Journal of Translational Research

All submissions of the EM system will be redirected to Online Manuscript Submission System. Authors are requested to submit articles directly to Online Manuscript Submission System of respective journal.
Reach Us +441518081136

Short Communication - Journal of Translational Research (2022) Volume 6, Issue 5

Knee bone fractures in patients with neurological injuries and neuromuscular disorders.

Farlane M*

Department of Dentistry-Biomaterials, Institute for Molecular Life Sciences, Radboud University Medical Center, Netherlands

Corresponding Author:
Mac Farlane
Department of Dentistry-Biomaterials
Institute for Molecular Life Sciences
Radboud University Medical Center, Netherlands
E mail:

Received: 06-Sep-2022, Manuscript No. AATR-22-78374; Editor assigned: 07-Sep-2022, Pre QC No. AATR-22-78374 (PQ); Reviewed: 21-Sep-2022, QC No. AATR-22-78374; Revised: 23-Sep-2022, Manuscript No. AATR-22-78374(R); Published: 30-Sep-2022, DOI:10.35841/aatr-6.5.125

Citation: Farlane M. Knee bone fractures in patients with neurological injuries and neuromuscular disorders. Am J Transl Res. 2022;6(5):125

Visit for more related articles at Journal of Translational Research


Diseases known as neuromuscular disorders affect our capacity to regulate bodily movements. Neuromuscular disorders are frequently diagnosed using needle electromyography (nEMG), an electrophysiological test that uses an invasive needle to measure the electric signals produced by muscles. An electromyography analyses nEMG signal characteristics manually to determine the different types of neuromuscular disorders and this process is heavily reliant on the electromyography's subjective observations. Modern computer-aided methods classified nEMG signals, which are not well-suited for signal classification, using deep learning image classification models. Additionally, model explainability-which is essential in medical applications-was not taken into account. In order to classify nEMG neuromuscular disorders, this study aims to increase prediction accuracy, inference speed and model predictions explanation.


Electromyography, Neuromuscular disorders, Electrophysiologic diagnosis.


One of our fundamental human abilities and a requirement for living a life with meaning is the capacity to voluntarily control our movements. However, such a crucial biological process could be compromised by diabetes, chemotherapy, or other unidentified causes, leading to neuromuscular disorders. Needle electromyography (nEMG), an electrophysiological test that records electrical activity generated from nerves, muscles, and neuromuscular junctions by inserting a needle into a muscle at rest or during muscle contraction, has been widely used in the electrophysiologic diagnosis of neuromuscular disorders. Contraction Based on the abnormalities in the measured nEMG signals, a qualified electromyography makes a diagnosis of the subject's neuromuscular disorders. The current subjective method is highly dependent on the electromyography’s experience, making it susceptible to errors despite the fact that nEMG is effective at diagnosing the subtypes of neuromuscular disorders, as shown by the inter- rater reliability of 61-81% [1-2].

Deep learning has demonstrated exceptional performance among the various machine learning models by utilizing the strength of large data in nonlinear tasks that are challenging to mathematically analyses. Although deep learning is being used more frequently in medicine, its use in classifying nEMG neuromuscular disorders is still limited. Surface electromyography data was frequently used in prior works on deep learning neuromuscular disorder classification using electromyography signals, and the majority of previous studies that used nEMG signals concentrated on using traditional machine learning models and manually crafted feature extraction techniques. Two studies on deep learning nEMG neuromuscular disorder classification used image classification models in order to categories the nEMG signals in their respective studies. NEMG signals were used to create Mel-spectrograms, and pretrained image classification was used [3].

While previous works have incontestable the potential of deep learning application in nEMG identification classification, further enhancements are needed to use deep learning in real nEMG electrophysiologic identification. First, comparable performance isn't bonded once exploitation image classification models in signal classification tasks since the models were designed for natural image classification second, previous works have targeted on classifying the signals rather than the individual subjects. However, signals of varied lengths are measured from differing kinds and numbers of muscles for every subject in nEMG electro diagnosis. An acceptable live to integrate the heterogeneousness in signal length, muscle sources, and variety of signals is important to predict the identification of subjects. Lastly, it's vital to spot however a machine learning model makes predictions, particularly in medical applications machine learning model should be investigated to make sure the model is creating predictions supported relevant options and not artifacts a subject not self- addressed by previous works [4].

Currently, there's no cure for contractor disorders. However, analysis is being conducted and numerous medicine and genetic therapies provide hope of finding ways that to cure those conditions at the moment, treating the symptoms, enhancing the standard of life, and delaying wellness progression has been with success administered physical therapy, physiatrist and surgery are all a crucial a part of the general management of youngsters and adults with contractor disorders. Most patients can have regular assessments (between half dozen and twelve months looking on the severity. wherever any issues or changes should be noted. The physical therapy protocol ought to record if deterioration or improvement has occurred; the presence of pain, falls or problems in school has to be compelled to be referred fitly. Home variations ought to be place in situ if the patient begins to lose operate or become non-ambulant. Independence during this cohort of patients ought to be the most priority. The individual must be rigorously assessed. For ambulatory patients, it's necessary to seem at speed, distance, causes of stopping. For non-ambulant, the sort of chair might verify their level of independence [5].


In this study, we have a tendency to propose nEMGNet, a one- dimensional convolutional neural network (1D-CNN) model that extracts options from raw nEMG signals with improved accuracy compared to models from previous works The motivation for nEMGNet was to create a domain-specific deep learning model instead of to use models designed for different tasks. This study additionally introduces the divide-and- vote (DiVote) rule to predict the identification of a theme by integration the heterogeneous muscle signals into an unvaried kind. By combining nEMGNet and DiVote rule, diagnoses of subjects were expected from a heterogeneous organisation that permits for sensible implementation in electrophysiologic identification. When the performance of nEMGNet and also the DiVote rule was verified, we have a tendency to known however nEMGNet created predictions by applying feature image Feature image could be a powerful interpretable deep learning technique that shows the options learned by a deep learning model.


  1. Danckworth F, Karabul N, Posa A. et al. Risk factors for osteoporosis, falls and fractures in hereditary myopathies and sporadic inclusion body myositis-A cross sectional survey. Mol Genet Metab Rep. 2014;1(3):85-97.
  2. Indexed at, Google Scholar, Cross Ref

  3. Ghatas MP, Sutor TW, Gorgey AS. Prediction of distal femur and proximal tibia bone mineral density from total body dual energy X-Ray absorptiometry scans in persons with spinal cord injury. J Clin Densitom. 2022;25(2):252-60.
  4. Indexed at, Google Scholar, Cross Ref

  5. Lobos S, Cooke A, Simonett G. et al. Assessment of bone mineral density at the distal femur and the proximal tibia by dual-energy x-ray absorptiometry in individuals with spinal cord injury: precision of protocol and relation to injury duration. J Clin Densitom. 2018;21(3):338-46.
  6. Indexed at, Google Scholar, Cross Ref

  7. Uebelhart D, Demiaux-Domenech B, Roth M. et al. Bone metabolism in spinal cord injured individuals and in others who have prolonged immobilisation. A review. Spinal Cord. 1995;33(11):669-73.
  8. Indexed at, Google Scholar, Cross Ref

  9. Craven C, Robertson R, McGillivray M. et al. Detection and treatment of sublesional osteoporosis among patients with chronic spinal cord injury proposed paradigms. Top Spinal Cord Inj Rehabil. 2009;14(4):1-22.
  10. Indexed at, Google Scholar, Cross Ref

Get the App