Computer-aided prediction of extent of motor recovery following constraint-induced movement therapy in chronic stroke

Online and Cross-User Finger Movement Pattern Recognition by Decoding Neural Drive Information from Surface Electromyogram

Cross-user variability is a well-known challenge that leads to severe performance degradation and impacts the robustness of practical myoelectric control systems. To address this issue, a novel method for myoelectric recognition of finger movement patterns is proposed by incorporating a neural decoding approach with unsupervised domain adaption (UDA) learning. In our method, the neural decoding approach is implemented by extracting microscopic features characterizing individual motor unit (MU) activities obtained from a two-stage online surface electromyogram (SEMG) decomposition. A specific deep learning model is designed and initially trained using labeled data from a set of existing users. The model can update adaptively when recognizing the movement patterns of a new user. The final movement pattern was determined by a fuzzy weighted decision strategy. SEMG signals were collected from the finger extensor muscles of 15 subjects to detect seven dexterous finger-movement patterns. The proposed method achieved a movement pattern recognition accuracy of ([Formula: see text])% over seven movements under cross-user testing scenarios, much higher than that of the conventional methods using global SEMG features. Our study presents a novel robust myoelectric pattern recognition approach at a fine-grained MU level, with wide applications in neural interface and prosthesis control.

A Hardware-Efficient Novelty-Aware Spike Sorting Approach for Brain-Implantable Microsystems

Unsupervised spike sorting, a vital processing step in real-time brain-implantable microsystems, is faced with the prominent challenge of managing nonstationarity in neural signals. In long-term recordings, spike waveforms gradually change and new source neurons are likely to become activated. Adaptive spike sorters combined with on-implant training units effectively process the nonstationary signals at the cost of high hardware resource utilization. On the other hand, static approaches, while being hardware-friendly, are subjected to decreased processing performance in such recordings where the neural signal characteristics gradually change. To strike a balance between the hardware cost and processing performance, this study proposes a hardware-efficient novelty-aware spike sorting approach that is capable of dealing with both variated spike waveforms and spike waveforms generated from new source neurons. Its improved hardware efficiency compared to adaptive ones and capability of dealing with nonstationary signals make it attractive for implantable applications. The proposed novelty-aware spike sorting especially would be a good fit for brain-computer interfaces where long-term, real-time interaction with the brain is required, and the available on-implant hardware resources are limited. Our unsupervised spike sorting benefits from a novelty detection process to deal with neural signal variations. It tracks the spike features so that in case of detecting an unexpected change (novelty detection) both on and off-implant parameters are updated to preserve the performance in new state. To make the proposed approach agile enough to be suitable for brain implants, the on-implant computations are reduced while the computational burden is realized off-implant. The performance of our proposed approach is evaluated using both synthetic and real datasets. The results demonstrate that, in the mean, it is capable of detecting 94.31% of novel spikes (wave-drifted or emerged spikes) with a classification accuracy (CA) of 96.31%. Moreover, an FPGA prototype of the on-implant circuit is implemented and tested. It is shown that in comparison to the OSORT algorithm, a pivotal spike sorting method, our spike sorting provides a higher CA at significantly lower hardware resources. The proposed circuit is also implemented in a 180-nm standard CMOS process, achieving a power consumption of 1.78[Formula: see text][Formula: see text] per channel and a chip area of 0.07[Formula: see text]mm2 per channel.

Self-Supervised Learning for Near-Wild Cognitive Workload Estimation

Feedback on cognitive workload may reduce decision-making mistakes. Machine learning-based models can produce feedback from physiological data such as electroencephalography (EEG) and electrocardiography (ECG). Supervised machine learning requires large training data sets that are (1) relevant and decontaminated and (2) carefully labeled for accurate approximation, a costly and tedious procedure. Commercial over-the-counter devices are low-cost resolutions for the real-time collection of physiological modalities. However, they produce significant artifacts when employed outside of laboratory settings, compromising machine learning accuracies. Additionally, the physiological modalities that most successfully machine-approximate cognitive workload in everyday settings are unknown. To address these challenges, a first-ever hybrid implementation of feature selection and self-supervised machine learning techniques is introduced. This model is employed on data collected outside controlled laboratory settings to (1) identify relevant physiological modalities to machine approximate six levels of cognitive-physical workloads from a seven-modality repository and (2) postulate limited labeling experiments and machine approximate mental-physical workloads using self-supervised learning techniques.

