Brain-Computer Interface Controlled Robotic Gait Orthosis (1208.5024v3)

Abstract: Reliance on wheelchairs after spinal cord injury (SCI) leads to many medical co-morbidities. Treatment of these conditions contributes to the majority of SCI health care costs. Restoring able-body-like ambulation after SCI may reduce the incidence of these conditions, and increase independence and quality of life. However, no biomedical solution exists that can reverse this lost neurological function, and hence novel methods are needed. Brain-computer interface (BCI) controlled lower extremity prosthesis may constitute one such novel approach. One subject with able-body and one with paraplegia due to SCI underwent electroencephalogram (EEG) recording 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 (treadmill suspended), was interfaced with the BCI computer. In an online test, the subjects were tasked to ambulate using the BCI-RoGO system when prompted by computerized cues. The performance of this system was assessed with cross-correlation analysis, and omission and false alarm rates. The offline accuracy of the EEG prediction model averaged 86.3%. The cross-correlation between instructional cues and BCI-RoGO walking epochs averaged 0.812 +/- 0.048 (p-value<10^-4). There were on average 0.8 false alarms per session and no omissions. This is the first time a person with parapegia due to SCI regained basic brain-controlled ambulation, thereby indicating that restoring brain-controlled ambulation is feasible. Future work will test this system in a population of individuals with SCI. If successful, this may justify future development of invasive BCI-controlled lower extremity prostheses. This system may also be applied to incomplete SCI to improve neurological outcomes beyond those of standard physiotherapy.

• The paper evaluates the feasibility of using non-invasive EEG-based brain-computer interfaces (BCI) to control a robotic gait orthosis for individuals with spinal cord injury (SCI).
• The study developed an EEG prediction model based on motor imagery, achieving 86.30% average offline accuracy and significant cross-correlation (0.812) with instructional cues when integrated with the orthosis.
• Results suggest BCI-controlled robotic orthoses have promising potential for restoring ambulation in SCI patients, improving independence, and reducing associated medical comorbidities.

Brain-Computer Interface Controlled Robotic Gait Orthosis: A Novel Approach for Spinal Cord Injury Rehabilitation

The development of brain-computer interface (BCI) systems to control robotic gait orthoses represents a significant advancement in addressing motor impairments due to spinal cord injuries (SCI). This paper evaluates the feasibility of BCI-controlled ambulation using non-invasive electroencephalogram (EEG) recordings interfaced with a commercial robotic gait orthosis (RoGO). The paper involved both an able-bodied subject and a subject with paraplegia from SCI, revealing promising results for the restoration of ambulation and the reduction of medical co-morbidities associated with prolonged wheelchair reliance, such as cardiovascular disease, osteoporosis, and pressure ulcers.

Summary of Methods

The research deployed an EEG-based BCI system where subjects engaged in alternating epochs of idling and walking kinesthetic motor imagery (KMI) to generate a prediction model for BCI operation. This model incorporated a commercial RoGO system, enabling computerized BCI control during ambulation tasks as prompted by cues. Key performance indicators included cross-correlation analyses, omission, and false alarm rates. The prediction model demonstrated robust offline accuracy and successful integration with the RoGO.

Results and Implications

The EEG prediction model achieved an average offline accuracy of 86.30% across subjects, indicating reliable discrimination between idling and walking states (chance: 50%). The cross-correlation between instructional cues and BCI-RoGO performance was notably significant, with an average of 0.812, substantiated by empirical p-values (p-value < 10⁻⁴) via Monte Carlo trials. The paper reported minimal false alarms and zero omissions, suggesting the robustness of BCI control. The observational shift of the subject with paraplegia demonstrates immediate effectiveness and indicates potential for practical applications in restoring ambulation, improving independence, and reducing health care costs associated with SCI.

Future Perspectives

This paper sets a foundation for future exploration into BCI-controlled prostheses for free overground walking. Emphasis on incorporating additional degrees of freedom, enhancing signal acquisition technologies, and integrating these developments into real-world scenarios is necessary for broad adoption. This BCI system could potentially extend beyond current therapy options, offering gait rehabilitation benefits in incomplete SCI through unique neuroplasticity mechanisms. It invites further testing in clinically diverse populations and long-term studies to validate sustained efficacy and safety.

Overall, the findings signify a pivotal step towards innovative, user-friendly solutions that could transform rehabilitation practices for individuals with SCI, aiming to improve their quality of life through advancements in brain-computer interface and robotics technologies.