A Novel Application of Deep Learning (Convolutional Neural Network) for Traumatic Spinal Cord Injury Classification Using Automatically Learned Features of EMG Signal.

In this study, a traumatic spinal cord injury (TSCI) classification system is proposed using a convolutional neural network (CNN) technique with automatically learned features from electromyography (EMG) signals for a non-human primate (NHP) model. A comparison between the proposed classification system and a classical classification method (k-nearest neighbors, kNN) is also presented. Developing such an NHP model with a suitable assessment tool (i.e., classifier) is a crucial step in detecting the effect of TSCI using EMG, which is expected to be essential in the evaluation of the efficacy of new TSCI treatments. Intramuscular EMG data were collected from an agonist/antagonist tail muscle pair for the pre- and post-spinal cord lesion from five Macaca fasicularis monkeys. The proposed classifier is based on a CNN using filtered segmented EMG signals from the pre- and post-lesion periods as inputs, while the kNN is designed using four hand-crafted EMG features. The results suggest that the CNN provides a promising classification technique for TSCI, compared to conventional machine learning classification. The kNN with hand-crafted EMG features classified the pre- and post-lesion EMG data with an F-measure of 89.7% and 92.7% for the left- and right-side muscles, respectively, while the CNN with the EMG segments classified the data with an F-measure of 89.8% and 96.9% for the left- and right-side muscles, respectively. Finally, the proposed deep learning classification model (CNN), with its learning ability of high-level features using EMG segments as inputs, shows high potential and promising results for use as a TSCI classification system. Future studies can confirm this finding by considering more subjects.

Neurophysiological Characterization of a Non-Human Primate Model of Traumatic Spinal Cord Injury Utilizing Fine-Wire EMG Electrodes.

This study aims to characterize traumatic spinal cord injury (TSCI) neurophysiologically using an intramuscular fine-wire electromyography (EMG) electrode pair. EMG data were collected from an agonist-antagonist pair of tail muscles of Macaca fasicularis, pre- and post-lesion, and for a treatment and control group. The EMG signals were decomposed into multi-resolution subsets using wavelet transforms (WT), then the relative power (RP) was calculated for each individual reconstructed EMG sub-band. Linear mixed models were developed to test three hypotheses: (i) asymmetrical volitional activity of left and right side tail muscles (ii) the effect of the experimental TSCI on the frequency content of the EMG signal, (iii) and the effect of an experimental treatment. The results from the electrode pair data suggested that there is asymmetry in the EMG response of the left and right side muscles (p-value < 0.001). This is consistent with the construct of limb dominance. The results also suggest that the lesion resulted in clear changes in the EMG frequency distribution in the post-lesion period with a significant increment in the low-frequency sub-bands (D4, D6, and A6) of the left and right side, also a significant reduction in the high-frequency sub-bands (D1 and D2) of the right side (p-value < 0.001). The preliminary results suggest that using the RP of the EMG data, the fine-wire intramuscular EMG electrode pair are a suitable method of monitoring and measuring treatment effects of experimental treatments for spinal cord injury (SCI).

Postanoxic myoclonus: two case presentations and review of medical management.

Postanoxic myoclonus is a rare manifestation after an anoxic event, with fewer than 150 cases reported in the literature. The condition is characterized by myoclonic jerks, which are worse on action than at rest, and postural lapses, ataxia, and dysarthria. The disability caused by postanoxic myoclonus can be profound, and treatment in the rehabilitation setting is exceptionally challenging. We present 2 patients who suffered from postanoxic myoclonus after an anoxic event, both of whom were successfully treated with a combination of levetiracetam, valproic acid, and clonazepam. These cases act as a framework for discussing the management of postanoxic myoclonus in the clinical setting.

Using Nutraceuticals to Help Manage Traumatic Spinal Cord Injury.

