•End-to-end neural network model for classifying motor imagery EEG signals.•Using 1-D CNN layers to learn temporal and spatial filters for feature extraction.•Application of transfer learning to ...calibrate the model for individual subjects.•Analysis of the temporal and spatial filters learned by the model.
Goal: To develop and implement a Deep Learning (DL) approach for an electroencephalogram (EEG) based Motor Imagery (MI) Brain-Computer Interface (BCI) system that could potentially be used to improve the current stroke rehabilitation strategies.
Method: The DL model is using Convolutional Neural Network (CNN) layers for learning generalized features and dimension reduction, while a conventional Fully Connected (FC) layer is used for classification. Together they build a unified end-to-end model that can be applied to raw EEG signals. This previously proposed model was applied to a new set of data to validate its robustness against data variations. Furthermore, it was extended by subject-specific adaptation. Lastly, an analysis of the learned filters provides insights into how such a model derives a classification decision.
Results: The selected global classifier reached 80.38%, 69.82%, and 58.58% mean accuracies for datasets with two, three, and four classes, respectively, validated using 5-fold crossvalidation. As a novel approach in this context, transfer learning was used to adapt the global classifier to single individuals improving the overall mean accuracy to 86.49%, 79.25%, and 68.51%, respectively. The global models were trained on 3s segments of EEG data from different subjects than they were tested on, which proved the generalization performance of the model.
Conclusion: The results are comparable with the reported accuracy values in related studies and the presented model outperforms the results in the literature on the same underlying data. Given that the model can learn features from data without having to use specialized feature extraction methods, DL should be considered as an alternative to established EEG classification methods, if enough data is available.
Strokes are a growing cause of mortality and many stroke survivors suffer from motor impairment as well as other types of disabilities in their daily life activities. To treat these sequelae, motor ...imagery (MI) based brain-computer interface (BCI) systems have shown potential to serve as an effective neurorehabilitation tool for post-stroke rehabilitation therapy. In this review, different MI-BCI based strategies, including “Functional Electric Stimulation, Robotics Assistance and Hybrid Virtual Reality based Models,” have been comprehensively reported for upper-limb neurorehabilitation. Each of these approaches have been presented to illustrate the in-depth advantages and challenges of the respective BCI systems. Additionally, the current state-of-the-art and main concerns regarding BCI based post-stroke neurorehabilitation devices have also been discussed. Finally, recommendations for future developments have been proposed while discussing the BCI neurorehabilitation systems.
•BCI methods are among the most effective tool for designing rehabilitation systems.•Use of virtual reality (VR) can increase the efficiency of BCI rehab systems.•“FES,” “Robotics Assistance,” and “Hybrid VR based Models” are main BCI approaches.•In the future, flexible electronics can be used for designing stroke rehab systems.
The efficacy of closure of a patent foramen ovale (PFO) in the prevention of recurrent stroke after cryptogenic stroke is uncertain. We investigated the effect of PFO closure combined with ...antiplatelet therapy versus antiplatelet therapy alone on the risks of recurrent stroke and new brain infarctions.
In this multinational trial involving patients with a PFO who had had a cryptogenic stroke, we randomly assigned patients, in a 2:1 ratio, to undergo PFO closure plus antiplatelet therapy (PFO closure group) or to receive antiplatelet therapy alone (antiplatelet-only group). Imaging of the brain was performed at the baseline screening and at 24 months. The coprimary end points were freedom from clinical evidence of ischemic stroke (reported here as the percentage of patients who had a recurrence of stroke) through at least 24 months after randomization and the 24-month incidence of new brain infarction, which was a composite of clinical ischemic stroke or silent brain infarction detected on imaging.
We enrolled 664 patients (mean age, 45.2 years), of whom 81% had moderate or large interatrial shunts. During a median follow-up of 3.2 years, clinical ischemic stroke occurred in 6 of 441 patients (1.4%) in the PFO closure group and in 12 of 223 patients (5.4%) in the antiplatelet-only group (hazard ratio, 0.23; 95% confidence interval CI, 0.09 to 0.62; P=0.002). The incidence of new brain infarctions was significantly lower in the PFO closure group than in the antiplatelet-only group (22 patients 5.7% vs. 20 patients 11.3%; relative risk, 0.51; 95% CI, 0.29 to 0.91; P=0.04), but the incidence of silent brain infarction did not differ significantly between the study groups (P=0.97). Serious adverse events occurred in 23.1% of the patients in the PFO closure group and in 27.8% of the patients in the antiplatelet-only group (P=0.22). Serious device-related adverse events occurred in 6 patients (1.4%) in the PFO closure group, and atrial fibrillation occurred in 29 patients (6.6%) after PFO closure.
