Brain-Computer Interface Group Research Articles

Rehabilitation with brain-computer interface and upper limb motor function in ischemic stroke: A randomized controlled trial

Upper limb motor dysfunction is a major problem in the rehabilitation of patients with stroke. Brain-computer interface (BCI) is a kind of communication system that converts the "ideas" in the brain into instructions and has been used in stroke rehabilitation. This study aimed to investigate the efficacy and safety of BCI in rehabilitation training on upper limb motor function among patients with ischemic stroke. This was an investigator-initiated, multicenter, randomized, open-label, blank-controlled clinical trial with blinded outcome assessment conducted at 17 centers in China. Patients were assigned in a 1:1 ratio to the BCI group or the control group based on traditional rehabilitation training. The primary efficacy outcome is the difference in improvement of the Fugl-Meyer Assessment upper extremity (FMA-UE) score between two groups at month 1 after randomization. The safety outcomes were any adverse events within 3months. A total of 296 patients with ischemic stroke were enrolled and randomly allocated to the BCI group (n= 150) and the control group (n= 146). The primary efficacy outcomes of FMA-UE score change from baseline to 1month were 13.17 (95% confidence interval [CI], 11.56-14.79) in the BCI group and 9.83 (95% CI, 8.19-11.47) in the control group (mean difference between groups was 3.35; 95% CI, 1.05-5.65; p= 0.0045). Adverse events occurred in 33 patients (22.00%) in the BCI group and in 31 patients (21.23%) in the control group. BCI rehabilitation training can further improve upper limb motor function based on traditional rehabilitation training in patients with ischemic stroke. This study was registered at ClinicalTrials.gov: NCT04387474. This work was supported by the National Key R&D Program of China (2018YFC1312903), the National Key Research and Development Program of China (2022YFC3600600), the Training Fund for Open Projects at Clinical Institutes and Departments of Capital Medical University (CCMU2022ZKYXZ009), the Beijing Natural Science Foundation Haidian original innovation joint fund (L222123), the Fund for Young Talents of Beijing Medical Management Center (QML20230505), and the high-level public health talents (xuekegugan-02-47).

Towards Implantable Brain-Computer Interface for Communication in Locked-In Syndrome patients

Abstract Locked-in Syndrome (LIS) severely restricts the communication abilities of individuals due to extensive paralysis. The Intracranial Neuro Telemetry to Restore communication (INTRECOM) project aims to aid patients in overcoming these limitations by developing a fully implantable brain computer interface (BCI) system based on state-of-the-art technology holding great promise in revolutionizing the lives of LIS patients. In this project, the Graz BCI group, with its expertise in understanding brain dynamics associated with movement, focuses on the algorithmic development of advanced decoders that enable the user to execute specific commands by simply attempting corresponding movements. Our preliminary findings using electrocorticography (ECoG) data obtained from one individual with LIS that underwent implantation of a BCI communication system demonstrate the applicability of a ‘brain switch’ function that detects brain signals associated with attempted movements. This switch can then be used to translate the intention of the user into a click/select function on a screen.

Augmenting mental imagery for robotic surgery using neurofeedback: results of a randomized controlled trial.

Mental imagery (MI) can enhance surgical skills. Research has shown that through brain-computer interface (BCI), it is possible to provide feedback on MI strength. We hypothesized that adding BCI to MI training would enhance robotic skill acquisition compared with controls. Surgical novices were recruited. At baseline, participants completed the Mental Imagery Questionnaire (MIQ) and the Vandenburg Mental Rotation Test (MRT). Students also performed several tasks on a robotic simulator. Participants were stratified based on MIQ and robotic skill and randomized into three groups: controls, MI, and MI and BCI training. All participants completed five 2-h training sessions. One hour was devoted to practicing robotic skill on the simulator. Additionally, controls completed crosswords for one hour, the MI group completed MI training and crosswords for one hour, and the MI + BCI group completed MI training and MI-related BCI training. Following training, participants completed the same baseline assessments. A Kruskal-Wallis test was used to determine differences between groups. Mann-Whitney U tests were performed to determine specific differences between groups. Twenty-seven undergraduates participated. There were post-test differences on the MRT and knot tying task. Sub-analyses revealed that the MI + BCI group significantly outperformed the other groups on knot tying. There were no appreciable differences between the control and MI groups on any measures. Augmenting MI training with BCI led to significantly enhanced MI and robotic skill acquisition than traditional MI or robotic training methods. To optimize surgical skill acquisition in robotic and other surgical skills curricula, educators should consider utilizing MI with BCI training.