Traumatic spinal cord injury (TSCI) is a significant public health challenge that has an adverse impact on functional independence, quality of life, and life expectancy. Management of people's chronic conditions is a key aspect of contemporary medical practice. Our study was an open label, single arm, prospective pilot study to evaluate the feasibility of treating people with TSCI. The study intervention was treatment with oral selenium and vitamin E. Participants were 18 years or older and experienced a TSCI at least one year prior to enrollment. Daily doses of 50 mcg of selenium and 400 IU of vitamin E were administered. Participants had radiologic (MRI tractography) and clinical (ASIA) assessments prior to initiating treatment, and these assessments were repeated after one year of treatment. Four subjects completed the full twelve-month study. Adherence, based on pill counts, was approximately 75% in all subjects. There were no adverse events related to study medications. During the treatment period, subjects reported improvement in certain symptoms. There was no significant difference in ASIA scores before and after the intervention. Combination treatment with vitamin E and selenium has been demonstrated as safe for TSCI patients. It is possible to use DTI values to locate the epicenter of a lesion as well as gauge the extent of injury. MRI tractography may serve as a meaningful surrogate endpoint. The results of this study suggest that it is feasible to conduct a larger long-term clinical trial to evaluate the efficacy of combination treatment of TSCI.

Functional improvement related to enrolment in a Parkinson's disease rehabilitation program.

BACKGROUND: Parkinson's disease (PD) is a progressive neurodegenerative disorder with manifestations such as tremors, rigidity and bradykinesia. OBJECTIVE: The objective of this study was to evaluate the efficacy of outpatient multidisciplinary rehabilitation. METHODS: 179 patients participated in the six-week program. The following outcomes were measured: Timed Up and Go (TUG), sit to stand five times (STSx5) and in 30 seconds (STS30), six minute walk distance (6MWD) and gait velocity (6MWV), MOCA, bilateral grip strength, 360-degree turn (360 R, 360 L) and bilateral nine hole peg test. Pre- and post- data was analyzed via paired t-tests. Multiple regression was used to determine age- or gender-affected outcomes. RESULTS: Patients showed a statistically significant improvement (p < 0.05) in all outcomes. Mean TUG improved by 1.63 seconds (s), STSx5 by 4.19s, STS30 by 2.37 repetitions, 6MWD by 66.8 metres, 6MWV by 0.15 m/s, MOCA by 1.50 points, 360 R by 1.17s, 360 L by 1.60s, Grip R by 0.78 kg, Grip L by 0.95 kg, 9HP R by 1.71s and 9HP L by 1.58s. Gender had no influence. Age was a statistically significant predictor in STSx5 and 6MW. CONCLUSIONS: An outpatient multidisciplinary program successfully decreased motor impairment and increased overall functional independence in PD.

Comparison study of classification methods of intramuscular electromyography data for non-human primate model of traumatic spinal cord injury.

Traumatic spinal cord injury is a serious neurological disorder. Patients experience a plethora of symptoms that can be attributed to the nerve fiber tracts that are compromised. This includes limb weakness, sensory impairment, and truncal instability, as well as a variety of autonomic abnormalities. This article will discuss how machine learning classification can be used to characterize the initial impairment and subsequent recovery of electromyography signals in an non-human primate model of traumatic spinal cord injury. The ultimate objective is to identify potential treatments for traumatic spinal cord injury. This work focuses specifically on finding a suitable classifier that differentiates between two distinct experimental stages (pre-and post-lesion) using electromyography signals. Eight time-domain features were extracted from the collected electromyography data. To overcome the imbalanced dataset issue, synthetic minority oversampling technique was applied. Different ML classification techniques were applied including multilayer perceptron, support vector machine, K-nearest neighbors, and radial basis function network; then their performances were compared. A confusion matrix and five other statistical metrics (sensitivity, specificity, precision, accuracy, and F-measure) were used to evaluate the performance of the generated classifiers. The results showed that the best classifier for the left- and right-side data is the multilayer perceptron with a total F-measure of 79.5% and 86.0% for the left and right sides, respectively. This work will help to build a reliable classifier that can differentiate between these two phases by utilizing some extracted time-domain electromyography features.

