Review of Machine Learning Algorithms for Brain Stroke Diagnosis and Prognosis by EEG Analysis

Currently, strokes are the leading cause of adult disability in the United States. Traditional treatment and rehabilitation options such as physical therapy and tissue plasminogen activator are limited in their effectiveness and ability to restore mobility and function to the patient. As a result, there exists an opportunity to greatly improve the treatment for strokes. Machine learning, specifically techniques that utilize Brain-Computer Interfaces (BCIs) to help the patient either restore neurologic pathways or effectively communicate with an electronic prosthetic, show promising results when applied to both stroke diagnosis and rehabilitation. In this review, sources that design and implement BCIs for treatment of stroke patients are evaluated and categorized based on their successful applications for stroke diagnosis or stroke rehabilitation. The various machine learning techniques and algorithms that are addressed and combined with BCI technology show that the use of BCIs for stroke treatment is a promising and rapidly expanding field.

[1]  Max A Viergever,et al.  Early Identification of Potentially Salvageable Tissue with MRI-Based Predictive Algorithms after Experimental Ischemic Stroke , 2013, Journal of cerebral blood flow and metabolism : official journal of the International Society of Cerebral Blood Flow and Metabolism.

[2]  Brice Rebsamen,et al.  A brain controlled wheelchair to navigate in familiar environments. , 2010, IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[3]  Liqing Zhang,et al.  Exploring Motor Imagery Eeg Patterns for Stroke Patients with Deep Neural Networks , 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[4]  Cuntai Guan,et al.  EEG-Based Strategies to Detect Motor Imagery for Control and Rehabilitation , 2017, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[5]  Xingyu Wang,et al.  Differences in Motor Imagery Activity Between the Paretic and Non-paretic Hands in Stroke Patients Using an EEG BCI , 2017, HCI.

[6]  Liqing Zhang,et al.  A Boosting-Based Spatial-Spectral Model for Stroke Patients’ EEG Analysis in Rehabilitation Training , 2016, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[7]  N. Birbaumera,et al.  Brain-machine interfaces for rehabilitation in stroke : A review , 2018 .

[8]  Guillermo Sapiro,et al.  A Shared Vision for Machine Learning in Neuroscience , 2018, The Journal of Neuroscience.

[9]  Brittany M. Young,et al.  Early Findings on Functional Connectivity Correlates of Behavioral Outcomes of Brain-Computer Interface Stroke Rehabilitation Using Machine Learning , 2018, Front. Neurosci..

[10]  Dario Pompili,et al.  Multimodal data analysis of epileptic EEG and rs-fMRI via deep learning and edge computing , 2020, Artif. Intell. Medicine.

[11]  Samar Hamid,et al.  Role of electrical stimulation for rehabilitation and regeneration after spinal cord injury: an overview , 2008, European Spine Journal.

[12]  L. Cohen,et al.  Decoding upper limb residual muscle activity in severe chronic stroke , 2014, Annals of clinical and translational neurology.

[13]  Jonathan R Wolpaw,et al.  Sensorimotor rhythm-based brain–computer interface (BCI): model order selection for autoregressive spectral analysis , 2008, Journal of neural engineering.

[14]  Bin He,et al.  Brain–Computer Interfaces Using Sensorimotor Rhythms: Current State and Future Perspectives , 2014, IEEE Transactions on Biomedical Engineering.

[15]  L. Cohen,et al.  Brain–machine interface in chronic stroke rehabilitation: A controlled study , 2013, Annals of neurology.

[16]  Ricardo Chavarriaga,et al.  Errare machinale est: the use of error-related potentials in brain-machine interfaces , 2014, Front. Neurosci..

[17]  Carlos Bibian,et al.  Influence of artifacts on movement intention decoding from EEG activity in severely paralyzed stroke patients , 2017, 2017 International Conference on Rehabilitation Robotics (ICORR).

[18]  L. Cohen,et al.  Mechanisms underlying recovery of motor function after stroke , 2005, Postgraduate Medical Journal.

[19]  Sarah N. Kraeutner,et al.  Motor imagery-based brain activity parallels that of motor execution: Evidence from magnetic source imaging of cortical oscillations , 2014, Brain Research.