Evidence of neuroplasticity with brain-computer interface in a randomized trial for post-stroke rehabilitation: a graph-theoretic study of subnetwork analysis.

Brain-computer interface (BCI) has been widely used for functional recovery after stroke. Understanding the brain mechanisms following BCI intervention to optimize BCI strategies is crucial for the benefit of stroke patients. Forty-six patients with upper limb motor dysfunction after stroke were recruited and randomly divided into the control group or the BCI group. The primary outcome was measured by the assessment of Fugl-Meyer Assessment of Upper Extremity (FMA-UE). Meanwhile, we performed resting-state functional magnetic resonance imaging (rs-fMRI) in all patients, followed by independent component analysis (ICA) to identify functionally connected brain networks. Finally, we assessed the topological efficiency of both groups using graph-theoretic analysis in these brain subnetworks. The FMA-UE score of the BCI group was significantly higher than that of the control group after treatment (p = 0.035). From the network topology analysis, we first identified seven subnetworks from the rs-fMRI data. In the following analysis of subnetwork properties, small-world properties including γ (p = 0.035) and σ (p = 0.031) within the visual network (VN) decreased in the BCI group. For the analysis of the dorsal attention network (DAN), significant differences were found in assortativity (p = 0.045) between the groups. Additionally, the improvement in FMA-UE was positively correlated with the assortativity of the dorsal attention network (R = 0.498, p = 0.011). Brain-computer interface can promote the recovery of upper limbs after stroke by regulating VN and DAN. The correlation trend of weak intensity proves that functional recovery in stroke patients is likely to be related to the brain's visuospatial processing ability, which can be used to optimize BCI strategies. The trial is registered in the Chinese Clinical Trial Registry, number ChiCTR2000034848. Registered 21 July 2020.

Sensorimotor Rhythm-Brain Computer Interface With Audio-Cue, Motor Observation and Multisensory Feedback for Upper-Limb Stroke Rehabilitation: A Controlled Study.

Several studies have shown the positive clinical effect of brain computer interface (BCI) training for stroke rehabilitation. This study investigated the efficacy of the sensorimotor rhythm (SMR)-based BCI with audio-cue, motor observation and multisensory feedback for post-stroke rehabilitation. Furthermore, we discussed the interaction between training intensity and training duration in BCI training. Twenty-four stroke patients with severe upper limb (UL) motor deficits were randomly assigned to two groups: 2-week SMR-BCI training combined with conventional treatment (BCI Group, BG, n = 12) and 2-week conventional treatment without SMR-BCI intervention (Control Group, CG, n = 12). Motor function was measured using clinical measurement scales, including Fugl-Meyer Assessment-Upper Extremities (FMA-UE; primary outcome measure), Wolf Motor Functional Test (WMFT), and Modified Barthel Index (MBI), at baseline (Week 0), post-intervention (Week 2), and follow-up week (Week 4). EEG data from patients allocated to the BG was recorded at Week 0 and Week 2 and quantified by mu suppression means event-related desynchronization (ERD) in mu rhythm (8–12 Hz). All functional assessment scores (FMA-UE, WMFT, and MBI) significantly improved at Week 2 for both groups (p < 0.05). The BG had significantly higher FMA-UE and WMFT improvement at Week 4 compared to the CG. The mu suppression of bilateral hemisphere both had a positive trend with the motor function scores at Week 2. This study proposes a new effective SMR-BCI system and demonstrates that the SMR-BCI training with audio-cue, motor observation and multisensory feedback, together with conventional therapy may promote long-lasting UL motor improvement.Clinical Trial Registration: [http://www.chictr.org.cn], identifier [ChiCTR2000041119].