Model of Traumatic Spinal Cord Injury for Evaluating Pharmacologic Treatments in Cynomolgus Macaques (Macaca fasicularis).

Here we present the results of experiments involving cynomolgus macaques, in which a model of traumatic spinal cord injury (TSCI) was created by using a balloon catheter inserted into the epidural space. Prior to the creation of the lesion, we inserted an EMG recording device to facilitate measurement of tail movement and muscle activity before and after TSCI. This model is unique in that the impairment is limited to the tail: the subjects do not experience limb weakness, bladder impairment, or bowel dysfunction. In addition, 4 of the 6 subjects received a combination treatment comprising thyrotropin releasing hormone, selenium, and vitamin E after induction of experimental TSCI. The subjects tolerated the implantation of the recording device and did not experience adverse effects due the medications administered. The EMG data were transformed into a metric of volitional tail moment, which appeared to be valid measure of initial impairment and subsequent natural or treatment-related recovery. The histopathologic assessment demonstrated widespread axon loss at the site of injury and areas cephalad and caudad. Histopathology revealed evidence of continuing inflammation, with macrophage activation. The EMG data did not demonstrate evidence of a statistically significant treatment effect.

A pilot study of functional access to public buildings and facilities for persons with impairments.

PURPOSE: To compare functional access to public buildings and facilities for persons with and without impairments. METHOD: This is a cross-sectional pilot study with a survey design. A four-member participant team representing three impairment types: mobility impaired person using a wheelchair, mobility impaired person who was not a wheelchair user, visually impaired person, and a control with no known impairments, challenged a stratified random sample of 30 public buildings in Greater Boston. Using a task oriented data collection instrument, functional access was determined in terms of percentage of tasks performed, time, distance, barriers and facilitators. RESULTS: Overall, task performance was high for the team. However, the wheelchair user reported a lower task performance (81%) in comparison to the control (100%) and persons with mobility and visual impairments (97-98%). There was little variation in mean values for time and distance to complete tasks. More barriers were reported by the persons with mobility impairments, wheelchair user and non-wheelchair user, and; highest facilitators by the person with visual impairment and the wheelchair user. The control reported the lowest barriers and facilitators. The types of barriers and facilitators varied for the three impairments and the control structural for wheelchair and mobility impairments, wayfinding for visual impairment and interpersonal for control. CONCLUSIONS: Task performance by itself may not be a good predictor of functional access. Barriers and facilitators are critical to understanding issues related to functional access for persons with impairments. Knowledge of how these differ for different impairments can be useful for improving environmental access and rehabilitation.

The impact of Internet access for people with spinal cord injuries: a descriptive analysis of a pilot study.

PURPOSE: A pilot study was undertaken regarding the effect of Internet access on health-related quality of life (HRQoL) and self-reported impact for people with spinal cord injuries (SCI). This study is unique in providing free Internet access and looking at benefits for people with disabilities. METHOD: HRQoL was measured using indicators of global health and social isolation at baseline and after 6 to 19 months of use via telephone interviews on a convenience sample of 23 adults with SCI. Additionally, monthly telephone surveys measured usage patterns, recreation, and self-reported impact. Both quantitative and qualitative analyses were conducted. Bivariate tests for differences in proportions and paired T-tests were conducted. Qualitatively, conceptual categories of impact were created using the Constant Comparative Method. RESULTS: Qualitatively, the predominant benefit was quality of life, mentioned by 61% of participants 46% of months surveyed, with quantitative trends towards improved emotional health. Ease of access to information, social connection, and quality of information were also frequently reported, with modest support from quantitative data. CONCLUSIONS: The study's persuasive qualitative results suggest the Internet has particular benefit to people with disabilities and that rehabilitation goals should include leisure. Further scientific research is strongly warranted.

