Scoring upper-extremity motor function from EEG with artificial neural networks: a preliminary study

AI Applications in Adult Stroke Recovery and Rehabilitation: A Scoping Review Using AI

Stroke is a leading cause of long-term disability worldwide. With the advancements in sensor technologies and data availability, artificial intelligence (AI) holds the promise of improving the amount, quality and efficiency of care and enhancing the precision of stroke rehabilitation. We aimed to identify and characterize the existing research on AI applications in stroke recovery and rehabilitation of adults, including categories of application and progression of technologies over time. Data were collected from peer-reviewed articles across various electronic databases up to January 2024. Insights were extracted using AI-enhanced multi-method, data-driven techniques, including clustering of themes and topics. This scoping review summarizes outcomes from 704 studies. Four common themes (impairment, assisted intervention, prediction and imaging, and neuroscience) were identified, in which time-linked patterns emerged. The impairment theme revealed a focus on motor function, gait and mobility, while the assisted intervention theme included applications of robotic and brain-computer interface (BCI) techniques. AI applications progressed over time, starting from conceptualization and then expanding to a broader range of techniques in supervised learning, artificial neural networks (ANN), natural language processing (NLP) and more. Applications focused on upper limb rehabilitation were reviewed in more detail, with machine learning (ML), deep learning techniques and sensors such as inertial measurement units (IMU) used for upper limb and functional movement analysis. AI applications have potential to facilitate tailored therapeutic delivery, thereby contributing to the optimization of rehabilitation outcomes and promoting sustained recovery from rehabilitation to real-world settings.

A novel scoring approach for the Wolf Motor Function Test in stroke survivors using motion-sensing technology and machine learning: A preliminary study

BACKGROUND AND OBJECTIVE

Human-administered clinical scales, such as the Functional Ability Scale of the Wolf Motor Function Test (WMFT-FAS), are widely utilized to evaluate upper-limb motor function in stroke survivors. However, these scales are generally subjective and labor-intensive. To end this, we proposed a novel scoring approach for the motor function assessment.

METHODS

The proposed novel scoring approach mainly contained one Microsoft Kinect v2, one customized motion tracking system, and one customized intelligent scoring system. Specifically, the Kinect v2 was used to capture stroke survivors' functional movements, the motion tracking system was developed for recording the gathered movement data, and the intelligent scoring system (kernel: feed-forward neural network, FFNN) was developed to evaluate movement quality and provide corresponding WMFT-FAS scores. Several methods have been applied to enhance the approach's usability, such as singular spectrum analysis and multi-ReliefF method.

RESULTS

Sixteen stroke survivors and ten healthy subjects were recruited for validation. Inspiring results of the proposed approach were achieved when compared with the clinical scores provided by a physiotherapist: 0.924 ± 0.027 for accuracy, 0.875 ± 0.063 for F1-score, 0.915 ± 0.051 for sensitivity, 0.969 ± 0.013 for specificity, 0.952 ± 0.038 for AUC, 0.098 ± 0.037 for mean absolute error, and 0.214 ± 0.078 for root mean squared error.

CONCLUSIONS

The results indicate that the proposed novel scoring approach can provide objective and accurate assessment scores, which can help physiotherapists make individualized treatment decisions.

A Method for Estimating Longitudinal Change in Motor Skill from Individualized Functional-Connectivity Measures

Pragmatic, objective, and accurate motor assessment tools could facilitate more frequent appraisal of longitudinal change in motor function and subsequent development of personalized therapeutic strategies. Brain functional connectivity (FC) has shown promise as an objective neurophysiological measure for this purpose. The involvement of different brain networks, along with differences across subjects due to age or existing capabilities, motivates an individualized approach towards the evaluation of FC. We advocate the use of EEG-based resting-state FC (rsFC) measures to address the pragmatic requirements. Pertaining to appraisal of accuracy, we suggest using the acquisition of motor skill by healthy individuals that could be quantified at small incremental change. Computer-based tracing tasks are a good candidate in this regard when using spatial error in tracing as an objective measure of skill. This work investigates the application of an individualized method that utilizes Partial Least Squares analysis to estimate the longitudinal change in tracing error from changes in rsFC. Longitudinal data from participants yielded an average accuracy of 98% (standard deviation of 1.2%) in estimating tracing error. The results show potential for an accurate individualized motor assessment tool that reduces the dependence on the expertise and availability of trained examiners, thereby facilitating more frequent appraisal of function and development of personalized training programs.

