Online asynchronous detection of error-related potentials in participants with a spinal cord injury using a generic classifier

A brain-computer interface (BCI) user awareness of an error is associated with a cortical signature named error-related potential (ErrP). The incorporation of ErrPs' detection in BCIs can improve BCIs' performance. OBJECTIVE This work is three-folded. First, we investigate if an ErrP classifier is transferable from able-bodied participants to participants with spinal cord injury (SCI). Second, we test this generic ErrP classifier with SCI and control participants, in an online experiment without offline calibration. Third, we investigate the morphology of ErrPs in both groups of participants. APPROACH We used previously recorded electroencephalographic (EEG) data from able-bodied participants to train an ErrP classifier. We tested the classifier asynchronously, in an online experiment with 16 new participants: 8 participants with SCI and 8 able-bodied control participants. The experiment had no offline calibration and participants received feedback regarding the ErrPs' detection from its start. For a matter of fluidity of the experiment, the feedback regarding false positive ErrP detections was not presented to the participants but these detections were taken into account in the evaluation of the classifier. The generic classifier was not trained with the user's brain signals. Still, its performance was optimized during the online experiment with the use of personalized decision thresholds. The classifier's performance was evaluated using trial-based metrics, which consider the asynchronous detection of ErrPs during the entire trials' duration. MAIN RESULTS Participants with SCI presented a non-homogenous ErrP morphology, and four of them did not present clear ErrP signals. The generic classifier performed above chance level in participants with clear ErrP signals, independently of the SCI (11 out of 16 participants). Three out of the five participants that obtained chance level results with the generic classifier would have not benefited from the use of a personalized classifier. SIGNIFICANCE This work shows the feasibility of transferring an ErrP classifier from able-bodied participants to participants with SCI, for asynchronous detection of ErrPs in an online experiment without offline calibration, which provided immediate feedback to the users.

[1]  Gordon Cheng,et al.  Calibration-Free Error-Related Potential Decoding With Adaptive Subject-Independent Models: A Comparative Study , 2020, IEEE Transactions on Medical Robotics and Bionics.

[2]  Vicenç Gómez,et al.  Adaptive Classification on Brain-Computer Interfaces Using Reinforcement Signals , 2012, Neural Computation.

[3]  K. R. Ridderinkhof,et al.  A computational account of altered error processing in older age: Dopamine and the error-related negativity , 2002, Cognitive, affective & behavioral neuroscience.

[4]  R Chavarriaga,et al.  Latency correction of event-related potentials between different experimental protocols. , 2014, Journal of neural engineering.

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

[6]  Gernot R. Müller-Putz,et al.  Decoding of velocities and positions of 3D arm movement from EEG , 2012, 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[7]  P. Good,et al.  Permutation Tests: A Practical Guide to Resampling Methods for Testing Hypotheses , 1995 .

[8]  Joseph DelPreto,et al.  Correcting robot mistakes in real time using EEG signals , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[9]  Gemma C. Garriga,et al.  Permutation Tests for Studying Classifier Performance , 2009, 2009 Ninth IEEE International Conference on Data Mining.

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

[11]  M. Post,et al.  Psychosocial issues in spinal cord injury: a review , 2012, Spinal Cord.

[12]  Z. Khazaeipour,et al.  Depression Following Spinal Cord Injury: Its Relationship to Demographic and Socioeconomic Indicators. , 2015, Topics in spinal cord injury rehabilitation.

[13]  Amit Konar,et al.  A Generic Transferable EEG Decoder for Online Detection of Error Potential in Target Selection , 2017, Front. Neurosci..

[14]  J. Hohnsbein,et al.  Changes of error-related ERPs with age , 2001, Experimental Brain Research.

[15]  Klaus Gramann,et al.  Neuroadaptive technology enables implicit cursor control based on medial prefrontal cortex activity , 2016, Proceedings of the National Academy of Sciences.