[20]  Xiaomu Song,et al.  A unified machine learning method for task-related and resting state fMRI data analysis , 2014, 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[21]  Jonathan R Wolpaw,et al.  Control of a two-dimensional movement signal by a noninvasive brain-computer interface in humans. , 2004, Proceedings of the National Academy of Sciences of the United States of America.

[22]  Mohammad-Parsa Hosseini,et al.  A Review on Machine Learning for EEG Signal Processing in Bioengineering , 2020, IEEE Reviews in Biomedical Engineering.

[23]  Z. Keirn,et al.  A new mode of communication between man and his surroundings , 1990, IEEE Transactions on Biomedical Engineering.

[24]  Mark Hallett,et al.  A binary method for simple and accurate two-dimensional cursor control from EEG with minimal subject training , 2009, Journal of NeuroEngineering and Rehabilitation.

[25]  E. Donchin,et al.  Talking off the top of your head: toward a mental prosthesis utilizing event-related brain potentials. , 1988, Electroencephalography and clinical neurophysiology.

[26]  G. Schalk,et al.  The emerging world of motor neuroprosthetics: a neurosurgical perspective. , 2006, Neurosurgery.

[27]  K. Mouridsen,et al.  Prediction of Tissue Outcome and Assessment of Treatment Effect in Acute Ischemic Stroke Using Deep Learning , 2018, Stroke.

[28]  T. Soemardi,et al.  Electroencephalography (EEG) for detecting acute ischemic stroke , 2015, 2015 4th International Conference on Instrumentation, Communications, Information Technology, and Biomedical Engineering (ICICI-BME).

[29]  Bernhard Neundörfer,et al.  Lifetime Cost of Ischemic Stroke in Germany: Results and National Projections From a Population-Based Stroke Registry: The Erlangen Stroke Project , 2006, Stroke.

[30]  Justin C. Williams,et al.  Machine Learning Classification to Identify the Stage of Brain-Computer Interface Therapy for Stroke Rehabilitation Using Functional Connectivity , 2018, Front. Neurosci..

[31]  N. Birbaumer,et al.  Brain–computer interfaces for communication and rehabilitation , 2016, Nature Reviews Neurology.

[32]  Reza Abiri,et al.  A comprehensive review of EEG-based brain–computer interface paradigms , 2019, Journal of neural engineering.

[33]  Liqing Zhang,et al.  Gaussian mixture modeling in stroke patients' rehabilitation EEG data analysis , 2013, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[34]  G. Pfurtscheller,et al.  ‘Thought’ – control of functional electrical stimulation to restore hand grasp in a patient with tetraplegia , 2003, Neuroscience Letters.

[35]  Jong-Hwan Lee,et al.  ERS differences between stroke patients and healthy controls after hand movement , 2016, 2016 4th International Winter Conference on Brain-Computer Interface (BCI).

[36]  Darren J. Leamy,et al.  An exploration of EEG features during recovery following stroke – implications for BCI-mediated neurorehabilitation therapy , 2014, Journal of NeuroEngineering and Rehabilitation.

[37]  Marcus A. Badgeley,et al.  Deep learning guided stroke management: a review of clinical applications , 2017, Journal of NeuroInterventional Surgery.

[38]  E B Stear,et al.  A new approach to prosthetic control: EEG motor signal tracking with an adaptively designed phase-locked loop. , 1971, IEEE transactions on bio-medical engineering.

[39]  Dario Pompili,et al.  Optimized Deep Learning for EEG Big Data and Seizure Prediction BCI via Internet of Things , 2017, IEEE Transactions on Big Data.

[40]  J J Vidal,et al.  Toward direct brain-computer communication. , 1973, Annual review of biophysics and bioengineering.

[41]  Touradj Ebrahimi,et al.  An efficient P300-based brain–computer interface for disabled subjects , 2008, Journal of Neuroscience Methods.

[42]  Hermano Igo Krebs,et al.  MIT-MANUS: a workstation for manual therapy and training. I , 1992, [1992] Proceedings IEEE International Workshop on Robot and Human Communication.

[43]  Yang Wei-we,et al.  A Review on , 2008 .