Use of artificial intelligence as an instrument of evaluation after stroke: a scoping review based on international classification of functioning, disability and health concept

INTRODUCTION

To understand the current practices in stroke evaluation, the main clinical decision support system and artificial intelligence (AI) technologies need to be understood to assist the therapist in obtaining better insights about impairments and level of activity and participation in persons with stroke during rehabilitation.

METHODS

This scoping review maps the use of AI for the functional evaluation of persons with stroke; the context involves any setting of rehabilitation. Data were extracted from CENTRAL, MEDLINE, EMBASE, LILACS, CINAHL, PEDRO Web of Science, IEEE Xplore, AAAI Publications, ACM Digital Library, MathSciNet, and arXiv up to January 2021. The data obtained from the literature review were summarized in a single dataset in which each reference paper was considered as an instance, and the study characteristics were considered as attributes. The attributes used for the multiple correspondence analysis were publication year, study type, sample size, age, stroke phase, stroke type, functional status, AI type, and AI function.

RESULTS

Forty-four studies were included. The analysis showed that spasticity analysis based on ML techniques was used for the cases of stroke with moderate functional status. The techniques of deep learning and pressure sensors were used for gait analysis. Machine learning techniques and algorithms were used for upper limb and reaching analyses. The inertial measurement unit technique was applied in studies where the functional status was between mild and severe. The fuzzy logic technique was used for activity classifiers.

CONCLUSION

The prevailing research themes demonstrated the growing utility of AI algorithms for stroke evaluation.

CNN-Based Prognosis of BCI Rehabilitation Using EEG From First Session BCI Training

Stroke is a world-leading disease for causing disability. Brain-computer interaction (BCI) training has been proved to be a promising method in facilitating motor recovery. However, due to differences in each patient's neural-clinical profile, the potential of recovery for different patients can vary significantly by conducting BCI training, which remains a major problem in clinical rehabilitation practice. To address this issue, the objective of this study is to prognosticate the outcome of BCI training using motor state electroencephalographic (EEG) collected during the first session of BCI tasks, with the aim of prescribing BCI training accordingly. A Convolution Neural Network (CNN) based prognosis model was developed to predict the outcome of 11 stroke patients' recovery following a 2-week rehabilitation training with BCI. In our study, functional connectivity and power spectrum have been evaluated and applied as the inputs of CNN to regress patients' recovery rate. A saliency map was used to identify the correlation between EEG channels with the recovery outcome. The performance of our model was assessed using the leave-one-out cross-validation. Overall, the proposed model predicted patients' recovery with R² 0.98 and MSE 0.89. According to the saliency map, the highest functional connectivity occurred in Fp2/Fpz-AF8, Fp2/F4/F8-P3, P1/PO7-PO5 and AF3-AF4. Our results demonstrated that deep learning method has the potential to predict the recovery rate of BCI training, which contributes to guiding individualized prescription in the early stage of clinical rehabilitation.

Quantitative Assessment of Motor Function by an End-Effector Upper Limb Rehabilitation Robot Based on Admittance Control

Various rehabilitation robots have been developed to assist the movement training of the upper limbs of stroke patients, among which some have been used to evaluate the motor recovery. However, how to understand the recovery of motor function from the quantitative assessment following robot-assisted rehabilitation training is still not clear. The objective of this study is to propose a quantitative assessment method of motor function based on the force and trajectory characteristics during robotic training to reflect motor functional recovery. To assist stroke patients who are not able to move voluntarily, an assistive training mode was developed for the robot-assisted rehabilitation system based on admittance control. Then, to validate the relationship between characteristic information and functional recovery, a clinical experiment was conducted, in which nine stroke patients and nine healthy subjects were recruited. The results showed a significant difference in movement range and movement smoothness during trajectory tracking tasks between stroke patients and healthy subjects. The two parameters above have a correlation with the Fugl-Meyer Assessment for Upper Extremity (FMU) of the involved patients. The multiple linear regression analysis showed FMU was positively correlated with parameters (R2=0.91,p<0.005). This finding indicated that the above-mentioned method can achieve quantitative assessment of motor function for stroke patients during robot-assisted rehabilitation training, which can contribute to promoting rehabilitation robots in clinical practice.

