Explainable Deep-Learning Prediction for Brain-Computer Interfaces Supported Lower Extremity Motor Gains Based on Multistate Fusion.

Predicting the potential for recovery of motor function in stroke patients who undergo specific rehabilitation treatments is an important and major challenge. Recently, electroencephalography (EEG) has shown potential in helping to determine the relationship between cortical neural activity and motor recovery. EEG recorded in different states could more accurately predict motor recovery than single-state recordings. Here, we design a multi-state (combining eyes closed, EC, and eyes open, EO) fusion neural network for predicting the motor recovery of patients with stroke after EEG-brain-computer-interface (BCI) rehabilitation training and use an explainable deep learning method to identify the most important features of EEG power spectral density and functional connectivity contributing to prediction. The prediction accuracy of the multi-states fusion network was 82%, significantly improved compared with a single-state model. The neural network explanation result demonstrated the important region and frequency oscillation bands. Specifically, in those two states, power spectral density and functional connectivity were shown as the regions and bands related to motor recovery in frontal, central, and occipital. Moreover, the motor recovery relation in bands, the power spectrum density shows the bands at delta and alpha bands. The functional connectivity shows the delta, theta, and alpha bands in the EC state; delta, theta, and beta mid at the EO state are related to motor recovery. Multi-state fusion neural networks, which combine multiple states of EEG signals into a single network, can increase the accuracy of predicting motor recovery after BCI training, and reveal the underlying mechanisms of motor recovery in brain activity.

Motor-Respiratory Coupling Improves Endurance Performance during Rhythmic Isometric Handgrip Exercise.

PURPOSE: This study aimed to evaluate whether motor-respiratory coupling exists in rhythmic isometric handgrip exercises and its effect on endurance performance. In addition, the mechanism underlying observed effects was to be investigated if higher motor-respiratory coupling rate could enhance endurance performance. METHODS: Eleven subjects completed three rhythmic isometric handgrip trials to task failure in a randomized manner. After one pretraining session to determine personal grip frequency, one trial was performed without respiration requirement (CON), and two trials were performed with inspiration-motor coupling (IMC) or expiration-motor coupling. Changes in maximal voluntary contraction (MVC) and EMG were used to measure neuromuscular fatigue. Force data during test were used to assess exercise intensity. Another 10 subjects completed electrical stimulation-induced finger flexion and extension during normal inspiration, normal expiration, fast inspiration, fast expiration, and breath holding. Force changes of different breathing conditions were compared. RESULTS: Normalized exercise time to exhaustion was significantly longer in IMC (1.27 ± 0.23) compared with expiration-motor coupling (0.82 ± 0.18) and CON (0.91 ± 0.18, P < 0.001). ΔMVC, grip frequency, force, and EMG indices were not different among conditions (all P > 0.05). Electrical stimulation-induced finger extensor force was significant higher during fast inspiration (1.11 ± 0.09) than normal respiration (1.00 ± 0.05) and fast expiration (0.94 ± 0.08, P < 0.05). CONCLUSIONS: IMC is an effective way to improve endurance performance of rhythmic handgrip exercise. This is likely due to a reduction in the energy consumption of motion control, as evidenced by similar peripheral fatigue in different conditions and modulation of corticospinal excitability by respiration.

Multiscale Canonical Coherence for Functional Corticomuscular Coupling Analysis.

Functional corticomuscular coupling (FCMC) probes multi-level information communication in the sensorimotor system. The canonical Coherence (caCOH) method has been leveraged to measure the FCMC between two multivariate signals within the single scale. In this paper, we propose the concept of multiscale canonical Coherence (MS-caCOH) to disentangle complex multi-layer information and extract coupling features in multivariate spaces from multiple scales. Then, we verified the reliability and effectiveness of MS-caCOH on two types of data sets, i.e., a synthetic multivariate data set and a real-world multivariate data set. Our simulation results showed that compared with caCOH, MS-caCOH enhanced coupling detection and achieved lower pattern recovery errors at multiple frequency scales. Further analysis on experimental data demonstrated that the proposed MS-caCOH method could also capture detailed multiscale spatial-frequency characteristics. This study leverages the multiscale analysis framework and multivariate method to give a new insight into corticomuscular coupling analysis.