Effects of Training with a Brain-Computer Interface-Controlled Robot on Rehabilitation Outcome in Patients with Subacute Stroke: A Randomized Controlled Trial.

IntroductionStroke is always associated with a difficult functional recovery process. A brain–computer interface (BCI) is a technology which provides a direct connection between the human brain and external devices. The primary aim of this study was to determine whether training with a BCI-controlled robot can improve functions in patients with subacute stroke.MethodsSubacute stroke patients aged 32–68 years with a course of 2 weeks to 3 months were randomly assigned to the BCI group or to the sham group for a 4-week course. The primary outcome measures were Loewenstein Occupational Therapy Cognitive Assessment (LOCTA) and Fugl-Meyer Assessment for Lower Extremity (FMA-LE). Secondary outcome measures included Fugl-Meyer Assessment for Balance (FMA-B), Functional Ambulation Category (FAC), Modified Barthel Index (MBI), serum brain-derived neurotrophic factor (BDNF) levels and motor-evoked potential (MEP).ResultsA total of 28 patients completed the study. Both groups showed a significant increase in mean LOCTA (sham: P < 0.001, Cohen’s d = − 2.972; BCI: P < 0.001, Cohen’s d = − 4.266) and FMA-LE (sham: P < 0.001, Cohen’s d = − 3.178; BCI: P < 0.001, Cohen’s d = − 3.063) scores. The LOCTA scores in the BCI group were 14.89% higher than in the sham group (P = 0.049, Cohen’s d = − 0.580). There were no significant differences between the two groups in terms of FMA-B (P = 0.363, Cohen’s d = − 0.252), FAC (P = 0.363), or MBI (P = 0.493, Cohen’s d = − 0.188) scores. The serum levels of BDNF were significantly higher within the BCI group (P < 0.001, Cohen’s d = − 1.167), and the MEP latency decreased by 3.75% and 4.71% in the sham and BCI groups, respectively.ConclusionTraining with a BCI-controlled robot combined with traditional physiotherapy promotes cognitive function recovery, and enhances motor functions of the lower extremity in patients with subacute stroke. These patients also showed increased secretion of BDNF.Trial RegistrationChinese clinical trial registry: ChiCTR-INR-17012874.

Motor Imagery-Based Brain-Computer Interface Combined with Multimodal Feedback to Promote Upper Limb Motor Function after Stroke: A Preliminary Study.

Background Recently, the brain-computer interface (BCI) has seen rapid development, which may promote the recovery of motor function in chronic stroke patients. Methods Twelve stroke patients with severe upper limb and hand motor impairment were enrolled and randomly assigned into two groups: motor imagery (MI)-based BCI training with multimodal feedback (BCI group, n = 7) and classical motor imagery training (control group, n = 5). Motor function and electrophysiology were evaluated before and after the intervention. The Fugl-Meyer assessment-upper extremity (FMA-UE) is the primary outcome measure. Secondary outcome measures include an increase in wrist active extension or surface electromyography (the amplitude and cocontraction of extensor carpi radialis during movement), the action research arm test (ARAT), the motor status scale (MSS), and Barthel index (BI). Time-frequency analysis and power spectral analysis were used to reflect the electroencephalogram (EEG) change before and after the intervention. Results Compared with the baseline, the FMA-UE score increased significantly in the BCI group (p = 0.006). MSS scores improved significantly in both groups, while ARAT did not improve significantly. In addition, before the intervention, all patients could not actively extend their wrists or just had muscle contractions. After the intervention, four patients regained the ability to extend their paretic wrists (two in each group). The amplitude and area under the curve of extensor carpi radialis improved to some extent, but there was no statistical significance between the groups. Conclusion MI-based BCI combined with sensory and visual feedback might improve severe upper limb and hand impairment in chronic stroke patients, showing the potential for application in rehabilitation medicine.