Levodopa/carbidopa to improve motor function subsequent to brain tumor excision.

OBJECTIVE: The aim of this study was to evaluate the role of levodopa/carbidopa as an augmenting agent to improve motor recovery after brain tumor excision. DESIGN: This case report is structured as an n-of-1 style trial. The study patient was an outpatient with residual hemiparesis secondary to removal of benign oligoastrocytoma seen in an outpatient physiatry practice at an academic center. The study intervention was levodopa/carbidopa vs. placebo, combined with a structured 6-wk physiotherapy regimen. Outcomes were measured using the motor subscale of the Fugl-Meyer Assessment to assess for motor recovery. RESULTS: The mean motor Fugl-Meyer Assessment score for the levodopa/carbidopa weeks was 6.90 points greater than the mean score for placebo. The results were significant at P < 0.05. CONCLUSIONS: Levodopa/carbidopa may have a beneficial effect on improving motor recovery after sustaining a brain injury as a result of tumor excision.

Facial paralysis: a critical review of accepted explanation.

Historically, paralysis of facial muscles has been divided into "upper motor neuron injury" and "lower motor neuron injury". Patients who experience a stroke in the cortex or internal capsule have UMN injury and cannot purse their lips or smile on command. They are, however, able to wrinkle their forehead, raise their eyebrows, and completely close their eyes. Patients with LMN injury, in addition to the aforementioned impairments cannot raise their eyebrows. The classical explanations for these clinical findings are that the upper facial muscles receive bilateral innervation from the cerebral cortex and the lower facial muscles receive only unilateral innervation from the contralateral cerebral cortex. However, a review of the basic science literature indicates that commonly accepted explanations and the pattern of cortical projections are not consistent with anatomical studies. Studies in monkeys demonstrate that both the upper facial nucleus and the lower facial nucleus receive bilateral cortical projections. As well, there is no direct anatomical evidence in human beings that the facial nucleus (upper or lower) receives any innervation from the cortex.

The complications of scar formation associated with intrathecal pump placement.

A 40-year-old man had an intrathecal morphine-baclofen pump inserted for the treatment of severe dystonia affecting all limbs and severe low back pain. The etiology of his dystonic symptoms, despite thorough investigations, was uncertain. At age 45, the patient fell resulting in a cervical spinal cord injury. He underwent C2 through C5 instrumentation and fusion for cervical spine stabilization. Subsequently, an intrathecal morphine-baclofen pump was implanted to control pain and decrease spasticity. The patient ultimately died at age 48 from complications of pneumonia, and an autopsy was performed. Gross pathologic examination revealed that the intrathecal catheter entered the posterior aspect of the lumbar thecal sac, but coursed superiorly in the anterior intradural space. The catheter tip exited the thecal sac in the upper thoracic spine and became embedded in a fibrotic scar. Displacement of the catheter tip of the intrathecal morphine-baclofen pump and subsequent formation of scar tissue resulted in decreased drug delivery, contributing to diminished pain control and functional status. Catheter displacement and epidural scar formation must be considered as a potential cause of ineffective pain control and decreased functional status in patients with intrathecal morphine-baclofen pumps.

Subjective hearing loss and history of traumatic brain injury exhibits abnormal brainstem auditory evoked response: a case report.

A 30-year-old woman presented with long-standing subjective unilateral auditory difficulties 13 years after sustaining closed head trauma. The battery of audiologic tests indicated normal hearing, but brainstem auditory evoked response (BAER) tests revealed abnormal neurogenic potentials in the symptomatic ear. The discrepancy between a normal pure tone audiogram and abnormal BAERs suggests that a site of neurologic injury could be causing the patient's problem with auditory perception. Imaging studies with gadolinium enhancement, however, did not document any abnormalities in the brainstem. Our present findings and previously published literature help identify the specific site of a neurologic deficit when routine audiologic tests and imaging studies detect no significant abnormality.