalizes deep brain stimulation for treatment-resistant depression: Spatiotemporal response characteristics following stimulation of neural fiber pathways , 2021, NeuroImage.

[2]  J. Jovicich,et al.  Structural Brain Network Reproducibility: Influence of Different Diffusion Acquisition and Tractography Reconstruction Schemes on Graph Metrics , 2021, Brain Connect..

[3]  Richard F. Betzel,et al.  Local structure-function relationships in human brain networks across the lifespan , 2021, Nature Communications.

[4]  M. Sabuncu,et al.  Heritability and interindividual variability of regional structure-function coupling , 2021, Nature Communications.

[5]  Justin W. M. Domhof,et al.  Parcellation-induced variation of empirical and simulated brain connectomes at group and subject levels , 2021, Network Neuroscience.

[6]  G. Deco,et al.  Multiscale dynamic mean field (MDMF) model relates resting-state brain dynamics with local cortical excitatory–inhibitory neurotransmitter homeostasis , 2021, Network Neuroscience.

[7]  Simon B. Eickhoff,et al.  Inter-subject and inter-parcellation variability of resting-state whole-brain dynamical modeling , 2021, NeuroImage.

[8]  Christian Desrosiers,et al.  Machine Learning for the Diagnosis of Parkinson's Disease: A Review of Literature , 2021, Frontiers in Aging Neuroscience.

[9]  J. Caspers Translation of predictive modeling and AI into clinics: a question of trust , 2021, European Radiology.

[10]  S. Eickhoff,et al.  Confound Removal and Normalization in Practice: A Neuroimaging Based Sex Prediction Case Study , 2021, ECML/PKDD.

[11]  G. Rees,et al.  Organisational and neuromodulatory underpinnings of structural-functional connectivity decoupling in patients with Parkinson’s disease , 2021, Communications biology.

[12]  Jasper Snoek,et al.  Second opinion needed: communicating uncertainty in medical machine learning , 2021, npj Digital Medicine.

[13]  Simon B. Eickhoff,et al.  Tractography density affects whole-brain structural architecture and resting-state dynamical modeling , 2020, NeuroImage.

[14]  Ninon Burgos,et al.  Machine learning for classification and prediction of brain diseases: recent advances and upcoming challenges. , 2020, Current opinion in neurology.

[15]  David N. Kennedy,et al.  Understanding the impact of preprocessing pipelines on neuroimaging cortical surface analyses , 2020, bioRxiv.

[16]  Bradley C. Love,et al.  Variability in the analysis of a single neuroimaging dataset by many teams , 2019, Nature.

[17]  Ellen Poliakoff,et al.  Machine learning algorithm validation with a limited sample size , 2019, PloS one.

[18]  Daniele Marinazzo,et al.  Modeling brain dynamics after tumor resection using The Virtual Brain , 2019, NeuroImage.

[19]  Joel Nothman,et al.  SciPy 1.0-Fundamental Algorithms for Scientific Computing in Python , 2019, ArXiv.

[20]  P. Tass,et al.  Adaptive delivery of continuous and delayed feedback deep brain stimulation - a computational study , 2019, Scientific Reports.

[21]  C. Hartmann,et al.  Machine-learning identifies Parkinson's disease patients based on resting-state between-network functional connectivity. , 2019, The British journal of radiology.

[22]  Chun-Hung Yeh,et al.  MRtrix3: A fast, flexible and open software framework for medical image processing and visualisation , 2019, NeuroImage.

[23]  Karla Batista-García-Ramó,et al.  What We Know About the Brain Structure–Function Relationship , 2018, Behavioral sciences.

[24]  J. Zimmermann,et al.  Differentiation of Alzheimer's disease based on local and global parameters in personalized Virtual Brain models , 2018, NeuroImage: Clinical.

[25]  Anna Plachti,et al.  On the integrity of functional brain networks in schizophrenia, Parkinson's disease, and advanced age: Evidence from connectivity‐based single‐subject classification , 2017, Human brain mapping.

[26]  Karl J. Friston,et al.  Uncovering the underlying mechanisms and whole-brain dynamics of deep brain stimulation for Parkinson’s disease , 2017, Scientific Reports.