Longitudinal Electroencephalography Analysis in Subacute Stroke Patients During Intervention of Brain-Computer Interface With Exoskeleton Feedback.

BackgroundBrain–computer interface (BCI) has been regarded as a newly developing intervention in promoting motor recovery in stroke survivors. Several studies have been performed in chronic stroke to explore its clinical and subclinical efficacy. However, evidence in subacute stroke was poor, and the longitudinal sensorimotor rhythm changes in subacute stroke after BCI with exoskeleton feedback were still unclear.Materials and MethodsFourteen stroke patients in subacute stage were recruited and randomly allocated to BCI group (n = 7) and the control group (n = 7). Brain–computer interface training with exoskeleton feedback was applied in the BCI group three times a week for 4 weeks. The Fugl–Meyer Assessment of Upper Extremity (FMA-UE) scale was used to assess motor function improvement. Brain–computer interface performance was calculated across the 12-time interventions. Sensorimotor rhythm changes were explored by event-related desynchronization (ERD) changes and topographies.ResultsAfter 1 month BCI intervention, both the BCI group (p = 0.032) and the control group (p = 0.048) improved in FMA-UE scores. The BCI group (12.77%) showed larger percentage of improvement than the control group (7.14%), and more patients obtained good motor recovery in the BCI group (57.1%) than did the control group (28.6%). Patients with good recovery showed relatively higher online BCI performance, which were greater than 70%. And they showed a continuous improvement in offline BCI performance and obtained a highest value in the last six sessions of interventions during BCI training. However, patients with poor recovery reached a platform in the first six sessions of interventions and did not improve any more or even showed a decrease. In sensorimotor rhythm, patients with good recovery showed an enhanced ERD along with time change. Topographies showed that the ipsilesional hemisphere presented stronger activations after BCI intervention.ConclusionBrain–computer interface training with exoskeleton feedback was feasible in subacute stroke patients. Brain–computer interface performance can be an index to evaluate the efficacy of BCI intervention. Patients who presented increasingly stronger or continuously strong activations (ERD) may obtain better motor recovery.

Brain Functional Networks Study of Subacute Stroke Patients With Upper Limb Dysfunction After Comprehensive Rehabilitation Including BCI Training.

Brain computer interface (BCI)-based training is promising for the treatment of stroke patients with upper limb (UL) paralysis. However, most stroke patients receive comprehensive treatment that not only includes BCI, but also routine training. The purpose of this study was to investigate the topological alterations in brain functional networks following comprehensive treatment, including BCI training, in the subacute stage of stroke. Twenty-five hospitalized subacute stroke patients with moderate to severe UL paralysis were assigned to one of two groups: 4-week comprehensive treatment, including routine and BCI training (BCI group, BG, n = 14) and 4-week routine training without BCI support (control group, CG, n = 11). Functional UL assessments were performed before and after training, including, Fugl-Meyer Assessment-UL (FMA-UL), Action Research Arm Test (ARAT), and Wolf Motor Function Test (WMFT). Neuroimaging assessment of functional connectivity (FC) in the BG was performed by resting state functional magnetic resonance imaging. After training, as compared with baseline, all clinical assessments (FMA-UL, ARAT, and WMFT) improved significantly (p < 0.05) in both groups. Meanwhile, better functional improvements were observed in FMA-UL (p < 0.05), ARAT (p < 0.05), and WMFT (p < 0.05) in the BG. Meanwhile, FC of the BG increased across the whole brain, including the temporal, parietal, and occipital lobes and subcortical regions. More importantly, increased inter-hemispheric FC between the somatosensory association cortex and putamen was strongly positively associated with UL motor function after training. Our findings demonstrate that comprehensive rehabilitation, including BCI training, can enhance UL motor function better than routine training for subacute stroke patients. The reorganization of brain functional networks topology in subacute stroke patients allows for increased coordination between the multi-sensory and motor-related cortex and the extrapyramidal system. Future long-term, longitudinal, controlled neuroimaging studies are needed to assess the effectiveness of BCI training as an approach to promote brain plasticity during the subacute stage of stroke.

