Brain-computer interface controlled robotic gait orthosis

BackgroundExcessive reliance on wheelchairs in individuals with tetraplegia or paraplegia due to spinal cord injury (SCI) leads to many medical co-morbidities, such as cardiovascular disease, metabolic derangements, osteoporosis, and pressure ulcers. Treatment of these conditions contributes to the majority of SCI health care costs. Restoring able-body-like ambulation in this patient population can potentially reduce the incidence of these medical co-morbidities, in addition to increasing independence and quality of life. However, no biomedical solution exists that can reverse this loss of neurological function, and hence novel methods are needed. Brain-computer interface (BCI) controlled lower extremity prostheses may constitute one such novel approach.MethodsOne able-bodied subject and one subject with paraplegia due to SCI underwent electroencephalogram (EEG) recordings while engaged in alternating epochs of idling and walking kinesthetic motor imagery (KMI). These data were analyzed to generate an EEG prediction model for online BCI operation. A commercial robotic gait orthosis (RoGO) system (suspended over a treadmill) was interfaced with the BCI computer to allow for computerized control. The subjects were then tasked to perform five, 5-min-long online sessions where they ambulated using the BCI-RoGO system as prompted by computerized cues. The performance of this system was assessed with cross-correlation analysis, and omission and false alarm rates.ResultsThe offline accuracy of the EEG prediction model averaged 86.30% across both subjects (chance: 50%). The cross-correlation between instructional cues and the BCI-RoGO walking epochs averaged across all subjects and all sessions was 0.812±0.048 (p-value <10−4). Also, there were on average 0.8 false alarms per session and no omissions.ConclusionThese results provide preliminary evidence that restoring brain-controlled ambulation after SCI is feasible. Future work will test the function of this system in a population of subjects with SCI. If successful, this may justify the future development of BCI-controlled lower extremity prostheses for free overground walking for those with complete motor SCI. Finally, this system can also be applied to incomplete motor SCI, where it could lead to improved neurological outcomes beyond those of standard physiotherapy.

[1]  Zoran Nenadic,et al.  Brain-computer interface controlled functional electrical stimulation device for foot drop due to stroke , 2012, 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[2]  O. Basso,et al.  What is a population-based registry? , 1999, Scandinavian journal of public health.

[3]  Z. Nenadic,et al.  A Classwise PCA-based Recognition of Neural Data for Brain-Computer Interfaces , 2007, 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[4]  David J. Reinkensmeyer,et al.  Noninvasive brain-computer interface driven hand orthosis , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[5]  An H. Do,et al.  Brain-Computer Interface Controlled Functional Electrical Stimulation System for Ankle Movement , 2011, Journal of NeuroEngineering and Rehabilitation.

[6]  Po T. Wang,et al.  BCI Controlled Walking Simulator For a BCI Driven FES Device , 2010 .

[7]  Zoran Nenadic,et al.  Approximate information discriminant analysis: A computationally simple heteroscedastic feature extraction technique , 2008, Pattern Recognit..

[8]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[9]  Zoran Nenadic,et al.  Operation of a Brain-Computer Interface Walking Simulator by Users with Spinal Cord Injury , 2012, ArXiv.

[10]  Zoran Nenadic,et al.  An efficient discriminant-based solution for small sample size problem , 2009, Pattern Recognit..

[11]  Kamiar Aminian,et al.  Spatio-temporal parameters of gait measured by an ambulatory system using miniature gyroscopes. , 2002, Journal of biomechanics.

[12]  Thomas Brandt,et al.  Real versus imagined locomotion: A [18F]-FDG PET-fMRI comparison , 2010, NeuroImage.

[13]  Zoran Nenadic,et al.  Self-paced brain–computer interface control of ambulation in a virtual reality environment , 2012, Journal of neural engineering.

[14]  S. Mazzoleni,et al.  Effects of a robot-mediated locomotor training on EMG activation in healthy and SCI subjects , 2009, 2009 IEEE International Conference on Rehabilitation Robotics.

[15]  G. Whiteneck,et al.  Cost of traumatic spinal cord injury in a population-based registry , 1996, Spinal Cord.

[16]  An H. Do,et al.  Operation of a brain-computer interface walking simulator for individuals with spinal cord injury , 2013, Journal of NeuroEngineering and Rehabilitation.