Neural correlates of user learning during long-term BCI training for the Cybathlon competition.

BACKGROUND: Brain-computer interfaces (BCIs) are systems capable of translating human brain patterns, measured through electroencephalography (EEG), into commands for an external device. Despite the great advances in machine learning solutions to enhance the performance of BCI decoders, the translational impact of this technology remains elusive. The reliability of BCIs is often unsatisfactory for end-users, limiting their application outside a laboratory environment. METHODS: We present the analysis on the data acquired from an end-user during the preparation for two Cybathlon competitions, where our pilot won the gold medal twice in a row. These data are of particular interest given the mutual learning approach adopted during the longitudinal training phase (8 months), the long training break in between the two events (1 year) and the demanding evaluation scenario. A multifaceted perspective on long-term user learning is proposed: we enriched the information gathered through conventional metrics (e.g., accuracy, application performances) by investigating novel neural correlates of learning in different neural domains. RESULTS: First, we showed that by focusing the training on user learning, the pilot was capable of significantly improving his performance over time even with infrequent decoder re-calibrations. Second, we revealed that the analysis of the within-class modifications of the pilot's neural patterns in the Riemannian domain is more effective in tracking the acquisition and the stabilization of BCI skills, especially after the 1-year break. These results further confirmed the key role of mutual learning in the acquisition of BCI skills, and particularly highlighted the importance of user learning as a key to enhance BCI reliability. CONCLUSION: We firmly believe that our work may open new perspectives and fuel discussions in the BCI field to shift the focus of future research: not only to the machine learning of the decoder, but also in investigating novel training procedures to boost the user learning and the stability of the BCI skills in the long-term. To this end, the analyses and the metrics proposed could be used to monitor the user learning during training and provide a marker guiding the decoder re-calibration to maximize the mutual adaptation of the user to the BCI system.

Human arm weight compensation in rehabilitation robotics: efficacy of three distinct methods.

BACKGROUND: Arm weight compensation with rehabilitation robots for stroke patients has been successfully used to increase the active range of motion and reduce the effects of pathological muscle synergies. However, the differences in structure, performance, and control algorithms among the existing robotic platforms make it hard to effectively assess and compare human arm weight relief. In this paper, we introduce criteria for ideal arm weight compensation, and furthermore, we propose and analyze three distinct arm weight compensation methods (Average, Full, Equilibrium) in the arm rehabilitation exoskeleton 'ARMin'. The effect of the best performing method was validated in chronic stroke subjects to increase the active range of motion in three dimensional space. METHODS: All three methods are based on arm models that are generalizable for use in different robotic devices and allow individualized adaptation to the subject by model parameters. The first method Average uses anthropometric tables to determine subject-specific parameters. The parameters for the second method Full are estimated based on force sensor data in predefined resting poses. The third method Equilibrium estimates parameters by optimizing an equilibrium of force/torque equations in a predefined resting pose. The parameters for all three methods were first determined and optimized for temporal and spatial estimation sensitivity. Then, the three methods were compared in a randomized single-center study with respect to the remaining electromyography (EMG) activity of 31 healthy participants who performed five arm poses covering the full range of motion with the exoskeleton robot. The best method was chosen for feasibility tests with three stroke patients. In detail, the influence of arm weight compensation on the three dimensional workspace was assessed by measuring of the horizontal workspace at three different height levels in stroke patients. RESULTS: All three arm weight compensation methods reduced the mean EMG activity of healthy subjects to at least 49% compared with the no compensation reference. The Equilibrium method outperformed the Average and the Full methods with a highly significant reduction in mean EMG activity by 19% and 28% respectively. However, upon direct comparison, each method has its own individual advantages such as in set-up time, cost, or required technology. The horizontal workspace assessment in poststroke patients with the Equilibrium method revealed potential workspace size-dependence of arm height, while weight compensation helped maximize the workspace as much as possible. CONCLUSION: Different arm weight compensation methods were developed according to initially defined criteria. The methods were then analyzed with respect to their sensitivity and required technology. In general, weight compensation performance improved with the level of technology, but increased cost and calibration efforts. This study reports a systematic way to analyze the efficacy of different weight compensation methods using EMG. Additionally, the feasibility of the best method, Equilibrium, was shown by testing with three stroke patients. In this test, a height dependence of the workspace size also seemed to be present, which further highlights the importance of patient-specific weight compensation, particularly for training at different arm heights. TRIAL REGISTRATION: ClinicalTrials.gov,NCT02720341. Registered 25 March 2016.

Effect of Lower Limb Exoskeleton on the Modulation of Neural Activity and Gait Classification.