A new method for P300 detection in deep belief networks: Nesterov momentum and drop based learning rate

Detecting P300 signal plays a vital role in Brain-Computer Interface (BCI) systems. In recent years, deep neural networks have been vastly utilized for P300 detection. However, by increasing the number of dimensions, the ratio of saddle points to local minima increases exponentially which hampers the performance of these networks for P300 detection. In this paper, a new method is introduced which improves the training procedure of Deep Belief Networks (DBN) by using Nesterov momentum. In another version of the proposed algorithm, the drop-based learning rate is also utilized to improve its performance. These strategies lead to escape saddle points in large scales of dimensions which causes the considerable improvement in P300 detection. Performance of the proposed algorithm is evaluated on a dataset of EPFL BCI group and compared with some other state-of-the-art methods. The results demonstrate that the best recognition rate is obtained by using the proposed method which is equal to 93.47%. The obtained results also show approximately 4.83% superiority in the accuracy of proposed algorithm against its alternatives.

Combined rTMS and virtual reality brain–computer interface training for motor recovery after stroke

Objective. Combining repetitive transcranial magnetic stimulation (rTMS) with brain–computer interface (BCI) training can address motor impairment after stroke by down-regulating exaggerated inhibition from the contralesional hemisphere and encouraging ipsilesional activation. The objective was to evaluate the efficacy of combined rTMS + BCI, compared to sham rTMS + BCI, on motor recovery after stroke in subjects with lasting motor paresis. Approach. Three stroke subjects approximately one year post-stroke participated in three weeks of combined rTMS (real or sham) and BCI, followed by three weeks of BCI alone. Behavioral and electrophysiological differences were evaluated at baseline, after three weeks, and after six weeks of treatment. Main results. Motor improvements were observed in both real rTMS + BCI and sham groups, but only the former showed significant alterations in inter-hemispheric inhibition in the desired direction and increased relative ipsilesional cortical activation from fMRI. In addition, significant improvements in BCI performance over time and adequate control of the virtual reality BCI paradigm were observed only in the former group. Significance. When combined, the results highlight the feasibility and efficacy of combined rTMS + BCI for motor recovery, demonstrated by increased ipsilesional motor activity and improvements in behavioral function for the real rTMS + BCI condition in particular. Our findings also demonstrate the utility of BCI training alone, as shown by behavioral improvements for the sham rTMS + BCI condition. This study is the first to evaluate combined rTMS and BCI training for motor rehabilitation and provides a foundation for continued work to evaluate the potential of both rTMS and virtual reality BCI training for motor recovery after stroke.

A New Method for Detecting P300 Signals by Using Deep Learning: Hyperparameter Tuning in High-Dimensional Space by Minimizing Nonconvex Error Function.

Background:P300 signal detection is an essential problem in many fields of Brain-Computer Interface (BCI) systems. Although deep neural networks have almost ubiquitously used in P300 detection, in such networks, increasing the number of dimensions leads to growth ratio of saddle points to local minimums. This phenomenon results in slow convergence in deep neural network. Hyperparameter tuning is one of the approaches in deep learning, which leads to fast convergence because of its ability to find better local minimums. In this paper, a new adaptive hyperparameter tuning method is proposed to improve training of Convolutional Neural Networks (CNNs).Methods:The aim of this paper is to introduce a novel method to improve the performance of deep neural networks in P300 signal detection. To reach this purpose, the proposed method transferred the non-convex error function of CNN) into Lagranging paradigm, then, Newton and dual active set techniques are utilized for hyperparameter tuning in order to minimize error of objective function in high dimensional space of CNN.Results:The proposed method was implemented on MATLAB 2017 package and its performance was evaluated on dataset of Ecole Polytechnique Fédérale de Lausanne (EPFL) BCI group. The obtained results depicted that the proposed method detected the P300 signals with 95.34% classification accuracy in parallel with high True Positive Rate (i.e., 92.9%) and low False Positive Rate (i.e., 0.77%).Conclusions:To estimate the performance of the proposed method, the achieved results were compared with the results of Naive Hyperparameter (NHP) tuning method. The comparisons depicted the superiority of the proposed method against its alternative, in such way that the best accuracy by using the proposed method was 6.44%, better than the accuracy of the alternative method.