Among patients with a PFO who had had a cryptogenic stroke, the risk of subsequent ischemic stroke was lower among those assigned to PFO closure combined with antiplatelet therapy than among those assigned to antiplatelet therapy alone; however, PFO closure was associated with higher rates of device complications and atrial fibrillation. (Funded by W.L. Gore and Associates; Gore REDUCE ClinicalTrials.gov number, NCT00738894 .).
Near-infrared spectroscopy (NIRS) is susceptible to signal artifacts caused by relative motion between NIRS optical fibers and the scalp. These artifacts can be very damaging to the utility of ...functional NIRS, particularly in challenging subject groups where motion can be unavoidable. A number of approaches to the removal of motion artifacts from NIRS data have been suggested. In this paper we systematically compare the utility of a variety of published NIRS motion correction techniques using a simulated functional activation signal added to 20 real NIRS datasets which contain motion artifacts. Principle component analysis, spline interpolation, wavelet analysis, and Kalman filtering approaches are compared to one another and to standard approaches using the accuracy of the recovered, simulated hemodynamic response function (HRF). Each of the four motion correction techniques we tested yields a significant reduction in the mean-squared error (MSE) and significant increase in the contrast-to-noise ratio (CNR) of the recovered HRF when compared to no correction and compared to a process of rejecting motion-contaminated trials. Spline interpolation produces the largest average reduction in MSE (55%) while wavelet analysis produces the highest average increase in CNR (39%). On the basis of this analysis, we recommend the routine application of motion correction techniques (particularly spline interpolation or wavelet analysis) to minimize the impact of motion artifacts on functional NIRS data.
Background and Purpose- The GLX (glycocalyx) is a protein/polysaccharide meshwork at the cellular surface. Consisting largely of glycosaminoglycans and proteoglycans, the GLX can shed in response to ...stress. In this study, we assay 11 components of the GLX in plasma from patients with ischemic stroke from a longitudinal cohort. Methods- Plasma samples from healthy individuals (N=8), and patients with ischemic stroke day ≥3, day 7, and day 90 (N=9-14) were immunoassayed for diverse components of the GLX. Results- Median stroke severity was mild (National Institutes of Health Stroke Scale 2.0 (range, 0-6) at day ≤3). Three (keratan-chondroitin-heparan-sulfate) of 4 glycosaminoglycans and CD44 (proteoglycan) were increased at day 7 and returned to baseline at day 90. Proteoglycan syndecan (Syn)-3 increased and Syn-2 levels decreased, significantly. Conclusions- Individual GLX components are often assayed as stand-alone biomarkers for endothelial health. This study suggests a full assessment of GLX components is more indicative of the endothelial health of an individual and represents a complex GLX signature that may be valuable as a composite biomarker of disease.
Lumbar puncture is generally performed in stroke settings when infectious or inflammatory diseases are suspected to be the etiology. This review aimed to assess the prevalence of pleocytosis in the ...cerebrospinal fluid following ischemic stroke without inflammatory or infectious etiology.
We searched PubMed for studies with mentions of “ischemic stroke AND cerebrospinal fluid”. We included only studies written in English, including patients with a primary diagnosis of either ischemic stroke or transient ischemic attack (TIA), and where white blood cell count in the spinal fluid was presented. Studies investigating common etiologies for pleocytosis, was excluded. Study and patient characteristics, white blood cell count and time to lumbar puncture were presented in tables, and the prevalence of pleocytosis were reported and plotted graphically.
We included 15 studies with 1607 patients, 1522 with ischemic stroke and 85 with TIA. The prevalence of pleocytosis was between 0% to 28,6% and a mean of 11.8%. The highest white blood cell count found with common etiologies for pleocytosis ruled out was 56 cells/mm3. A mean white blood cell count of 4.0 was based on the three studies where this was available.