[27]  Gustavo Deco,et al.  Cognitive performance in healthy older adults relates to spontaneous switching between states of functional connectivity during rest , 2017, Scientific Reports.

[28]  Evan M. Gordon,et al.  Local-Global Parcellation of the Human Cerebral Cortex From Intrinsic Functional Connectivity MRI , 2017, bioRxiv.

[29]  C. Hartmann,et al.  Differential Functional Connectivity Alterations of Two Subdivisions within the Right dlPFC in Parkinson's Disease , 2017, Front. Hum. Neurosci..

[30]  Simon B. Eickhoff,et al.  Resting-state test–retest reliability of a priori defined canonical networks over different preprocessing steps , 2017, Brain Structure and Function.

[31]  Vince D. Calhoun,et al.  The effect of preprocessing pipelines in subject classification and detection of abnormal resting state functional network connectivity using group ICA , 2017, NeuroImage.

[32]  Gustavo Deco,et al.  The dynamics of resting fluctuations in the brain: metastability and its dynamical cortical core , 2016, bioRxiv.

[33]  Michael Breakspear,et al.  Whole-brain analytic measures of network communication reveal increased structure-function correlation in right temporal lobe epilepsy , 2016, NeuroImage: Clinical.

[34]  Anthony R. McIntosh,et al.  Functional Mechanisms of Recovery after Chronic Stroke: Modeling with the Virtual Brain123 , 2016, eNeuro.

[35]  A. Schnitzler,et al.  Functional Connectivity Differences of the Subthalamic Nucleus Related to Parkinson's Disease , 2016, Human brain mapping.

[36]  Karl J. Friston,et al.  Physiologically informed dynamic causal modeling of fMRI data , 2015, NeuroImage.

[37]  M. Chun,et al.  Functional connectome fingerprinting: Identifying individuals based on patterns of brain connectivity , 2015, Nature Neuroscience.

[38]  G. Tononi,et al.  Rethinking segregation and integration: contributions of whole-brain modelling , 2015, Nature Reviews Neuroscience.

[39]  Michael W. Cole,et al.  Early-Course Unmedicated Schizophrenia Patients Exhibit Elevated Prefrontal Connectivity Associated with Longitudinal Change , 2015, The Journal of Neuroscience.

[40]  Jan Sijbers,et al.  Multi-tissue constrained spherical deconvolution for improved analysis of multi-shell diffusion MRI data , 2014, NeuroImage.

[41]  M. Hallett,et al.  Frequency‐dependent neural activity in Parkinson's disease , 2014, Human brain mapping.

[42]  Andrew Zalesky,et al.  Disruption of structure–function coupling in the schizophrenia connectome , 2014, NeuroImage: Clinical.

[43]  Michael W. Cole,et al.  Altered global brain signal in schizophrenia , 2014, Proceedings of the National Academy of Sciences.

[44]  Morten L. Kringelbach,et al.  Neural Plasticity in Human Brain Connectivity: The Effects of Long Term Deep Brain Stimulation of the Subthalamic Nucleus in Parkinson’s Disease , 2014, PloS one.

[45]  Gustavo Deco,et al.  Structural connectivity in schizophrenia and its impact on the dynamics of spontaneous functional networks. , 2013, Chaos.

[46]  Karl J. Friston,et al.  Structural and Functional Brain Networks: From Connections to Cognition , 2013, Science.

[47]  R. Caminiti,et al.  Diameter, Length, Speed, and Conduction Delay of Callosal Axons in Macaque Monkeys and Humans: Comparing Data from Histology and Magnetic Resonance Imaging Diffusion Tractography , 2013, The Journal of Neuroscience.

[48]  Joaquín Goñi,et al.  Abnormal rich club organization and functional brain dynamics in schizophrenia. , 2013, JAMA psychiatry.

[49]  Roland N. Boubela,et al.  Beyond Noise: Using Temporal ICA to Extract Meaningful Information from High-Frequency fMRI Signal Fluctuations during Rest , 2013, Front. Hum. Neurosci..

[50]  Karl J. Friston,et al.  Neural masses and fields in dynamic causal modeling , 2013, Front. Comput. Neurosci..