Reinforcement Learning May Demystify the Limited Human Motor Learning Efficacy Due to Visual-Proprioceptive Mismatch

Vision and proprioception have fundamental sensory mismatches in delivering locational information, and such mismatches are critical factors limiting the efficacy of motor learning. However, it is still not clear how and to what extent this mismatch limits motor learning outcomes. To further the understanding of the effect of sensory mismatch on motor learning outcomes, a reinforcement learning algorithm and the simplified biomechanical elbow joint model were employed to mimic the motor learning process in a computational environment. By applying a reinforcement learning algorithm to the motor learning of elbow joint flexion task, simulation results successfully explained how visual-proprioceptive mismatch limits motor learning outcomes in terms of motor control accuracy and task completion speed. The larger the perceived angular offset between the two sensory modalities, the lower the motor control accuracy. Also, the more similar the peak reward amplitude of the two sensory modalities, the lower the motor control accuracy. In addition, simulation results suggest that insufficient exploration rate limits task completion speed, and excessive exploration rate limits motor control accuracy. Such a speed-accuracy trade-off shows that a moderate exploration rate could serve as another important factor in motor learning.

Self-Supervised Learning for Electroencephalography

Decades of research have shown machine learning superiority in discovering highly nonlinear patterns embedded in electroencephalography (EEG) records compared with conventional statistical techniques. However, even the most advanced machine learning techniques require relatively large, labeled EEG repositories. EEG data collection and labeling are costly. Moreover, combining available datasets to achieve a large data volume is usually infeasible due to inconsistent experimental paradigms across trials. Self-supervised learning (SSL) solves these challenges because it enables learning from EEG records across trials with variable experimental paradigms, even when the trials explore different phenomena. It aggregates multiple EEG repositories to increase accuracy, reduce bias, and mitigate overfitting in machine learning training. In addition, SSL could be employed in situations where there is limited labeled training data, and manual labeling is costly. This article: 1) provides a brief introduction to SSL; 2) describes some SSL techniques employed in recent studies, including EEG; 3) proposes current and potential SSL techniques for future investigations in EEG studies; 4) discusses the cons and pros of different SSL techniques; and 5) proposes holistic implementation tips and potential future directions for EEG SSL practices.

Self-Supervised EEG Representation Learning with Contrastive Predictive Coding for Post-Stroke Patients

Stroke patients are prone to fatigue during the EEG acquisition procedure, and experiments have high requirements on cognition and physical limitations of subjects. Therefore, how to learn effective feature representation is very important. Deep learning networks have been widely used in motor imagery (MI) based brain-computer interface (BCI). This paper proposes a contrast predictive coding (CPC) framework based on the modified s-transform (MST) to generate MST-CPC feature representations. MST is used to acquire the temporal-frequency feature to improve the decoding performance for MI task recognition. EEG2Image is used to convert multi-channel one-dimensional EEG into two-dimensional EEG topography. High-level feature representations are generated by CPC which consists of an encoder and autoregressive model. Finally, the effectiveness of generated features is verified by the k-means clustering algorithm. It can be found that our model generates features with high efficiency and a good clustering effect. After classification performance evaluation, the average classification accuracy of MI tasks is 89% based on 40 subjects. The proposed method can obtain effective feature representations and improve the performance of MI-BCI systems. By comparing several self-supervised methods on the public dataset, it can be concluded that the MST-CPC model has the highest average accuracy. This is a breakthrough in the combination of self-supervised learning and image processing of EEG signals. It is helpful to provide effective rehabilitation training for stroke patients to promote motor function recovery.

Enhancing Prediction of Forelimb Movement Trajectory through a Calibrating-Feedback Paradigm Incorporating RAT Primary Motor and Agranular Cortical Ensemble Activity in the Goal-Directed Reaching Task

Complete reaching movements involve target sensing, motor planning, and arm movement execution, and this process requires the integration and communication of various brain regions. Previously, reaching movements have been decoded successfully from the motor cortex (M1) and applied to prosthetic control. However, most studies attempted to decode neural activities from a single brain region, resulting in reduced decoding accuracy during visually guided reaching motions. To enhance the decoding accuracy of visually guided forelimb reaching movements, we propose a parallel computing neural network using both M1 and medial agranular cortex (AGm) neural activities of rats to predict forelimb-reaching movements. The proposed network decodes M1 neural activities into the primary components of the forelimb movement and decodes AGm neural activities into internal feedforward information to calibrate the forelimb movement in a goal-reaching movement. We demonstrate that using AGm neural activity to calibrate M1 predicted forelimb movement can improve decoding performance significantly compared to neural decoders without calibration. We also show that the M1 and AGm neural activities contribute to controlling forelimb movement during goal-reaching movements, and we report an increase in the power of the local field potential (LFP) in beta and gamma bands over AGm in response to a change in the target distance, which may involve sensorimotor transformation and communication between the visual cortex and AGm when preparing for an upcoming reaching movement. The proposed parallel computing neural network with the internal feedback model improves prediction accuracy for goal-reaching movements.