The included studies were methodologically heterogenous and few had pleocytosis as primary outcome. Pleocytosis following ischemic stroke is uncommon and should prompt further investigations
•Pleocytosis in cerebrospinal fluid after ischemic stroke is uncommon.•Findings of pleocytosis in CSF after ischemic stroke should lead to further investigations.•Pleocytosis is more common in settings of neuroinflammation or infection.•The studies identified in this review where heterogenous in design.
Melatonin plays an important role in regulation and maintaining of the circadian rhythm. In the elderly population, an array of disturbances of circadian rhythm and sleep can be observed; however the ...current knowledge within the group of healthy, elderly is scarce. This systematic literature review of studies on the melatonin profile measured in the blood of healthy, elderly individuals included 519 studies, found in the primary search on PubMed. After reviewing the title and abstract, 47 studies were found eligible for full text review. The inclusion criteria were defined as follows: healthy, elderly individuals, with a mean or average age over 65 years and analysis done in blood or plasma. In addition to the primary search, three studies were directly identified by the reference lists of already included studies. A final total of 23 studies were included in the systematic literature review. In reviewing the literature, a clear circadian melatonin profile with a nocturnal peak at 3 am and lower daytime levels was observed in the healthy, elderly population. In elderly over 75 years of age, the nocturnal level of melatonin may be lower; however, the circadian rhythmicity is maintained. In the comparison of elderly, independently living individuals and individuals living in care facilities, the latter group had lower levels of nocturnal melatonin peak as well as higher daytime levels; however one can wonder if elderly in care facilities are healthy. The 23 included studies in the systematic literature review had varying primary objectives and generally the term "healthy" within this population group proves difficult to clearly define. As a result of this, an obvious interstudy variability existed, which is a limitation of this systematic literature review. However, the graphs depicted represent the best possible estimation of the melatonin profile in a healthy, elderly population. Future research in the melatonin profile within this population should focus on clearly defined healthy elderly to ensure a valid normal material in this age group.
Dysphagia is common after stroke, associated with increased death and dependency, and treatment options are limited. Pharyngeal electric stimulation (PES) is a novel treatment for poststroke ...dysphagia that has shown promise in 3 pilot randomized controlled trials.
We randomly assigned 162 patients with a recent ischemic or hemorrhagic stroke and dysphagia, defined as a penetration aspiration score (PAS) of ≥3 on video fluoroscopy, to PES or sham treatment given on 3 consecutive days. The primary outcome was swallowing safety, assessed using the PAS, at 2 weeks. Secondary outcomes included dysphagia severity, function, quality of life, and serious adverse events at 6 and 12 weeks.
In randomized patients, the mean age was 74 years, male 58%, ischemic stroke 89%, and PAS 4.8. The mean treatment current was 14.8 (7.9) mA and duration 9.9 (1.2) minutes per session. On the basis of previous data, 45 patients (58.4%) randomized to PES seemed to receive suboptimal stimulation. The PAS at 2 weeks, adjusted for baseline, did not differ between the randomized groups: PES 3.7 (2.0) versus sham 3.6 (1.9), P=0.60. Similarly, the secondary outcomes did not differ, including clinical swallowing and functional outcome. No serious adverse device-related events occurred.
In patients with subacute stroke and dysphagia, PES was safe but did not improve dysphagia. Undertreatment of patients receiving PES may have contributed to the neutral result.
URL: http://www.controlled-trials.com. Unique identifier: ISRCTN25681641.
To estimate the direct and indirect costs of stroke in patients and their partners.
Direct and indirect costs were calculated using records from the Danish National Patient Registry from 93,047 ...ischemic, 26,012 hemorrhagic and 128,824 unspecified stroke patients and compared with 364,433, 103,741 and 500,490 matched controls, respectively.
Independent of age and gender, stroke patients had significantly higher rates of mortality, health-related contacts, medication use and lower employment, lower income and higher social-transfer payments than controls. The attributable cost of direct net health care costs after the stroke (general practitioner services, hospital services, and medication) and indirect costs (loss of labor market income) were €10,720, €8,205 and €7,377 for patients, and €989, €1,544 and €1.645 for their partners, over and above that of controls for hemorrhagic, ischemic and unspecified stroke, respectively. The negative social- and health-related status could be identified up to eleven years before the first diagnosis.
Stroke has significant mortality, morbidity and socioeconomic consequences for patients, their partners and society.