[44]  M. Nicolelis,et al.  Brain-Machine Interfaces: From Basic Science to Neuroprostheses and Neurorehabilitation. , 2017, Physiological reviews.

[45]  Sabine Van Huffel,et al.  Machine Learning Approach for Classifying Multiple Sclerosis Courses by Combining Clinical Data with Lesion Loads and Magnetic Resonance Metabolic Features , 2017, Front. Neurosci..

[46]  Dinggang Shen,et al.  Machine Learning in Medical Imaging , 2012, Lecture Notes in Computer Science.

[47]  M. Molinari,et al.  Rehabilitation of gait after stroke: a review towards a top-down approach , 2011, Journal of NeuroEngineering and Rehabilitation.

[48]  Laura Astolfi,et al.  Interfacing brain and computer in neurorehabilitation , 2016, 2016 4th International Winter Conference on Brain-Computer Interface (BCI).

[49]  Jie Yang,et al.  Degree prediction of malignancy in brain glioma using support vector machines , 2006, Comput. Biol. Medicine.

[50]  Xun Chen,et al.  Classification of EEG Signals Using a Multiple Kernel Learning Support Vector Machine , 2014, Sensors.

[51]  Youxi Wu,et al.  Classification of Mental Task From EEG Signals Using Immune Feature Weighted Support Vector Machines , 2011, IEEE Transactions on Magnetics.

[52]  Stephan Waldert,et al.  Invasive vs. Non-Invasive Neuronal Signals for Brain-Machine Interfaces: Will One Prevail? , 2016, Front. Neurosci..

[53]  Jose L. Contreras-Vidal,et al.  Design and Optimization of an EEG-Based Brain Machine Interface (BMI) to an Upper-Limb Exoskeleton for Stroke Survivors , 2016, Front. Neurosci..

[54]  M. Hallett,et al.  Classifying EEG signals preceding right hand, left hand, tongue, and right foot movements and motor imageries , 2008, Clinical Neurophysiology.

[55]  Du-Yih Tsai,et al.  An automated detection method for the MCA dot sign of acute stroke in unenhanced CT , 2013, Radiological Physics and Technology.

[56]  V Kishore Ayyadevara,et al.  Pro Machine Learning Algorithms , 2018, Apress.

[57]  Jan Claassen,et al.  Quantitative EEG for the detection of brain ischemia , 2012, Critical Care.

[58]  João Ricardo Sato,et al.  Defining multivariate normative rules for healthy aging using neuroimaging and machine learning: an application to Alzheimer's disease. , 2014, Journal of Alzheimer's disease : JAD.

[59]  E. W. Sellers,et al.  Toward enhanced P300 speller performance , 2008, Journal of Neuroscience Methods.

[60]  Nathan Intrator,et al.  Machine learning fMRI classifier delineates subgroups of schizophrenia patients , 2014, Schizophrenia Research.

[61]  Zoran Nenadic,et al.  Brain-computer interface controlled robotic gait orthosis , 2012, Journal of NeuroEngineering and Rehabilitation.

[62]  Dario Pompili,et al.  Random ensemble learning for EEG classification , 2018, Artif. Intell. Medicine.

[63]  Bin He,et al.  Noninvasive Brain-Computer Interfaces Based on Sensorimotor Rhythms , 2015, Proceedings of the IEEE.

[64]  Pasin Israsena,et al.  Comparison of EEG measurement of upper limb movement in motor imagery training system , 2018, BioMedical Engineering OnLine.

[65]  Dewen Hu,et al.  Decreased white matter integrity in mesial temporal lobe epilepsy: a machine learning approach , 2014, Neuroreport.

[66]  N. Hogan,et al.  Response to upper-limb robotics and functional neuromuscular stimulation following stroke. , 2005, Journal of rehabilitation research and development.

[67]  C.W. Anderson,et al.  Comparison of linear, nonlinear, and feature selection methods for EEG signal classification , 2003, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[68]  D. Basak,et al.  Support Vector Regression , 2008 .

[69]  Hamid Soltanian-Zadeh,et al.  Multimodal Analysis in Biomedicine , 2019 .