Investigation of a wavelet-based neural network learning algorithm applied to P300 based brain-computer interface

The paper presented herein proposes an algorithm that aims at improving the classification accuracy of Brain-Computer Interface (BCI) speller. In this work, feed-forward neural network with back propagation learning is used for classification purposes. Testing of the proposed algorithm was performed through the utilization of two datasets, namely; Berlin BCI Competition III and EPFL BCI groups. Results, for the first dataset, indicated that the use of 64 electrodes with 30 hidden layers grants an accuracy of 94.9 %, while an average accuracy of 95.8% (range: 92%-100%) was obtained for the second dataset when using a 32 electrode configuration with 20 hidden layers. The obtained accuracy levels, in this study, are higher when compared with other recent classification approaches.

Post-stroke Rehabilitation Training with a Motor-Imagery-Based Brain-Computer Interface (BCI)-Controlled Hand Exoskeleton: A Randomized Controlled Multicenter Trial.

Repeated use of brain-computer interfaces (BCIs) providing contingent sensory feedback of brain activity was recently proposed as a rehabilitation approach to restore motor function after stroke or spinal cord lesions. However, there are only a few clinical studies that investigate feasibility and effectiveness of such an approach. Here we report on a placebo-controlled, multicenter clinical trial that investigated whether stroke survivors with severe upper limb (UL) paralysis benefit from 10 BCI training sessions each lasting up to 40 min. A total of 74 patients participated: median time since stroke is 8 months, 25 and 75% quartiles [3.0; 13.0]; median severity of UL paralysis is 4.5 points [0.0; 30.0] as measured by the Action Research Arm Test, ARAT, and 19.5 points [11.0; 40.0] as measured by the Fugl-Meyer Motor Assessment, FMMA. Patients in the BCI group (n = 55) performed motor imagery of opening their affected hand. Motor imagery-related brain electroencephalographic activity was translated into contingent hand exoskeleton-driven opening movements of the affected hand. In a control group (n = 19), hand exoskeleton-driven opening movements of the affected hand were independent of brain electroencephalographic activity. Evaluation of the UL clinical assessments indicated that both groups improved, but only the BCI group showed an improvement in the ARAT's grasp score from 0 [0.0; 14.0] to 3.0 [0.0; 15.0] points (p < 0.01) and pinch scores from 0.0 [0.0; 7.0] to 1.0 [0.0; 12.0] points (p < 0.01). Upon training completion, 21.8% and 36.4% of the patients in the BCI group improved their ARAT and FMMA scores respectively. The corresponding numbers for the control group were 5.1% (ARAT) and 15.8% (FMMA). These results suggests that adding BCI control to exoskeleton-assisted physical therapy can improve post-stroke rehabilitation outcomes. Both maximum and mean values of the percentage of successfully decoded imagery-related EEG activity, were higher than chance level. A correlation between the classification accuracy and the improvement in the upper extremity function was found. An improvement of motor function was found for patients with different duration, severity and location of the stroke.

