Effects of brain-computer interface with functional electrical stimulation for gait rehabilitation in multiple sclerosis patients: preliminary findings in gait speed and event-related desynchronization onset latency

Abstract Objective. Brain-Computer Interfaces (BCI) with Functional Electrical Stimulation (FES) as a feedback device might promote neuroplasticity and hence improve motor function. Novel findings suggested that neuroplasticity could be possible in people with multiple sclerosis (pwMS). This preliminary study explores the effects of using a BCI-FES in therapeutic intervention, as an emerging methodology for gait rehabilitation in pwMS. Approach: People with relapsing-remitting, primary progressive or secondary progressive MS were evaluated with the inclusion criteria to enroll the 9 participants required by the statistically computed sample size. Each patient trained with a BCI-FES during 24 sessions distributed in 8 weeks. The effects were evaluated on gait speed (Timed 25 Foot Walk), walking ability (12-item Multiple Sclerosis Walking Scale), quality of life measures, the true positive rate as the BCI-FES performance metric and the event-related desynchronization onset latency of the sensorimotor rhythms. Main results: Seven patients completed the therapeutic intervention. A statistically and clinically significant post-treatment improvement was observed in gait speed, as a result of a reduction in the time to walk 25 feet (-1.99 s, p=0.018), and walking ability (-31.25 score points, p=0.028). The true positive rate showed a statistically significant improvement (+15.87 score points, p=0.018). An earlier event-related desynchronization onset latency (-180ms) after treatment was found. Significance: This is the first study that explored gait rehabilitation using BCI-FES in pwMS. The results showed improvement in gait which might have been promoted by changes in functional brain connections involved in sensorimotor rhythm modulation. Although more studies with a larger sample size and control group are required to validate the efficacy of this approach, these results suggest that BCI-FES technology could have a positive effect on MS gait rehabilitation.

Download Full-text

Pulse Width Does Not Influence the Gains Achieved With Neuromuscular Electrical Stimulation in People With Multiple Sclerosis: Double-Blind, Randomized Trial

Neurorehabilitation and Neural Repair ◽

10.1177/1545968317753681 ◽

2018 ◽

Vol 32 (1) ◽

pp. 84-93 ◽

Cited By ~ 4

Author(s):

Awad M. Almuklass ◽

Leah Davis ◽

Landon D. Hamilton ◽

Jeffrey R. Hebert ◽

Enrique Alvarez ◽

...

Keyword(s):

Multiple Sclerosis ◽

Electrical Stimulation ◽

Pulse Duration ◽

Gait Speed ◽

Neuromuscular Electrical Stimulation ◽

Walking Ability ◽

Plantar Flexor ◽

Stimulus Pulse ◽

Walking Performance ◽

Walking Endurance

Background. Multiple sclerosis (MS) eventually compromises the walking ability of most individuals burdened with the disease. Treatment with neuromuscular electrical stimulation (NMES) can restore some functional abilities in persons with MS, but its effectiveness may depend on stimulus-pulse duration. Objective. To compare the effects of a 6-week intervention with narrow- or wide-pulse NMES on walking performance, neuromuscular function, and disability status of persons with relapsing-remitting MS. Methods. Individuals with MS (52.6 ± 7.4 years) were randomly assigned to either the narrow-pulse (n = 13) or wide-pulse (n = 14) group. The NMES intervention was performed on the dorsiflexor and plantar flexor muscles of both legs (10 minutes each muscle, 4 s on and 12 s off) at a tolerable level for 18 sessions across 6 weeks. Outcomes were obtained before (week 0) and after (week 7) the intervention and 4 weeks later (week 11). Results. There was no influence of stimulus-pulse duration on the outcomes ( P > .05); thus, the data were collapsed across groups. The NMES intervention improved ( P < .05) gait speed and walking endurance, dorsiflexor strength in the more-affected leg, plantar flexor strength in the less-affected leg, force control for plantar flexors in the less-affected leg, and self-reported levels of fatigue and walking limitations. Conclusion. There was no influence of stimulus-pulse duration on the primary outcomes (gait speed and walking endurance). The 6-week NMES intervention applied to the lower leg muscles of persons with mild to moderate levels of disability can improve their walking performance and provide some symptom relief.

Download Full-text

Effect of a 2-Week Trial of Functional Electrical Stimulation on Gait Function and Quality of Life in People with Multiple Sclerosis

International Journal of MS Care ◽

10.7224/1537-2073.2013-032 ◽

2014 ◽

Vol 16 (3) ◽

pp. 146-152 ◽

Cited By ~ 11

Author(s):

Abbey Downing ◽

David Van Ryn ◽

Anne Fecko ◽

Christopher Aiken ◽

Sean McGowan ◽

...