Neurorehabilitation with robotic devices requires a paradigm shift to enhance human-robot interaction. The coupling of robot assisted gait training (RAGT) with a brain-machine interface (BMI) represents an important step in this direction but requires better elucidation of the effect of RAGT on the user's neural modulation. Here, we investigated how different exoskeleton walking modes modify brain and muscular activity during exoskeleton assisted gait. We recorded electroencephalographic (EEG) and electromyographic (EMG) activity from ten healthy volunteers walking with an exoskeleton with three modes of user assistance (i.e., transparent, adaptive and full assistance) and during free overground gait. Results identified that exoskeleton walking (irrespective of the exoskeleton mode) induces a stronger modulation of central mid-line mu (8-13 Hz) and low-beta (14-20 Hz) rhythms compared to free overground walking. These modifications are accompanied by a significant re-organization of the EMG patterns in exoskeleton walking. On the other hand, we observed no significant differences in neural activity during exoskeleton walking with the different assistance levels. We subsequently implemented four gait classifiers based on deep neural networks trained on the EEG data during the different walking conditions. Our hypothesis was that exoskeleton modes could impact the creation of a BMI-driven RAGT. We demonstrated that all classifiers achieved an average accuracy of 84.13±3.49% in classifying swing and stance phases on their respective datasets. In addition, we demonstrated that the classifier trained on the transparent mode exoskeleton data can classify gait phases during adaptive and full modes with an accuracy of 78.3±4.8% , while the classifier trained on free overground walking data fails to classify the gait during exoskeleton walking (accuracy of 59.4±11.8% ). These findings provide important insights into the effect of robotic training on neural activity and contribute to the advancement of BMI technology for improving robotic gait rehabilitation therapy.

ROS-Neuro: An Open-Source Platform for Neurorobotics.

The growing interest in neurorobotics has led to a proliferation of heterogeneous neurophysiological-based applications controlling a variety of robotic devices. Although recent years have seen great advances in this technology, the integration between human neural interfaces and robotics is still limited, making evident the necessity of creating a standardized research framework bridging the gap between neuroscience and robotics. This perspective paper presents Robot Operating System (ROS)-Neuro, an open-source framework for neurorobotic applications based on ROS. ROS-Neuro aims to facilitate the software distribution, the repeatability of the experimental results, and support the birth of a new community focused on neuro-driven robotics. In addition, the exploitation of Robot Operating System (ROS) infrastructure guarantees stability, reliability, and robustness, which represent fundamental aspects to enhance the translational impact of this technology. We suggest that ROS-Neuro might be the future development platform for the flourishing of a new generation of neurorobots to promote the rehabilitation, the inclusion, and the independence of people with disabilities in their everyday life.

Cortical correlates in upright dynamic and static balance in the elderly.

Falls are the second most frequent cause of injury in the elderly. Physiological processes associated with aging affect the elderly's ability to respond to unexpected balance perturbations, leading to increased fall risk. Every year, approximately 30% of adults, 65 years and older, experiences at least one fall. Investigating the neurophysiological mechanisms underlying the control of static and dynamic balance in the elderly is an emerging research area. The study aimed to identify cortical and muscular correlates during static and dynamic balance tests in a cohort of young and old healthy adults. We recorded cortical and muscular activity in nine elderly and eight younger healthy participants during an upright stance task in static and dynamic (core board) conditions. To simulate real-life dual-task postural control conditions, the second set of experiments incorporated an oddball visual task. We observed higher electroencephalographic (EEG) delta rhythm over the anterior cortex in the elderly and more diffused fast rhythms (i.e., alpha, beta, gamma) in younger participants during the static balance tests. When adding a visual oddball, the elderly displayed an increase in theta activation over the sensorimotor and occipital cortices. During the dynamic balance tests, the elderly showed the recruitment of sensorimotor areas and increased muscle activity level, suggesting a preferential motor strategy for postural control. This strategy was even more prominent during the oddball task. Younger participants showed reduced cortical and muscular activity compared to the elderly, with the noteworthy difference of a preferential activation of occipital areas that increased during the oddball task. These results support the hypothesis that different strategies are used by the elderly compared to younger adults during postural tasks, particularly when postural and cognitive tasks are combined. The knowledge gained in this study could inform the development of age-specific rehabilitative and assistive interventions.

Age-related differences in visual P300 ERP during dual-task postural balance.

Standing and concurrently performing a cognitive task is a very common situation in everyday life. It is associated with a higher risk of falling in the elderly. Here, we aim at evaluating the differences of the P300 evoked potential elicited by a visual oddball paradigm between healthy younger (< 35 y) and older (> 64 y) adults during a simultaneous postural task. We found that P300 latency increases significantly (p < 0.001) when the elderly are engaged in more challenging postural tasks; younger adults show no effect of balance condition. Our results demonstrate that, even if the elderly have the same accuracy in odd stimuli detection as younger adults do, they require a longer processing time for stimulus discrimination. This finding suggests an increased attentional load which engages additional cerebral reserves.

Experimental Protocol to Assess Neuromuscular Plasticity Induced by an Exoskeleton Training Session.