[16]  Gernot R Müller-Putz,et al.  Tuning characteristics of low-frequency EEG to positions and velocities in visuomotor and oculomotor tracking tasks , 2018, Scientific Reports.

[17]  Martin Spüler,et al.  Error-related potentials during continuous feedback: using EEG to detect errors of different type and severity , 2015, Front. Hum. Neurosci..

[18]  P. Sajda,et al.  Response error correction-a demonstration of improved human-machine performance using real-time EEG monitoring , 2003, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[19]  Andreea Ioana Sburlea,et al.  A Comparison of ocular Artifact removal Methods for Block Design based Electroencephalography Experiments , 2017, GBCIC.

[20]  José del R. Millán,et al.  You Are Wrong! - Automatic Detection of Interaction Errors from Brain Waves , 2005, IJCAI.

[21]  Iñaki Iturrate,et al.  Asynchronous detection of error potentials , 2014 .

[22]  José del R. Millán,et al.  BNCI Horizon 2020: Towards a Roadmap for the BCI Community , 2015 .

[23]  Gernot R. Müller-Putz,et al.  Online asynchronous decoding of error-related potentials during the continuous control of a robot , 2019, Scientific Reports.

[24]  Ricardo Chavarriaga,et al.  Asynchronous Decoding of Error Potentials during the Monitoring of a Reaching Task , 2015, 2015 IEEE International Conference on Systems, Man, and Cybernetics.

[25]  Ricardo Chavarriaga,et al.  Minimizing calibration time using inter-subject information of single-trial recognition of error potentials in brain-computer interfaces , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[26]  Ricardo Chavarriaga,et al.  Latency correction of error potentials between different experiments reduces calibration time for single-trial classification , 2012, 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[27]  Andreea Ioana Sburlea,et al.  Asynchronous detection of Error-related potentials using a generic classifier , 2019, GBCIC.

[28]  Andreea Ioana Sburlea,et al.  Corneo-retinal-dipole and eyelid-related eye artifacts can be corrected offline and online in electroencephalographic and magnetoencephalographic signals , 2020, NeuroImage.

[29]  Gordon Cheng,et al.  Human-agent co-adaptation using error-related potentials , 2018, Journal of neural engineering.

[30]  M. Post,et al.  Validity of the mental health subscale of the SF-36 in persons with spinal cord injury , 2012, Spinal Cord.

[31]  B. Tonge,et al.  Spinal Cord Injury and Mental Health , 2008, The Australian and New Zealand journal of psychiatry.

[32]  Christa Neuper,et al.  Error potential detection during continuous movement of an artificial arm controlled by brain–computer interface , 2012, Medical & Biological Engineering & Computing.

[33]  Andreea Ioana Sburlea,et al.  Continuous detection of the self-initiated walking pre-movement state from EEG correlates without session-to-session recalibration , 2015, Journal of neural engineering.

[34]  Stefan Haufe,et al.  Single-trial analysis and classification of ERP components — A tutorial , 2011, NeuroImage.

[35]  Doreen M. Olvet,et al.  Depression symptom severity and error-related brain activity , 2010, Psychiatry Research.

[36]  Elsa Andrea Kirchner,et al.  Classifier Transferability in the Detection of Error Related Potentials from Observation to Interaction , 2013, 2013 IEEE International Conference on Systems, Man, and Cybernetics.

[37]  Akshay Kumar,et al.  Error-Related Neural Responses Recorded by Electroencephalography During Post-stroke Rehabilitation Movements , 2019, Front. Neurorobot..

[38]  R Chavarriaga,et al.  EEG-based decoding of error-related brain activity in a real-world driving task , 2015, Journal of neural engineering.

[39]  J. Pereira,et al.  EEG patterns of self-paced movement imaginations towards externally-cued and internally-selected targets , 2018, Scientific Reports.

[40]  Hongwei Mao,et al.  Decoding arm speed during reaching , 2018, Nature Communications.

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

[42]  Michael Falkenstein,et al.  Aging and Error Processing: Age Related Increase in the Variability of the Error-Negativity Is Not Accompanied by Increase in Response Variability , 2011, PloS one.