Predicting Outcome in Patients with Brain Injury: Differences between Machine Learning versus Conventional Statistics

Defining reliable tools for early prediction of outcome is the main target for physicians to guide care decisions in patients with brain injury. The application of machine learning (ML) is rapidly increasing in this field of study, but with a poor translation to clinical practice. This is basically dependent on the uncertainty about the advantages of this novel technique with respect to traditional approaches. In this review we address the main differences between ML techniques and traditional statistics (such as logistic regression, LR) applied for predicting outcome in patients with stroke and traumatic brain injury (TBI). Thirteen papers directly addressing the different performance among ML and LR methods were included in this review. Basically, ML algorithms do not outperform traditional regression approaches for outcome prediction in brain injury. Better performance of specific ML algorithms (such as Artificial neural networks) was mainly described in the stroke domain, but the high heterogeneity in features extracted from low-dimensional clinical data reduces the enthusiasm for applying this powerful method in clinical practice. To better capture and predict the dynamic changes in patients with brain injury during intensive care courses ML algorithms should be extended to high-dimensional data extracted from neuroimaging (structural and fMRI), EEG and genetics.

Cross-validation of predictive models for functional recovery after post-stroke rehabilitation

Background

Rehabilitation treatments and services are essential for the recovery of post-stroke patients’ functions; however, the increasing number of available therapies and the lack of consensus among outcome measures compromises the possibility to determine an appropriate level of evidence. Machine learning techniques for prognostic applications offer accurate and interpretable predictions, supporting the clinical decision for personalised treatment. The aim of this study is to develop and cross-validate predictive models for the functional prognosis of patients, highlighting the contributions of each predictor.

Methods

A dataset of 278 post-stroke patients was used for the prediction of the class transition, obtained from the modified Barthel Index. Four classification algorithms were cross-validated and compared. On the best performing model on the validation set, an analysis of predictors contribution was conducted.

Results

The Random Forest obtained the best overall results on the accuracy (76.2%), balanced accuracy (74.3%), sensitivity (0.80), and specificity (0.68). The combination of all the classification results on the test set, by weighted voting, reached 80.2% accuracy. The predictors analysis applied on the Support Vector Machine, showed that a good trunk control and communication level, and the absence of bedsores retain the major contribution in the prediction of a good functional outcome.

Conclusions

Despite a more comprehensive assessment of the patients is needed, this work paves the way for the implementation of solutions for clinical decision support in the rehabilitation of post-stroke patients. Indeed, offering good prognostic accuracies for class transition and patient-wise view of the predictors contributions, it might help in a personalised optimisation of the patients’ rehabilitation path.

Machine learning methods for functional recovery prediction and prognosis in post-stroke rehabilitation: a systematic review

BACKGROUND

Rehabilitation medicine is facing a new development phase thanks to a recent wave of rigorous clinical trials aimed at improving the scientific evidence of protocols. This phenomenon, combined with new trends in personalised medical therapies, is expected to change clinical practice dramatically. The emerging field of Rehabilomics is only possible if methodologies are based on biomedical data collection and analysis. In this framework, the objective of this work is to develop a systematic review of machine learning algorithms as solutions to predict motor functional recovery of post-stroke patients after treatment.

METHODS

We conducted a comprehensive search of five electronic databases using the Patient, Intervention, Comparison and Outcome (PICO) format. We extracted health conditions, population characteristics, outcome assessed, the method for feature extraction and selection, the algorithm used, and the validation approach. The methodological quality of included studies was assessed using the prediction model risk of bias assessment tool (PROBAST). A qualitative description of the characteristics of the included studies as well as a narrative data synthesis was performed.

RESULTS

A total of 19 primary studies were included. The predictors most frequently used belonged to the areas of demographic characteristics and stroke assessment through clinical examination. Regarding the methods, linear and logistic regressions were the most frequently used and cross-validation was the preferred validation approach.

CONCLUSIONS

We identified several methodological limitations: small sample sizes, a limited number of external validation approaches, and high heterogeneity among input and output variables. Although these elements prevented a quantitative comparison across models, we defined the most frequently used models given a specific outcome, providing useful indications for the application of more complex machine learning algorithms in rehabilitation medicine.