Exoskeleton gait rehabilitation is an emerging area of research, with potential applications in the elderly and in people with central nervous system lesions, e.g., stroke, traumatic brain/spinal cord injury. However, adaptability of such technologies to the user is still an unmet goal. Despite important technological advances, these robotic systems still lack the fine tuning necessary to adapt to the physiological modification of the user and are not yet capable of a proper human-machine interaction. Interfaces based on physiological signals, e.g., recorded by electroencephalography (EEG) and/or electromyography (EMG), could contribute to solving this technological challenge. This protocol aims to: (1) quantify neuro-muscular plasticity induced by a single training session with a robotic exoskeleton on post-stroke people and on a group of age and sex-matched controls; (2) test the feasibility of predicting lower limb motor trajectory from physiological signals for future use as control signal for the robot. An active exoskeleton that can be set in full mode (i.e., the robot fully replaces and drives the user motion), adaptive mode (i.e., assistance to the user can be tuned according to his/her needs), and free mode (i.e., the robot completely follows the user movements) will be used. Participants will undergo a preparation session, i.e., EMG sensors and EEG cap placement and inertial sensors attachment to measure, respectively, muscular and cortical activity, and motion. They will then be asked to walk in a 15 m corridor: (i) self-paced without the exoskeleton (pre-training session); (ii) wearing the exoskeleton and walking with the three modes of use; (iii) self-paced without the exoskeleton (post-training session). From this dataset, we will: (1) quantitatively estimate short-term neuroplasticity of brain connectivity in chronic stroke survivors after a single session of gait training; (2) compare muscle activation patterns during exoskeleton-gait between stroke survivors and age and sex-matched controls; and (3) perform a feasibility analysis on the use of physiological signals to decode gait intentions.

Deep learning-based BCI for gait decoding from EEG with LSTM recurrent neural network.

OBJECTIVE: Mobile Brain/Body Imaging (MoBI) frameworks allowed the research community to find evidence of cortical involvement at walking initiation and during locomotion. However, the decoding of gait patterns from brain signals remains an open challenge. The aim of this work is to propose and validate a deep learning model to decode gait phases from Electroenchephalography (EEG). APPROACH: A Long-Short Term Memory (LSTM) deep neural network has been trained to deal with time-dependent information within brain signals during locomotion. The EEG signals have been preprocessed by means of Artifacts Subspace Reconstruction (ASR) and Reliable Independent Component Analysis (RELICA) to ensure that classification performance was not affected by movement-related artifacts. MAIN RESULTS: The network was evaluated on the dataset of 11 healthy subjects walking on a treadmill. The proposed decoding approach shows a robust reconstruction (AUC > 90%) of gait patterns (i.e. swing and stance states) of both legs together, or of each leg independently. SIGNIFICANCE: Our results support for the first time the use of a memory-based deep learning classifier to decode walking activity from non-invasive brain recordings. We suggest that this classifier, exploited in real time, can be a more effective input for devices restoring locomotion in impaired people.

Hybrid Human-Machine Interface for Gait Decoding Through Bayesian Fusion of EEG and EMG Classifiers.

Despite the advances in the field of brain computer interfaces (BCI), the use of the sole electroencephalography (EEG) signal to control walking rehabilitation devices is currently not viable in clinical settings, due to its unreliability. Hybrid interfaces (hHMIs) represent a very recent solution to enhance the performance of single-signal approaches. These are classification approaches that combine multiple human-machine interfaces, normally including at least one BCI with other biosignals, such as the electromyography (EMG). However, their use for the decoding of gait activity is still limited. In this work, we propose and evaluate a hybrid human-machine interface (hHMI) to decode walking phases of both legs from the Bayesian fusion of EEG and EMG signals. The proposed hHMI significantly outperforms its single-signal counterparts, by providing high and stable performance even when the reliability of the muscular activity is compromised temporarily (e.g., fatigue) or permanently (e.g., weakness). Indeed, the hybrid approach shows a smooth degradation of classification performance after temporary EMG alteration, with more than 75% of accuracy at 30% of EMG amplitude, with respect to the EMG classifier whose performance decreases below 60% of accuracy. Moreover, the fusion of EEG and EMG information helps keeping a stable recognition rate of each gait phase of more than 80% independently on the permanent level of EMG degradation. From our study and findings from the literature, we suggest that the use of hybrid interfaces may be the key to enhance the usability of technologies restoring or assisting the locomotion on a wider population of patients in clinical applications and outside the laboratory environment.

Feedforward model based arm weight compensation with the rehabilitation robot ARMin.

Highly impaired stroke patients at early stages of recovery are unable to generate enough muscle force to lift the weight of their own arm. Accordingly, task-related training is strongly limited or even impossible. However, as soon as partial or full arm weight support is provided, patients are enabled to perform arm rehabilitation training again throughout an increased workspace. In the literature, the current solutions for providing arm weight support are mostly mechanical. These systems have components that restrict the freedom of movement or entail additional disturbances. A scalable weight compensation for upper and lower arm that is online adjustable as well as generalizable to any robotic system is necessary. In this paper, a model-based feedforward weight compensation of upper and lower arm fulfilling these requirements is introduced. The proposed method is tested with the upper extremity rehabilitation robot ARMin V, but can be applied in any other actuated exoskeleton system. Experimental results were verified using EMG measurements. These results revealed that the proposed weight compensation reduces the effort of the subjects to 26% on average and more importantly throughout the entire workspace of the robot.