Portable neuromodulation induces neuroplasticity to re-activate motor function recovery from brain injury: a high-density MEG case study

BACKGROUND

In a recent high-profile case study, we used functional magnetic resonance imaging (fMRI) to monitor improvements in motor function related to neuroplasticity following rehabilitation for severe traumatic brain injury (TBI). The findings demonstrated that motor function improvements can occur years beyond current established limits. The current study extends the functional imaging investigation to characterize neuromodulation effects on neuroplasticity to further push the limits.

METHODS

Canadian Soldier Captain (retired) Trevor Greene (TG) survived a severe open-TBI when attacked with an axe during a 2006 combat tour in Afghanistan. TG has since continued intensive daily rehabilitation to recover motor function, experiencing an extended plateau using conventional physical therapy. To overcome this plateau, we paired translingual neurostimulation (TLNS) with the continuing rehabilitation program.

RESULTS

Combining TLNS with rehabilitation resulted in demonstrable clinical improvements along with corresponding changes in movement evoked electro-encephalography (EEG) activity. High-density magneto-encephalography (MEG) characterized cortical activation changes in corresponding beta frequency range (27 Hz). MEG activation changes corresponded with reduced interhemispheric inhibition in the post-central gyri regions together with increased right superior/middle frontal activation suggesting large scale network level changes.

CONCLUSIONS

The findings provide valuable insight into the potential importance of non-invasive neuromodulation to enhance neuroplasticity mechanisms for recovery beyond the perceived limits of rehabilitation.

The Feasibility of Longitudinal Upper Extremity Motor Function Assessment Using EEG

Motor function assessment is crucial in quantifying motor recovery following stroke. In the rehabilitation field, motor function is usually assessed using questionnaire-based assessments, which are not completely objective and require prior training for the examiners. Some research groups have reported that electroencephalography (EEG) data have the potential to be a good indicator of motor function. However, those motor function scores based on EEG data were not evaluated in a longitudinal paradigm. The ability of the motor function scores from EEG data to track the motor function changes in long-term clinical applications is still unclear. In order to investigate the feasibility of using EEG to score motor function in a longitudinal paradigm, a convolutional neural network (CNN) EEG model and a residual neural network (ResNet) EEG model were previously generated to translate EEG data into motor function scores. To validate applications in monitoring rehabilitation following stroke, the pre-established models were evaluated using an initial small sample of individuals in an active 14-week rehabilitation program. Longitudinal performances of CNN and ResNet were evaluated through comparison with standard Fugl-Meyer Assessment (FMA) scores of upper extremity collected in the assessment sessions. The results showed good accuracy and robustness with both proposed networks (average difference: 1.22 points for CNN, 1.03 points for ResNet), providing preliminary evidence for the proposed method in objective evaluation of motor function of upper extremity in long-term clinical applications.

Estimating Fugl-Meyer Upper Extremity Motor Score From Functional-Connectivity Measures

Fugl-Meyer assessment is an accepted method of evaluating motor function for people with stroke. A challenge associated with this assessment is the availability of trained examiners to carry out the evaluation. Neurophysiological biomarkers show promise in addressing the above impediment. Our study investigated the potential of using resting state electroencephalographic (EEG) functional connectivity measures as biomarkers for estimating Fugl-Meyer upper extremity motor score (FMU) in people with chronic stroke. Resting state EEG was recorded from 10 individuals with stroke. Functional connectivity was evaluated through five different processing algorithms and quantified in terms of maximum-coherence between EEG electrodes at 15 frequencies from 1 to 45 Hz. We applied a multi-variate Partial Least Squares (PLS) Correlation analysis to simultaneously identify specific connectivity channels (EEG electrode pairings) and frequencies that robustly correlated with FMU. We then applied PLS-Regression to the identified channels and frequencies to generate a set of coefficients for estimating the FMU. Participants were randomly assigned to a training-set of eight and a test-set of two. Cross-validation with leave-one-out approach on the training-set, using Phase-Lag-Index processing algorithm, resulted in an R² of 0.97 and a least-square linear fit slope of 1 for predicted versus actual FMU, with a root-mean-square error of 1.9 on FMU scale. Application of regression coefficients to the connectivity measures from the test-set resulted in predicted FMU of 47 and 38 versus actual scores of 46 and 39, respectively. Our results demonstrated that the evaluation of neural correlates of FMU shows promise in addressing the challenges associated with the availability of trained examiners to carry out the assessments.