Baseline Predictors of Response to Repetitive Task Practice in Chronic Stroke

BACKGROUND

Repetitive task practice reduces mean upper extremity motor impairment in populations of patients with chronic stroke, but individual response is highly variable. A method to predict meaningful reduction in impairment in response to training based on biomarkers and other data collected prior to an intervention is needed to establish realistic rehabilitation goals and to effectively allocate resources.

OBJECTIVES

To identify prognostic factors and better understand the biological substrate for reductions in arm impairment in response to repetitive task practice among patients with chronic (≥6 months) post-stroke hemiparesis.

METHODS

The intervention is a form of repetitive task practice using a combination of robot-assisted therapy and functional arm use in real-world tasks. Baseline measures include the Fugl-Meyer Assessment, Wolf Motor Function Test, Action Research Arm Test, Stroke Impact Scale, questionnaires on pain and expectancy, MRI, transcranial magnetic stimulation, kinematics, accelerometry, and genomic testing.

RESULTS

Mean increase in FM-UE was 4.6 ± 1.0 SE, median 2.5. Approximately one-third of participants had a clinically meaningful response to the intervention, defined as an increase in FM ≥ 5. The selected logistic regression model had a receiver operating curve with AUC = .988 (Std Error = .011, 95% Wald confidence limits: .967-1) showed little evidence of overfitting. Six variables that predicted response represented impairment, functional, and genomic measures.

CONCLUSION

A simple weighted sum of 6 baseline factors can accurately predict clinically meaningful impairment reduction after outpatient intensive practice intervention in chronic stroke. Reduction of impairment may be a critical first step to functional improvement. Further validation and generalization of this model will increase its utility in clinical decision-making.

Brain Network Organization Following Post-Stroke Neurorehabilitation

Brain network analysis can offer useful information to guide the rehabilitation of post-stroke patients. We applied functional network connection models based on multiplex-multilayer network analysis (MMN) to explore functional network connectivity changes induced by robot-aided gait training (RAGT) using the Ekso, a wearable exoskeleton, and compared it to conventional overground gait training (COGT) in chronic stroke patients. We extracted the coreness of individual nodes at multiple locations in the brain from EEG recordings obtained before and after gait training in a resting state. We found that patients provided with RAGT achieved a greater motor function recovery than those receiving COGT. This difference in clinical outcome was paralleled by greater changes in connectivity patterns among different brain areas central to motor programming and execution, as well as a recruitment of other areas beyond the sensorimotor cortices and at multiple frequency ranges, contemporarily. The magnitude of these changes correlated with motor function recovery chances. Our data suggest that the use of RAGT as an add-on treatment to COGT may provide post-stroke patients with a greater modification of the functional brain network impairment following a stroke. This might have potential clinical implications if confirmed in large clinical trials.

A Vector Quantization-Based Spike Compression Approach Dedicated to Multichannel Neural Recording Microsystems

Implantable high-density multichannel neural recording microsystems provide simultaneous recording of brain activities. Wireless transmission of the entire recorded data causes high bandwidth usage, which is not tolerable for implantable applications. As a result, a hardware-friendly compression module is required to reduce the amount of data before it is transmitted. This paper presents a novel compression approach that utilizes a spike extractor and a vector quantization (VQ)-based spike compressor. In this approach, extracted spikes are vector quantized using an unsupervised learning process providing a high spike compression ratio (CR) of 10-80. A combination of extracting and compressing neural spikes results in a significant data reduction as well as preserving the spike waveshapes. The compression performance of the proposed approach was evaluated under variant conditions. We also developed new architectures such that the hardware blocks of our approach can be implemented more efficiently. The compression module was implemented in a 180-nm standard CMOS process achieving a SNDR of 14.49[Formula: see text]dB and a classification accuracy (CA) of 99.62% at a CR of 20, while consuming 4[Formula: see text][Formula: see text]W power and 0.16[Formula: see text]mm² chip area per channel.

