A variational Bayesian approach for the robust analysis of the cortical silent period from EMG recordings of brain stroke patients

Transcranial magnetic stimulation (TMS) is a powerful tool for the calculation of parameters related to the intracortical excitability and inhibition of the motor cortex. The cortical silent period (CSP) is one such parameter that corresponds to the suppression of muscle activity for a short period after a muscle response to TMS. The duration of the CSP is known to be correlated with the prognosis of brain stroke patients' motor ability. Current methods for the estimation of the CSP duration are very sensitive to the presence of noise. A variational Bayesian formulation of a manifold-constrained hidden Markov model is applied in this paper to the segmentation of a set of multivariate time series (MTS) of electromyographic recordings corresponding to stroke patients and control subjects. A novel index of variability associated to this model is defined and applied to the detection of the silent period interval of the signal and to the estimation of its duration. This model and its associated index are shown to behave robustly in the presence of noise and provide more reliable estimations than the current standard in clinical practice.

[1]  B. Shahani,et al.  Motor inhibition and excitation are independent effects of magnetic cortical stimulation , 1992, Annals of neurology.

[2]  L. Baum,et al.  An inequality with applications to statistical estimation for probabilistic functions of Markov processes and to a model for ecology , 1967 .

[3]  Yasuo Terao,et al.  Basic Mechanisms of TMS , 2002, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.

[4]  Matthew J. Beal.  Variational algorithms for approximate Bayesian inference , 2003 .

[5]  Peter Langhorne,et al.  Effects of Augmented Exercise Therapy Time After Stroke: A Meta-Analysis , 2004, Stroke.

[6]  Nick J. Davey,et al.  Estimation of cortical silent period following transcranial magnetic stimulation using a computerised cumulative sum method , 2006, Journal of Neuroscience Methods.

[7]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[8]  Cornelius Weiller,et al.  The surround inhibition determines therapy-induced cortical reorganization , 2006, NeuroImage.

[9]  Geoffrey E. Hinton,et al.  GTM through time , 1997 .

[10]  Paulo J. G. Lisboa,et al.  Selective smoothing of the generative topographic mapping , 2003, IEEE Trans. Neural Networks.

[11]  M. Kramer.  Nonlinear principal component analysis using autoassociative neural networks , 1991 .

[12]  C. I. Mosier.  A note on dwyer: The determination of the factor loadings of a given test , 1938 .

[13]  A Schnitzler,et al.  The motor syndrome associated with exaggerated inhibition within the primary motor cortex of patients with hemiparetic. , 1997, Brain : a journal of neurology.

[14]  IItevor Hattie.  Principal Curves and Surfaces , 1984 .

[15]  Jack L. Lancaster,et al.  Automated-parameterization of the motor evoked potential and cortical silent period induced by transcranial magnetic stimulation , 2009, Clinical Neurophysiology.

[16]  Sergio P. Rigonatti,et al.  Transcranial direct current stimulation of the unaffected hemisphere in stroke patients , 2005, Neuroreport.

[17]  Alfredo Vellido,et al.  Semi-supervised geodesic Generative Topographic Mapping , 2010, Pattern Recognit. Lett..

[18]  Heng Tao Shen,et al.  Principal Component Analysis , 2009, Encyclopedia of Biometrics.

[19]  Robert Chen,et al.  An automated method to determine the transcranial magnetic stimulation-induced contralateral silent period , 2003, Clinical Neurophysiology.

[20]  Paolo Maria Rossini,et al.  Neurophysiological follow-up of motor cortical output in stroke patients , 2000, Clinical Neurophysiology.

[21]  Á. Pascual-Leone,et al.  Transcranial magnetic stimulation in neurology , 2003, The Lancet Neurology.

[22]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[23]  A. Berardelli.  Transcranial magnetic stimulation in movement disorders. , 1999, Electroencephalography and clinical neurophysiology. Supplement.

[24]  A. E. Maxwell,et al.  Factor Analysis as a Statistical Method. , 1964 .

[25]  Ata Kabán,et al.  A Dynamic Probabilistic Model to Visualise Topic Evolution in Text Streams , 2002, Journal of Intelligent Information Systems.

[26]  Peter Tiño,et al.  Hierarchical GTM: Constructing Localized Nonlinear Projection Manifolds in a Principled Way , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[27]  Mark A. Girolami.  Latent variable models for the topographic organisation of discrete and strictly positive data , 2002, Neurocomputing.

[28]  Alfredo Vellido,et al.  On the benefits for model regularization of a variational formulation of GTM , 2008, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).

[29]  A. Basilevsky,et al.  Factor Analysis as a Statistical Method. , 1964 .

[30]  T. Münte,et al.  Using musical instruments to improve motor skill recovery following a stroke , 2007, Journal of Neurology.

[31]  Christopher M. Bishop,et al.  Developments of the generative topographic mapping , 1998, Neurocomputing.

[32]  Alfredo Vellido,et al.  Comparative Assessment of the Robustness of Missing Data Imputation Through Generative Topographic Mapping , 2005, IWANN.

[33]  M. Veloso,et al.  Latent Variable Models , 2019, Statistical and Econometric Methods for Transportation Data Analysis.

[34]  P M Rossini,et al.  Post-stroke reorganization of brain motor output to the hand: a 2-4 month follow-up with focal magnetic transcranial stimulation. , 1997, Electroencephalography and clinical neurophysiology.

[35]  Michael Y. Hu,et al.  Forecasting with artificial neural networks: The state of the art , 1997 .

[36]  B. Dobkin.  Rehabilitation after Stroke , 2005 .

[37]  Iván Olier Caparroso.  Variational bayesian algorithms for generative topographic mapping and its extensions , 2008 .

[38]  Armin Thron,et al.  Motor representation in patients rapidly recovering after stroke: a functional magnetic resonance imaging and transcranial magnetic stimulation study , 2003, Clinical Neurophysiology.

[39]  Stan Lipovetsky,et al.  Latent Variable Models and Factor Analysis , 2001, Technometrics.

[40]  Paulo J. G. Lisboa,et al.  Robust analysis of MRS brain tumour data using t-GTM , 2006, Neurocomputing.

[41]  Alfredo Vellido,et al.  Advances in clustering and visualization of time series using GTM through time , 2008, Neural Networks.

[42]  Christopher M. Bishop,et al.  GTM: The Generative Topographic Mapping , 1998, Neural Computation.

[43]  Joachim Liepert,et al.  Motor Cortex Excitability in Stroke Before and After Constraint-induced Movement Therapy , 2006, Cognitive and behavioral neurology : official journal of the Society for Behavioral and Cognitive Neurology.

[44]  L. Cronbach.  Coefficient alpha and the internal structure of tests , 1951 .

[45]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[46]  Alfredo Vellido,et al.  A variational formulation for GTM through time , 2008, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).

[47]  M. Hallett.  Transcranial Magnetic Stimulation: A Primer , 2007, Neuron.

[48]  C. Caltagirone,et al.  Cerebellar magnetic stimulation decreases levodopa-induced dyskinesias in Parkinson disease , 2009, Neurology.

[49]  Craig B. Borkowf,et al.  Time-Series Forecasting , 2002, Technometrics.

[50]  Christopher M. Bishop,et al.  A Hierarchical Latent Variable Model for Data Visualization , 1998, IEEE Trans. Pattern Anal. Mach. Intell..