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.

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).

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.

Objective : Alzheimer’s disease (AD) continues to be a major challenge because handling high-dimensional data is time-consuming and expensive due to its complexity. A large feature space often increases computational costs and reduces model interpretability. This study addresses this problem by evaluating and comparing multiple feature selection techniques to identify the most informative biomarkers for AD diagnosis. Methods : Our study used data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) to implement and test three feature selection approaches, visualization-based, filter-based, and wrapper-based, within a Naive Bayes (NB) classification framework. Results : Based on the results of the analysis, the wrapper method achieved 96.77% classification accuracy, outperforming both visualization and filter methods with 86.19 and 91.87%, respectively. Interestingly, even when over 92.5% of the original features were removed the classifier still performed well, indicating that only a small set of features is necessary to ensure reliable diagnosis. Discussion : This study illustrates that strategically selecting features improves diagnostic accuracy while reducing computational burden, providing a more efficient framework for machine learning applications in Alzheimer's disease research.