[70]  C. Neuper,et al.  Combining Brain–Computer Interfaces and Assistive Technologies: State-of-the-Art and Challenges , 2010, Front. Neurosci..

[71]  Kiseon Kim,et al.  Review of Wireless Brain-Computer Interface Systems , 2013 .

[72]  J. Wolpaw,et al.  Clinical Applications of Brain-Computer Interfaces: Current State and Future Prospects , 2009, IEEE Reviews in Biomedical Engineering.

[73]  F. L. D. Silva,et al.  Event-related EEG/MEG synchronization and desynchronization: basic principles , 1999, Clinical Neurophysiology.

[74]  R Chavarriaga,et al.  Learning From EEG Error-Related Potentials in Noninvasive Brain-Computer Interfaces , 2010, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[75]  Dean J Krusienski,et al.  Brain-computer interfaces in medicine. , 2012, Mayo Clinic proceedings.

[76]  Ricardo Ron-Angevin,et al.  Brain–computer interface: Changes in performance using virtual reality techniques , 2009, Neuroscience Letters.

[77]  Dario Pompili,et al.  Cloud-based deep learning of big EEG data for epileptic seizure prediction , 2016, 2016 IEEE Global Conference on Signal and Information Processing (GlobalSIP).

[78]  Liang Chen,et al.  Fully automatic acute ischemic lesion segmentation in DWI using convolutional neural networks , 2017, NeuroImage: Clinical.

[79]  Miguel A. L. Nicolelis,et al.  Brain–machine interfaces: past, present and future , 2006, Trends in Neurosciences.

[80]  P. Celnik,et al.  Stroke Rehabilitation. , 2015, Physical medicine and rehabilitation clinics of North America.

[81]  Mohamad Ivan Fanany,et al.  Ischemic stroke identification based on EEG and EOG using ID convolutional neural network and batch normalization , 2016, 2016 International Conference on Advanced Computer Science and Information Systems (ICACSIS).

[82]  Andrés Úbeda,et al.  LDA-based classifiers for a mental tasks-based Brain-Computer Interface , 2010, IEEE International Conference on Systems, Man and Cybernetics.

[83]  M. Kubát.  An Introduction to Machine Learning , 2017, Springer International Publishing.

[84]  Eric Leuthardt,et al.  An EEG-based brain computer interface for rehabilitation and restoration of hand control following stroke using ipsilateral cortical physiology , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[85]  B. Rockstroh,et al.  Biofeedback of slow cortical potentials. I. , 1980, Electroencephalography and clinical neurophysiology.

[86]  Dennis J. McFarland,et al.  Brain–computer interfaces for communication and control , 2002, Clinical Neurophysiology.

[87]  Dean J Krusienski,et al.  Emulation of computer mouse control with a noninvasive brain–computer interface , 2008, Journal of neural engineering.

[88]  M. Jeannerod.  Mental imagery in the motor context , 1995, Neuropsychologia.

[89]  Mads Jochumsen,et al.  Prediction of Hand Movement Speed and Force from Single-trial EEG with Convolutional Neural Networks , 2018, bioRxiv.

[90]  Ayman El-Baz,et al.  Big Data in Multimodal Medical Imaging , 2019 .

[91]  Mohammad-Parsa Hosseini,et al.  Deep Learning Architectures , 2019, Deep Learning: Concepts and Architectures.

[92]  Dario Pompili,et al.  Real-Time Epileptic Seizure Detection from EEG Signals via Random Subspace Ensemble Learning , 2016, 2016 IEEE International Conference on Autonomic Computing (ICAC).

[93]  William Speier,et al.  Classifying Acute Ischemic Stroke Onset Time using Deep Imaging Features , 2017, AMIA.

[94]  Sunil A. Sheth,et al.  Machine Learning in Acute Ischemic Stroke Neuroimaging , 2018, Front. Neurol..

[95]  Tonio Ball,et al.  Deep learning with convolutional neural networks for decoding and visualization of EEG pathology , 2017, 2017 IEEE Signal Processing in Medicine and Biology Symposium (SPMB).

[96]  Francesca N. Delling,et al.  Heart Disease and Stroke Statistics—2018 Update: A Report From the American Heart Association , 2018, Circulation.