Detection of Movement Intention in EEG-Based Brain-Computer Interfaces Using Fourier-Based Synchrosqueezing Transform

Patients with motor impairments need caregivers' help to initiate the operation of brain-computer interfaces (BCI). This study aims to identify and characterize movement intention using multichannel electroencephalography (EEG) signals as a means to initiate BCI systems without extra accessories/methodologies. We propose to discriminate the resting and motor imagery (MI) states with high accuracy using Fourier-based synchrosqueezing transform (FSST) as a feature extractor. FSST has been investigated and compared with other popular approaches in 28 healthy subjects for a total of 6657 trials. The accuracy and f-measure values were obtained as 99.8% and 0.99, respectively, when FSST was used as the feature extractor and singular value decomposition (SVD) as the feature selection method and support vector machines as the classifier. Moreover, this study investigated the use of data that contain certain amount of noise without any preprocessing in addition to the clean counterparts. Furthermore, the statistical analysis of EEG channels with the best discrimination (of resting and MI states) characteristics demonstrated that F4-Fz-C3-Cz-C4-Pz channels and several statistical features had statistical significance levels, [Formula: see text], less than 0.05. This study showed that the preparation of the movement can be detected in real-time employing FSST-SVD combination and several channels with minimal pre-processing effort.

Do somatosensory deficits predict efficacy of neurorehabilitation using neuromuscular electrical stimulation for moderate to severe motor paralysis of the upper limb in chronic stroke?

Background:

Various neurorehabilitation programs have been developed to promote recovery from motor impairment of upper extremities. However, the response of patients with chronic-phase stroke varies greatly. Prediction of the treatment response is important to provide appropriate and efficient rehabilitation. This study aimed to clarify whether clinical assessments, such as motor impairments and somatosensory deficits, before treatment could predict the treatment response in neurorehabilitation.

Methods:

The data from patients who underwent neurorehabilitation using closed-loop electromyography (EMG)-controlled neuromuscular electrical stimulation were retrospectively analyzed. A total of 66 patients with chronic-phase stroke with moderate to severe paralysis were included. The changes from baseline in the Fugl-Meyer Assessment–Upper Extremity (FMA-UE) and the Motor Activity Log-14 (MAL-14) of amount of use (AOU) and quality of movement (QOM) were used to assess treatment response, and multivariate logistic regression analysis was performed using the extracted candidate predictors, such as baseline clinical assessments, to identify predictors of FMA-UE and MAL-14 improvement.

Results:

FMA-UE and MAL-14 scores improved significantly after the intervention (FMA-UE p < 0.01, AOU p < 0.01, QOM p < 0.01). On multivariate logistic regression analysis, tactile sensory (p = 0.043) and hand function (p = 0.030) were both identified as significant predictors of FMA-UE improvement, tactile sensory (p = 0.047) was a significant predictor of AOU improvement, and hand function (p = 0.026) was a significant predictor of QOM improvement. The regression equations explained 71.2% of the variance in the improvement of FMA-UE, 69.7% of AOU, and 69.7% of QOM.

Conclusion:

Both motor and tactile sensory impairments predict improvement in motor function, tactile sensory impairment predicts improvement in the amount of paralytic hand use, and motor impairment predicts improvement in the quality of paralytic hand use following neurorehabilitation treatment in patients with moderate to severe paralysis in chronic-phase stroke. These findings may help select the appropriate treatment for patients with more severe paralysis and to maximize the treatment effect.

Feature Selection Combining Filter and Wrapper Methods for Motor-Imagery Based Brain-Computer Interfaces

Motor imagery (MI) based brain-computer interfaces help patients with movement disorders to regain the ability to control external devices. Common spatial pattern (CSP) is a popular algorithm for feature extraction in decoding MI tasks. However, due to noise and nonstationarity in electroencephalography (EEG), it is not optimal to combine the corresponding features obtained from the traditional CSP algorithm. In this paper, we designed a novel CSP feature selection framework that combines the filter method and the wrapper method. We first evaluated the importance of every CSP feature by the infinite latent feature selection method. Meanwhile, we calculated Wasserstein distance between feature distributions of the same feature under different tasks. Then, we redefined the importance of every CSP feature based on two indicators mentioned above, which eliminates half of CSP features to create a new CSP feature subspace according to the new importance indicator. At last, we designed the improved binary gravitational search algorithm (IBGSA) by rebuilding its transfer function and applied IBGSA on the new CSP feature subspace to find the optimal feature set. To validate the proposed method, we conducted experiments on three public BCI datasets and performed a numerical analysis of the proposed algorithm for MI classification. The accuracies were comparable to those reported in related studies and the presented model outperformed other methods in literature on the same underlying data.