Keyword(s):

Quality Of Life ◽

Multiple Sclerosis ◽

Electrical Stimulation ◽

Functional Electrical Stimulation ◽

Gait Speed ◽

Walking Ability ◽

Full Time ◽

Short Period ◽

The Impact

Background: Footdrop is a common gait deviation in people with multiple sclerosis (MS) leading to impaired gait and balance as well as decreased functional mobility. Functional electrical stimulation (FES) provides an alternative to the current standard of care for footdrop, an ankle-foot orthosis (AFO). FES stimulates the peroneal nerve and activates the dorsiflexor muscles, producing an active toe clearance and a more normal gait. This study was undertaken to determine the effects of a 2-week FES Home Assessment Program on gait speed, perceived walking ability, and quality of life (QOL) among people with MS-related footdrop. Methods: Participants completed the Timed 25-Foot Walk test (T25FW) and two self-report measures: 12-item Multiple Sclerosis Walking Scale (MSWS-12) and 29-item Multiple Sclerosis Impact Scale (MSIS-29). Measures were taken without FES before and with FES after 2 weeks of full-time FES wear. Results: A total of 19 participants (10 female, 9 male) completed the study; mean age and duration of disease were 51.77 ± 10.16 and 9.01 ± 7.90 years, respectively. Use of FES for 2 weeks resulted in a significant decrease in time to complete the T25FW (P < .0001), the MSWS-12 standardized score (P < .0001), and the MSIS-29 total (P < .0001), Physical subscale (P < .0001), and Psychological subscale (P = .0006) scores. Conclusions: These results suggest that use of FES can significantly improve gait speed, decrease the impact of MS on walking ability, and improve QOL in people with MS-related footdrop even over a short period of time.

Download Full-text

PRATD: A Phased Remote Access Trojan Detection Method with Double-Sided Features

Electronics ◽

10.3390/electronics9111894 ◽

2020 ◽

Vol 9 (11) ◽

pp. 1894

Author(s):

Chun Guo ◽

Zihua Song ◽

Yuan Ping ◽

Guowei Shen ◽

Yuhei Cui ◽

...

Keyword(s):

False Positive ◽

Detection Method ◽

False Positive Rate ◽

True Positive Rate ◽

Remote Access ◽

Detection Methods ◽

Security Threats ◽

True Positive ◽

Trojan Detection ◽

Positive Rate

Remote Access Trojan (RAT) is one of the most terrible security threats that organizations face today. At present, two major RAT detection methods are host-based and network-based detection methods. To complement one another’s strengths, this article proposes a phased RATs detection method by combining double-side features (PRATD). In PRATD, both host-side and network-side features are combined to build detection models, which is conducive to distinguishing the RATs from benign programs because that the RATs not only generate traffic on the network but also leave traces on the host at run time. Besides, PRATD trains two different detection models for the two runtime states of RATs for improving the True Positive Rate (TPR). The experiments on the network and host records collected from five kinds of benign programs and 20 famous RATs show that PRATD can effectively detect RATs, it can achieve a TPR as high as 93.609% with a False Positive Rate (FPR) as low as 0.407% for the known RATs, a TPR 81.928% and FPR 0.185% for the unknown RATs, which suggests it is a competitive candidate for RAT detection.

Download Full-text

Classifying the Biological Status of Honeybee Workers Using Gas Sensors

Sensors ◽

10.3390/s21010166 ◽

2020 ◽

Vol 21 (1) ◽

pp. 166

Author(s):

Jakub T. Wilk ◽

Beata Bąk ◽

Piotr Artiemjew ◽

Jerzy Wilde ◽

Maciej Siuda

Keyword(s):

Gas Sensors ◽

Laboratory Tests ◽

Test Chamber ◽

Ambient Air ◽

True Positive Rate ◽

True Positive ◽

Positive Rate ◽

Parameters Of Accuracy ◽

Selection Of

Honeybee workers have a specific smell depending on the age of workers and the biological status of the colony. Laboratory tests were carried out at the Department of Apiculture at UWM Olsztyn, using gas sensors installed in two twin prototype multi-sensor detectors. The study aimed to compare the responses of sensors to the odor of old worker bees (3–6 weeks old), young ones (0–1 days old), and those from long-term queenless colonies. From the experimental colonies, 10 samples of 100 workers were taken for each group and placed successively in the research chambers for the duration of the study. Old workers came from outer nest combs, young workers from hatching out brood in an incubator, and laying worker bees from long-term queenless colonies from brood combs (with laying worker bee’s eggs, humped brood, and drones). Each probe was measured for 10 min, and then immediately for another 10 min ambient air was given to regenerate sensors. The results were analyzed using 10 different classifiers. Research has shown that the devices can distinguish between the biological status of bees. The effectiveness of distinguishing between classes, determined by the parameters of accuracy balanced and true positive rate, of 0.763 and 0.742 in the case of the best euclidean.1nn classifier, may be satisfactory in the context of practical beekeeping. Depending on the environment accompanying the tested objects (a type of insert in the test chamber), the introduction of other classifiers as well as baseline correction methods may be considered, while the selection of the appropriate classifier for the task may be of great importance for the effectiveness of the classification.