Lesion-specific cortical activation following sensory stimulation in patients with subacute stroke.

BACKGROUND: Sensory stimulation can play a fundamental role in the activation of the primary sensorimotor cortex (S1-M1), which can promote motor learning and M1 plasticity in stroke patients. However, studies have focused mainly on investigating the influence of brain lesion profiles on the activation patterns of S1-M1 during motor tasks instead of sensory tasks. Therefore, the objective of this study is to explore the lesion-specific activation patterns due to different brain lesion profiles and types during focal vibration (FV). METHODS: In total 52 subacute stroke patients were recruited in this clinical experiment, including patients with basal ganglia hemorrhage/ischemia, brainstem ischemia, other subcortical ischemia, cortical ischemia, and mixed cortical-subcortical ischemia. Electroencephalograms (EEG) were recorded following a resting state lasting for 4 min and three sessions of FV. FV was applied over the muscle belly of the affected limb's biceps for 3 min each session. Beta motor-related EEG power desynchronization overlying S1-M1 was used to indicate the activation of S1-M1, while the laterality coefficient (LC) of the activation of S1-M1 was used to assess the interhemispheric asymmetry of brain activation. RESULTS: (1) Regarding brain lesion profiles, FV could lead to the significant activation of bilateral S1-M1 in patients with basal ganglia ischemia and other subcortical ischemia. The activation of ipsilesional S1-M1 in patients with brainstem ischemia was higher than that in patients with cortical ischemia. No activation of S1-M1 was observed in patients with lesions involving cortical regions. (2) Regarding brain lesion types, FV could induce the activation of bilateral S1-M1 in patients with basal ganglia hemorrhage, which was significantly higher than that in patients with basal ganglia ischemia. Additionally, LC showed no significant correlation with the modified Barthel index (MBI) in all patients, but a positive correlation with MBI in patients with basal ganglia lesions. CONCLUSIONS: These results reveal that sensory stimulation can induce lesion-specific activation patterns of S1-M1. This indicates FV could be applied in a personalized manner based on the lesion-specific activation of S1-M1 in stroke patients with different lesion profiles and types. Our study may contribute to a better understanding of the underlying mechanisms of cortical reorganization.

A Transferable Deep Learning Prognosis Model for Predicting Stroke Patients' Recovery in Different Rehabilitation Trainings.

Since the underlying mechanisms of neurorehabilitation are not fully understood, the prognosis of stroke recovery faces significant difficulties. Recovery outcomes can vary when undergoing different treatments; however, few models have been developed to predict patient outcomes toward multiple treatments. In this study, we aimed to investigate the potential of predicting a treatment's outcome using a deep learning prognosis model developed for another treatment. A total of 15 stroke survivors were recruited in this study, and their clinical and physiological data were measured before and after the treatment (clinical measurement, biomechanical measurement, and electroencephalography (EEG) measurement). Multiple biomarkers and clinical scale scores of patients who had completed manual stretching rehabilitation training were analyzed. Data were used to train deep learning prognosis models, yielding an 87.50% prognosis accuracy. Pre-trained prognosis models were then applied to patients who completed robotic-assisted stretching training, yielding a prognosis accuracy of 91.84%. Interpretation of the deep learning models revealed several key factors influencing patients' recoveries, including the plantar-flexor active range of movement (r = 0.930, P = 0.02), dorsiflexor strength (r = 0.932, P = 0.002), plantar-flexor strength (r = 0.930, P = 0.002), EEG power spectrum density and EEG functional connectivities in the occipital, central parietal, and parietal areas. Our results suggest (i) that deep learning can be a promising method for accurate prediction of the recovery potential of stroke patients in clinical scenarios and (ii) that it can be successfully applied to different rehabilitation trainings with explainable factors.

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.