Optimization of Model Training Based on Iterative Minimum Covariance Determinant In Motor-Imagery BCI

The common spatial patterns (CSP) algorithm is one of the most frequently used and effective spatial filtering methods for extracting relevant features for use in motor imagery brain-computer interfaces (MI-BCIs). However, the inherent defect of the traditional CSP algorithm is that it is highly sensitive to potential outliers, which adversely affects its performance in practical applications. In this work, we propose a novel feature optimization and outlier detection method for the CSP algorithm. Specifically, we use the minimum covariance determinant (MCD) to detect and remove outliers in the dataset, then we use the Fisher score to evaluate and select features. In addition, in order to prevent the emergence of new outliers, we propose an iterative minimum covariance determinant (IMCD) algorithm. We evaluate our proposed algorithm in terms of iteration times, classification accuracy and feature distribution using two BCI competition datasets. The experimental results show that the average classification performance of our proposed method is 12% and 22.9% higher than that of the traditional CSP method in two datasets ([Formula: see text]), and our proposed method obtains better performance in comparison with other competing methods. The results show that our method improves the performance of MI-BCI systems.

Detection of the Intention of Direction Changes During Gait Through EEG Signals

Brain-Computer Interfaces (BCIs) are becoming an important technological tool for the rehabilitation process of patients with locomotor problems, due to their ability to recover the connection between brain and limbs by promoting neural plasticity. They can be used as assistive devices to improve the mobility of handicapped people. For this reason, current BCIs have to be improved to allow an accurate and natural use of external devices. This work proposes a novel methodology for the detection of the intention to change the direction during gait based on event-related desynchronization (ERD). Frequency and temporal features of the electroencephalographic (EEG) signals are characterized. Then, a selection of the most influential features and electrodes to differentiate the direction change intention from the walking is carried out. Best results are obtained when combining frequency and temporal features with an average accuracy of [Formula: see text]%, which are promising to be applied for future BCIs.

Concurrent Prediction of Finger Forces Based on Source Separation and Classification of Neuron Discharge Information

A reliable neural-machine interface is essential for humans to intuitively interact with advanced robotic hands in an unconstrained environment. Existing neural decoding approaches utilize either discrete hand gesture-based pattern recognition or continuous force decoding with one finger at a time. We developed a neural decoding technique that allowed continuous and concurrent prediction of forces of different fingers based on spinal motoneuron firing information. High-density skin-surface electromyogram (HD-EMG) signals of finger extensor muscle were recorded, while human participants produced isometric flexion forces in a dexterous manner (i.e. produced varying forces using either a single finger or multiple fingers concurrently). Motoneuron firing information was extracted from the EMG signals using a blind source separation technique, and each identified neuron was further classified to be associated with a given finger. The forces of individual fingers were then predicted concurrently by utilizing the corresponding motoneuron pool firing frequency of individual fingers. Compared with conventional approaches, our technique led to better prediction performances, i.e. a higher correlation ([Formula: see text] versus [Formula: see text]), a lower prediction error ([Formula: see text]% MVC versus [Formula: see text]% MVC), and a higher accuracy in finger state (rest/active) prediction ([Formula: see text]% versus [Formula: see text]%). Our decoding method demonstrated the possibility of classifying motoneurons for different fingers, which significantly alleviated the cross-talk issue of EMG recordings from neighboring hand muscles, and allowed the decoding of finger forces individually and concurrently. The outcomes offered a robust neural-machine interface that could allow users to intuitively control robotic hands in a dexterous manner.

The Influence of Visual Attention on The Performance of A Novel Tactile P300 Brain-Computer Interface with Cheeks-Stim Paradigm

Tactile P300 brain-computer interface (BCI) generally has a worse accuracy and information transfer rate (ITR) than the visual-based BCI. It may be due to the fact that human beings have a relatively poor tactile perception. This study investigated the influence of visual attention on the performance of a tactile P300 BCI. We designed our paradigms based on a novel cheeks-stim paradigm which attached the stimulators on the subject's cheeks. Two paradigms were designed as follows: a paradigm with no visual attention and another paradigm with visual attention to the target position. Eleven subjects were invited to perform the two paradigms. We also recorded and analyzed the eyeball movement data during the paradigm with visual attention to explore whether the eyeball movement would have an effect on the BCI classification. The average online accuracy was 89.09% for the paradigm with visual attention, which was significantly higher than that of the paradigm with no visual attention (70.45%). Significant difference in ITR was also found between the two paradigms ([Formula: see text]). The results demonstrated that visual attention was an effective method to improve the performance of tactile P300 BCI. Our findings suggested that it may be feasible to complete an efficient tactile BCI system by adding visual attention.