Download Full-text

The Heartbeat Classification Based on PCA

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.195-196.402 ◽

2012 ◽

Vol 195-196 ◽

pp. 402-406

Author(s):

Xue Qin Chen ◽

Rui Ping Wang

Keyword(s):

Principal Component Analysis ◽

Pattern Recognition ◽

Recognition Task ◽

Principal Component ◽

True Positive Rate ◽

True Positive ◽

Heartbeat Classification ◽

Positive Rate ◽

Electrocardiogram Ecg ◽

Pattern Recognition Task

Classify the electrocardiogram (ECG) into different pathophysiological categories is a complex pattern recognition task which has been tried in lots of methods. This paper will discuss a method of principal component analysis (PCA) in exacting the heartbeat features, and a new method of classification that is to calculate the error between the testing heartbeat and reconstructed heartbeat. Training and testing heartbeat is taken from the MIT-BIH Arrhythmia Database, in which 8 types of arrhythmia signals are selected in this paper. The true positive rate (TPR) is 83%.

Download Full-text

The influence of digital PET/CT on diagnostic certainty and interrater reliability in [68Ga]Ga-PSMA-11 PET/CT for recurrent prostate cancer

European Radiology ◽

10.1007/s00330-021-07870-5 ◽

2021 ◽

Author(s):

Ian Alberts ◽

Jan-Niklas Hünermund ◽

Christos Sachpekidis ◽

Clemens Mingels ◽

Viktor Fech ◽

...

Keyword(s):

Prostate Cancer ◽

Interrater Reliability ◽

True Positive Rate ◽

True Positive ◽

Recurrent Prostate Cancer ◽

Pathological Lesions ◽

Diagnostic Certainty ◽

Pet Ct ◽

Positive Rate ◽

Digital Pet

Abstract Objective To investigate the impact of digital PET/CT on diagnostic certainty, patient-based sensitivity and interrater reliability. Methods Four physicians retrospectively evaluated two matched cohorts of patients undergoing [68Ga]Ga-PSMA-11 PET/CT on a digital (dPET/CT n = 65) or an analogue scanner (aPET/CT n = 65) for recurrent prostate cancer between 11/2018 and 03/2019. The number of equivocal and pathological lesions as well as the frequency of discrepant findings and the interrater reliability for the two scanners were compared. Results dPET/CT detected more lesions than aPET/CT (p < 0.001). A higher number of pathological scans were observed for dPET/CT (83% vs. 57%, p < 0.001). The true-positive rate at follow-up was 100% for dPET/CT compared to 84% for aPET/CT (p < 0.001). The proportion of lesions rated as non-pathological as a total of all PSMA-avid lesions detected for dPET/CT was comparable to aPET/CT (61.8% vs. 57.0%, p = 0.99). Neither a higher rate of diagnostically uncertain lesions (11.5% dPET/CT vs. 13.7% aPET/CT, p = 0.95) nor discrepant scans (where one or more readers differed in opinion as to whether the scan is pathological) were observed (18% dPET/CT vs. 17% aPET/CT, p = 0.76). Interrater reliability for pathological lesions was excellent for both scanner types (Cronbach’s α = 0.923 dPET/CT; α = 0.948 aPET/CT) and interrater agreement was substantial for dPET/CT (Krippendorf’s α = 0.701) and almost perfect in aPET/CT (α = 0.802). Conclusions A higher detection rate for pathological lesions for dPET/CT compared with aPET/CT in multiple readers was observed. This improved sensitivity was coupled with an improved true-positive rate and was not associated with increased diagnostic uncertainty, rate of non-specific lesions, or reduced interrater reliability. Key Points • New generation digital scanners detect more cancer lesions in men with prostate cancer. • When using digital scanners, the doctors are able to diagnose prostate cancer lesions with better certainty • When using digital scanners, the doctors do not disagree with each other more than with other scanner types.

Download Full-text

Face Recognition Using the SR-CNN Model

Sensors ◽

10.3390/s18124237 ◽

2018 ◽

Vol 18 (12) ◽

pp. 4237 ◽

Cited By ~ 9

Author(s):

Yu-Xin Yang ◽

Chang Wen ◽

Kai Xie ◽

Fang-Qing Wen ◽

Guan-Qun Sheng ◽

...