[43]  Andreea Ioana Sburlea,et al.  A Generic Error-related Potential Classifier Offers a Comparable Performance to a Personalized Classifier , 2020, 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC).

[44]  Markus Kiefer,et al.  Error processing in major depressive disorder: evidence from event-related potentials. , 2006, Journal of psychiatric research.

[45]  Rabab K. Ward,et al.  Evaluating the performance of a self-paced BCI with a new movement and using a more engaging environment , 2008, 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[46]  L. Montesano,et al.  Analysis and asynchronous detection of gradually unfolding errors during monitoring tasks , 2015, Journal of neural engineering.

[47]  Salwani Mohd Daud,et al.  A Review of Asynchronous Electroencephalogram-based Brain Computer Interface Systems , 2011 .

[48]  Gordon Cheng,et al.  A Feasibility Study for Validating Robot Actions Using EEG-Based Error-Related Potentials , 2018, Int. J. Soc. Robotics.

[49]  Elsa Andrea Kirchner,et al.  Handling Few Training Data: Classifier Transfer Between Different Types of Error-Related Potentials , 2016, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[50]  Rüdiger Rupp,et al.  Differences in Characteristics of Error-Related Potentials Between Individuals With Spinal Cord Injury and Age- and Sex-Matched Able-Bodied Controls , 2019, Front. Neurol..

[51]  J. Morimoto,et al.  Towards a robot-enabled, Neuroscience-guided healthy society , 2013 .

[52]  Vicenç Gómez,et al.  On the use of interaction error potentials for adaptive brain computer interfaces , 2011, Neural Networks.

[53]  Qiong Zhang,et al.  Improving motor imagery BCI with user response to feedback , 2017 .

[54]  Wolfgang Rosenstiel,et al.  Online use of error-related potentials in healthy users and people with severe motor impairment increases performance of a P300-BCI , 2012, Clinical Neurophysiology.

[55]  Brendan Z. Allison,et al.  A hybrid ERD/SSVEP BCI for continuous simultaneous two dimensional cursor control , 2012, Journal of Neuroscience Methods.

[56]  Gernot R Müller-Putz,et al.  Masked and unmasked error-related potentials during continuous control and feedback , 2018, Journal of neural engineering.

[57]  Andreea Ioana Sburlea,et al.  Error-Related potentials with Masked and unmasked onset during continuous control and feedback , 2017, GBCIC.

[58]  Xavier Artusi,et al.  Accuracy of a BCI based on movement-related and error potentials , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[59]  Ferran Argelaguet,et al.  Detecting System Errors in Virtual Reality Using EEG Through Error-Related Potentials , 2020, 2020 IEEE Conference on Virtual Reality and 3D User Interfaces (VR).

[60]  Carlos E. Thomaz,et al.  Statistical learning approaches for discriminant features selection , 2008, Journal of the Brazilian Computer Society.

[61]  G. Pfurtscheller,et al.  EEG-based communication: presence of an error potential , 2000, Clinical Neurophysiology.

[62]  Gernot R. Müller-Putz,et al.  Single Versus Multiple Events Error Potential Detection in a BCI-Controlled Car Game With Continuous and Discrete Feedback , 2016, IEEE Transactions on Biomedical Engineering.

[63]  Á. Gil-Agudo,et al.  Continuous decoding of movement intention of upper limb self-initiated analytic movements from pre-movement EEG correlates , 2014, Journal of NeuroEngineering and Rehabilitation.

[64]  Jonathan D. Cohen,et al.  The neural basis of error detection: conflict monitoring and the error-related negativity. , 2004, Psychological review.

[65]  Frank Kirchner,et al.  Intrinsic interactive reinforcement learning – Using error-related potentials for real world human-robot interaction , 2017, Scientific Reports.

[66]  Tom Chau,et al.  Online detection of error-related potentials in multi-class cognitive task-based BCIs , 2019 .