Electroencephalography-Derived Prognosis of Functional Recovery in Acute Stroke Through Machine Learning Approaches

Stroke, if not lethal, is a primary cause of disability. Early assessment of markers of recovery can allow personalized interventions; however, it is difficult to deliver indexes in the acute phase able to predict recovery. In this perspective, evaluation of electrical brain activity may provide useful information. A machine learning approach was explored here to predict post-stroke recovery relying on multi-channel electroencephalographic (EEG) recordings of few minutes performed at rest. A data-driven model, based on partial least square (PLS) regression, was trained on 19-channel EEG recordings performed within 10 days after mono-hemispheric stroke in 101 patients. The band-wise (delta: 1-4[Formula: see text]Hz, theta: 4-7[Formula: see text]Hz, alpha: 8-14[Formula: see text]Hz and beta: 15-30[Formula: see text]Hz) EEG effective powers were used as features to predict the recovery at 6 months (based on clinical status evaluated through the NIH Stroke Scale, NIHSS) in an optimized and cross-validated framework. In order to exploit the multimodal contribution to prognosis, the EEG-based prediction of recovery was combined with NIHSS scores in the acute phase and both were fed to a nonlinear support vector regressor (SVR). The prediction performance of EEG was at least as good as that of the acute clinical status scores. A posteriori evaluation of the features exploited by the analysis highlighted a lower delta and higher alpha activity in patients showing a positive outcome, independently of the affected hemisphere. The multimodal approach showed better prediction capabilities compared to the acute NIHSS scores alone ([Formula: see text] versus [Formula: see text], AUC = 0.80 versus AUC = 0.70, [Formula: see text]). The multimodal and multivariate model can be used in acute phase to infer recovery relying on standard EEG recordings of few minutes performed at rest together with clinical assessment, to be exploited for early and personalized therapies. The easiness of performing EEG may allow such an approach to become a standard-of-care and, thanks to the increasing number of labeled samples, further improving the model predictive power.

Nonspecific Visuospatial Imagery as a Novel Mental Task for Online EEG-Based BCI Control

Brain-computer interfaces (BCIs) can provide a means of communication to individuals with severe motor disorders, such as those presenting as locked-in. Many BCI paradigms rely on motor neural pathways, which are often impaired in these individuals. However, recent findings suggest that visuospatial function may remain intact. This study aimed to determine whether visuospatial imagery, a previously unexplored task, could be used to signify intent in an online electroencephalography (EEG)-based BCI. Eighteen typically developed participants imagined checkerboard arrow stimuli in four quadrants of the visual field in 5-s trials, while signals were collected using 16 dry electrodes over the visual cortex. In online blocks, participants received graded visual feedback based on their performance. An initial BCI pipeline (visuospatial imagery classifier I) attained a mean accuracy of [Formula: see text]% classifying rest against visuospatial imagery in online trials. This BCI pipeline was further improved using restriction to alpha band features (visuospatial imagery classifier II), resulting in a mean pseudo-online accuracy of [Formula: see text]%. Accuracies exceeded the threshold for practical BCIs in 12 participants. This study supports the use of visuospatial imagery as a real-time, binary EEG-BCI control paradigm.

Predicting Improved Daily Use of the More Affected Arm Poststroke Following Constraint-Induced Movement Therapy

BACKGROUND

Constraint-induced movement therapy (CI therapy) produces, on average, large and clinically meaningful improvements in the daily use of a more affected upper extremity in individuals with hemiparesis. However, individual responses vary widely.

OBJECTIVE

The study objective was to investigate the extent to which individual characteristics before treatment predict improved use of the more affected arm following CI therapy.

DESIGN

This study was a retrospective analysis of 47 people who had chronic (> 6 months) mild to moderate upper extremity hemiparesis and were consecutively enrolled in 2 CI therapy randomized controlled trials.

METHODS

An enhanced probabilistic neural network model predicted whether individuals showed a low, medium, or high response to CI therapy, as measured with the Motor Activity Log, on the basis of the following baseline assessments: Wolf Motor Function Test, Semmes-Weinstein Monofilament Test of touch threshold, Motor Activity Log, and Montreal Cognitive Assessment. Then, a neural dynamic classification algorithm was applied to improve prognostic accuracy using the most accurate combination obtained in the previous step.

RESULTS

Motor ability and tactile sense predicted improvement in arm use for daily activities following intensive upper extremity rehabilitation with an accuracy of nearly 100%. Complex patterns of interaction among these predictors were observed.

LIMITATIONS

The fact that this study was a retrospective analysis with a moderate sample size was a limitation.

CONCLUSIONS

Advanced machine learning/classification algorithms produce more accurate personalized predictions of rehabilitation outcomes than commonly used general linear models.