Keyword(s):

Face Recognition ◽

Target Position ◽

Operation Time ◽

True Positive Rate ◽

Processing Unit ◽

True Positive ◽

Face Database ◽

Acceleration Ratio ◽

Computational Performance ◽

Positive Rate

In order to solve the problem of face recognition in complex environments being vulnerable to illumination change, object rotation, occlusion, and so on, which leads to the imprecision of target position, a face recognition algorithm with multi-feature fusion is proposed. This study presents a new robust face-matching method named SR-CNN, combining the rotation-invariant texture feature (RITF) vector, the scale-invariant feature transform (SIFT) vector, and the convolution neural network (CNN). Furthermore, a graphics processing unit (GPU) is used to parallelize the model for an optimal computational performance. The Labeled Faces in the Wild (LFW) database and self-collection face database were selected for experiments. It turns out that the true positive rate is improved by 10.97–13.24% and the acceleration ratio (the ratio between central processing unit (CPU) operation time and GPU time) is 5–6 times for the LFW face database. For the self-collection, the true positive rate increased by 12.65–15.31%, and the acceleration ratio improved by a factor of 6–7.

Download Full-text

True Positive Rate

Encyclopedia of Machine Learning and Data Mining ◽

10.1007/978-1-4899-7687-1_100492 ◽

2017 ◽

pp. 1293-1293

Keyword(s):

True Positive Rate ◽

True Positive ◽

Positive Rate

Download Full-text

Markerless tracking of an entire insect colony

10.1101/2020.03.26.007302 ◽

2020 ◽

Cited By ~ 5

Author(s):

Katarzyna Bozek ◽

Laetitia Hebert ◽

Yoann Portugal ◽

Greg J. Stephens

Keyword(s):

Cell Activity ◽

True Positive Rate ◽

Computational Method ◽

Visual Features ◽

Brood Cell ◽

True Positive ◽

Body Width ◽

Markerless Tracking ◽

Positive Rate ◽

Fast Motion

AbstractWe present a comprehensive, computational method for tracking an entire colony of the honey bee Apis mellifera using high-resolution video on a natural honeycomb background. We adapt a convolutional neural network (CNN) segmentation architecture to automatically identify bee and brood cell positions, body orientations and within-cell states. We achieve high accuracy (~10% body width error in position, ~10° error in orientation, and true positive rate > 90%) and demonstrate months-long monitoring of sociometric colony fluctuations. We combine extracted positions with rich visual features of organism-centered images to track individuals over time and through challenging occluding events, recovering ~79% of bee trajectories from five observation hives over a span of 5 minutes. The resulting trajectories reveal important behaviors, including fast motion, comb-cell activity, and waggle dances. Our results provide new opportunities for the quantitative study of collective bee behavior and for advancing tracking techniques of crowded systems.

Download Full-text

Finding COVID-19 from Chest X-rays using Deep Learning on a Small Dataset

10.36227/techrxiv.12083964 ◽

2020 ◽

Cited By ~ 1

Author(s):

Lawrence Hall ◽

Dmitry Goldgof ◽

Rahul Paul ◽

Gregory M. Goldgof

Keyword(s):

False Negative ◽

True Positive Rate ◽

Small Data ◽

Good Resolution ◽

X Rays ◽

True Positive ◽

Data Set ◽

X Ray ◽

Negative Rate ◽

Positive Rate

Testing for COVID-19 has been unable to keep up with the demand. Further, the false negative rate is projected to be as high as 30% and test results can take some time to obtain. X-ray machines are widely available and provide images for diagnosis quickly. This paper explores how useful chest X-ray images can be in diagnosing COVID-19 disease. We have obtained 135 chest X-rays of COVID-19 and 320 chest X-rays of viral and bacterial pneumonia. A pre-trained deep convolutional neural network, Resnet50 was tuned on 102 COVID-19 cases and 102 other pneumonia cases in a 10-fold cross validation. The results were an overall accuracy of 89.2% with a COVID-19 true positive rate of 0.8039 and an AUC of 0.95. Pre-trained Resnet50 and VGG16 plus our own small CNN were tuned or trained on a balanced set of COVID-19 and pneumonia chest X-rays. An ensemble of the three types of CNN classifiers was applied to a test set of 33 unseen COVID-19 and 218 pneumonia cases. The overall accuracy was 91.24% with the true positive rate for COVID-19 of 0.7879 with 6.88% false positives for a true negative rate of 0.9312 and AUC of 0.94. This preliminary study has flaws, most critically a lack of information about where in the disease process the COVID-19 cases were and the small data set size. More COVID-19 case images at good resolution will enable a better answer to the question of how useful chest X-rays can be for diagnosing COVID-19.

Download Full-text