[51]  Dinggang Shen,et al.  Resting-State Multi-Spectrum Functional Connectivity Networks for Identification of MCI Patients , 2012, PloS one.

[52]  G Deco,et al.  Functional Graph Alterations in Schizophrenia: A Result from a Global Anatomic Decoupling? , 2012, Pharmacopsychiatry.

[53]  Alexis T Baria,et al.  Anatomical and Functional Assemblies of Brain BOLD Oscillations , 2011, The Journal of Neuroscience.

[54]  Brian B. Avants,et al.  N4ITK: Improved N3 Bias Correction , 2010, IEEE Transactions on Medical Imaging.

[55]  Bharat B. Biswal,et al.  The oscillating brain: Complex and reliable , 2010, NeuroImage.

[56]  O Sporns,et al.  Predicting human resting-state functional connectivity from structural connectivity , 2009, Proceedings of the National Academy of Sciences.

[57]  Andrea A. Kühn,et al.  Pathological synchronisation in the subthalamic nucleus of patients with Parkinson's disease relates to both bradykinesia and rigidity , 2009, Experimental Neurology.

[58]  Cornelis J. Stam,et al.  Increased cortico-cortical functional connectivity in early-stage Parkinson's disease: An MEG study , 2008, NeuroImage.

[59]  Anders M. Dale,et al.  An automated labeling system for subdividing the human cerebral cortex on MRI scans into gyral based regions of interest , 2006, NeuroImage.

[60]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[61]  P. Brown,et al.  Cortico-cortical coupling in Parkinson's disease and its modulation by therapy. , 2005, Brain : a journal of neurology.

[62]  Mark W. Woolrich,et al.  Advances in functional and structural MR image analysis and implementation as FSL , 2004, NeuroImage.

[63]  Karl J. Friston,et al.  Dynamic causal modelling , 2003, NeuroImage.

[64]  Eric R. Ziegel,et al.  The Elements of Statistical Learning , 2003, Technometrics.

[65]  Karl J. Friston,et al.  To Smooth or Not to Smooth? Bias and Efficiency in fMRI Time-Series Analysis , 2000, NeuroImage.

[66]  Anders M. Dale,et al.  Cortical Surface-Based Analysis I. Segmentation and Surface Reconstruction , 1999, NeuroImage.

[67]  R. Buxton,et al.  Dynamics of blood flow and oxygenation changes during brain activation: The balloon model , 1998, Magnetic resonance in medicine.

[68]  M. Hallett Human Brain Function , 1998, Trends in Neurosciences.

[69]  R W Cox,et al.  AFNI: software for analysis and visualization of functional magnetic resonance neuroimages. , 1996, Computers and biomedical research, an international journal.

[70]  Ben H. Jansen,et al.  Electroencephalogram and visual evoked potential generation in a mathematical model of coupled cortical columns , 1995, Biological Cybernetics.

[71]  Alan C. Evans,et al.  A Three-Dimensional Statistical Analysis for CBF Activation Studies in Human Brain , 1992, Journal of cerebral blood flow and metabolism : official journal of the International Society of Cerebral Blood Flow and Metabolism.

[72]  M. Raichle,et al.  The Effects of Changes in PaCO2 Cerebral Blood Volume, Blood Flow, and Vascular Mean Transit Time , 1974, Stroke.

[73]  L. V. Kantorovich,et al.  Mathematical Methods of Organizing and Planning Production , 1960 .

[74]  E. Katunina,et al.  [Epidemiology of Parkinson's disease]. , 2013, Zhurnal nevrologii i psikhiatrii imeni S.S. Korsakova.

[75]  M. Greicius,et al.  Resting-state functional connectivity reflects structural connectivity in the default mode network. , 2009, Cerebral cortex.

[76]  A. Connelly,et al.  Improved probabilistic streamlines tractography by 2 nd order integration over fibre orientation distributions , 2009 .

[77]  Nikos Makris,et al.  Automatically parcellating the human cerebral cortex. , 2004, Cerebral cortex.

[78]  R. Tibshirani Regression Shrinkage and Selection via the Lasso , 1996 .

[79]  G. Brier VERIFICATION OF FORECASTS EXPRESSED IN TERMS OF PROBABILITY , 1950 .