Improved quality of life following constraint-induced movement therapy is associated with gains in arm use, but not motor improvement

BACKGROUND

Constraint-induced movement therapy (CI therapy) is one of few treatments for upper extremity (UE) hemiparesis that has been shown to result in motor recovery and improved quality of life in chronic stroke. However, the extent to which treatment-induced improvements in motor function versus daily use of the more affected arm independently contribute to improved quality of life remains largely unexplored.

OBJECTIVE

The objective of this study is to identify whether motor function or daily use of a hemiparetic arm has a greater influence on quality of life after CI therapy.

METHODS

Two cohorts of participants with chronic stroke received either in-person CI therapy (n = 29) or video-game home-based CI therapy (n = 16). The two cohorts were combined and the motor-related outcomes (Wolf Motor Function Test, Action Research Arm Test, Motor Activity Log [MAL]) and quality of life (Stroke-Specific Quality of Life) were jointly modeled to assess the associations between outcomes.

RESULTS

The only outcome associated with improved quality of life was the MAL. Improvements in quality of life were not restricted to motor domains, but generalized to psychosocial domains as well.

CONCLUSIONS

Results suggest that improved arm use during everyday activities is integral to maximizing quality of life gains during motor rehabilitation for chronic post-stroke UE hemiparesis. In contrast, gains in motor function were not associated with increases in quality of life. These findings further support the need to implement techniques into clinical practice that promote arm use during daily life if improving quality of life is a main goal of treatment. ClinicalTrials.gov Registration Numbers: NCT01725919 and NCT03005457.

Comparing Recalibration Strategies for Electroencephalography-Based Decoders of Movement Intention in Neurological Patients with Motor Disability

Motor rehabilitation based on the association of electroencephalographic (EEG) activity and proprioceptive feedback has been demonstrated as a feasible therapy for patients with paralysis. To promote long-lasting motor recovery, these interventions have to be carried out across several weeks or even months. The success of these therapies partly relies on the performance of the system decoding movement intentions, which normally has to be recalibrated to deal with the nonstationarities of the cortical activity. Minimizing the recalibration times is important to reduce the setup preparation and maximize the effective therapy time. To date, a systematic analysis of the effect of recalibration strategies in EEG-driven interfaces for motor rehabilitation has not yet been performed. Data from patients with stroke (4 patients, 8 sessions) and spinal cord injury (SCI) (4 patients, 5 sessions) undergoing two different paradigms (self-paced and cue-guided, respectively) are used to study the performance of the EEG-based classification of motor intentions. Four calibration schemes are compared, considering different combinations of training datasets from previous and/or the validated session. The results show significant differences in classifier performances in terms of the true and false positives (TPs) and (FPs). Combining training data from previous sessions with data from the validation session provides the best compromise between the amount of data needed for calibration and the classifier performance. With this scheme, the average true (false) positive rates obtained are 85.3% (17.3%) and 72.9% (30.3%) for the self-paced and the cue-guided protocols, respectively. These results suggest that the use of optimal recalibration schemes for EEG-based classifiers of motor intentions leads to enhanced performances of these technologies, while not requiring long calibration phases prior to starting the intervention.

Gross motor ability predicts response to upper extremity rehabilitation in chronic stroke

The majority of rehabilitation research focuses on the comparative effectiveness of different interventions in groups of patients, while much less is currently known regarding individual factors that predict response to rehabilitation. In a recent article, the authors presented a prognostic model to identify the sensorimotor characteristics predictive of the extent of motor recovery after Constraint-Induced Movement (CI) therapy amongst individuals with chronic mild-to-moderate motor deficit using the enhanced probabilistic neural network (EPNN). This follow-up paper examines which participant characteristics are robust predictors of rehabilitation response irrespective of the training modality. To accomplish this, EPNN was first applied to predict treatment response amongst individuals who received a virtual-reality gaming intervention (utilizing the same enrollment criteria as the prior study). The combinations of predictors that yield high predictive validity for both therapies, using their respective datasets, were then identified. High predictive classification accuracy was achieved for both the gaming (94.7%) and combined datasets (94.5%). Though CI therapy employed primarily fine-motor training tasks and the gaming intervention emphasized gross-motor practice, larger improvements in gross motor function were observed within both datasets. Poorer gross motor ability at pre-treatment predicted better rehabilitation response in both the gaming and combined datasets. The conclusion of this research is that for individuals with chronic mild-to-moderate upper extremity hemiparesis, residual deficits in gross motor function are highly responsive to motor restorative interventions, irrespective of the modality of training.