Brain–computer interface: The first experience of clinical use in Russia

Motor imagery can stimulate the same neuroplastic mechanisms of the brain as their actual execution. The motor imagery can be controlled via the brain–computer interface (BCI), which transforms the EEG signals of the brain appearing during the motor imagery into commands for the external device. The results of the two-stage study of the application of a non-invasive BCI for the rehabilitation of patients with marked hemiparesis resulted from a local brain injury. We have shown that the learning to manage the BCI does not depend on the duration of disease, localization of the damaged site, and the severity of neurological deficit. The results of the first stage of the study carried out in a group of 36 patients showed that the rehabilitation therapy was more effective in the group that was trained to manage the BCI (the ARAT score improved from 1 [0; 2] to 5 [0; 16], p = 0.012 in the BCI group; no significant improvement was detected in the control group). In the second phase of the study, 19 patients participated in the testing of a BCI–exoskeleton system. Rehabilitation based on this technology led to an improvement of the motor function of an arm from 2 [0; 37] to 4 [1; 45.5], p = 0.005, according to the ARAT scale, and from 72 [63; 110] to 79 [68; 115], p = 0.005, according to the Fugl-Meyer scale.

Brain-Computer Interface Users Speak Up: The Virtual Users' Forum at the 2013 International Brain-Computer Interface Meeting

More than 300 researchers gathered at the 2013 International Brain-Computer Interface (BCI) Meeting to discuss current practice and future goals for BCI research and development. The authors organized the Virtual Users' Forum at the meeting to provide the BCI community with feedback from users. We report on the Virtual Users' Forum, including initial results from ongoing research being conducted by 2 BCI groups. Online surveys and in-person interviews were used to solicit feedback from people with disabilities who are expert and novice BCI users. For the Virtual Users' Forum, their responses were organized into 4 major themes: current (non-BCI) communication methods, experiences with BCI research, challenges of current BCIs, and future BCI developments. Two authors with severe disabilities gave presentations during the Virtual Users' Forum, and their comments are integrated with the other results. While participants' hopes for BCIs of the future remain high, their comments about available systems mirror those made by consumers about conventional assistive technology. They reflect concerns about reliability (eg, typing accuracy/speed), utility (eg, applications and the desire for real-time interactions), ease of use (eg, portability and system setup), and support (eg, technical support and caregiver training). People with disabilities, as target users of BCI systems, can provide valuable feedback and input on the development of BCI as an assistive technology. To this end, participatory action research should be considered as a valuable methodology for future BCI research.

9. Brain network modulation following motor imagery BCI-assisted training after stroke

To evaluate the influence of Motor Imagery (MI) training assisted via Brain Computer Interface (BCI) on brain network organization in subacute stroke patients. We analyzed EEG-derived brain networks estimated before and after two training strategies (with and without BCI support); correlations between connectivity indices and clinical improvement were performed. Twenty-eight subacute stroke patients were enrolled and assigned to two groups: 14 patients underwent a one-month motor imagery (MI) training supported by a sensorimotor–based BCI (BCI group) while 14 underwent a similar MI training without BCI support (CTRL group). Before and after training we recorded EEG from 61 positions during 5 min of rest. Effective connectivity was computed by means of Partial Directed Coherence. Paired sample t -tests and Pearson’s Correlation were employed to analyze data (significance was defined by p p R = 0.568, p = 0.034). Overall findings indicate that MI training supported via BCI induces a reinforcement of interhemispheric connections related to sensorimotor rhythms; brain connectivity is a promising neurophysiological marker for BCI training efficacy in stroke rehabilitation. This work was partially supported by the European ICT Programme Project FP7-224631 and by the project “Brain Computer Interface-Driven Rehabilitation After Stroke: An Add-On Intervention For Hand Motor Recovery” (RF-2010-2319611) founded by the Italian Ministry of Healthcare.

Different classification techniques considering brain computer interface applications

In this work the application of different machine learning techniques for classification of mental tasks from electroencephalograph (EEG) signals is investigated. The main application for this research is the improvement of brain computer interface (BCI) systems. For this purpose, Bayesian graphical network, neural network, Bayesian quadratic, Fisher linear and hidden Markov model classifiers are applied to two known EEG datasets in the BCI field. The Bayesian network classifier is used for the first time in this work for classification of EEG signals. The Bayesian network appeared to have a significant accuracy and more consistent classification compared to the other four methods. In addition to classical correct classification accuracy criteria, the mutual information is also used to compare the classification results with other BCI groups.