Browse the latest research summaries in the field of bioinformatics for spinal cord injury patients and caregivers.
Showing 111-120 of 334 results
Diagnostics, 2024 • August 30, 2024
This prospective study evaluates a large variety of HHUS devices in a comprehensive head-to-head comparison by several experts. The primary goal is to make a direct comparison of B-image quality, hand...
KEY FINDING: Vscan Air and SonoEye Chison achieved the best overall ratings, differing significantly from the other devices (p < 0.01).
Frontiers in Neurology, 2024 • August 30, 2024
This study aimed to identify shared molecular mechanisms between spinal cord injury (SCI) and sarcopenia through comprehensive genomics analysis, focusing on potential biomarkers for diagnosis and pro...
KEY FINDING: Three hub genes (DCN, FSTL1, and COL12A1) were identified as significantly altered in sarcopenic SCI patients both before and after rehabilitation training.
Biomedicines, 2024 • October 21, 2024
This systematic review aimed to investigate how AI tools are revolutionizing the diagnosis and treatment of neurological disorders, highlighting their transformative impact on neurorehabilitation stra...
KEY FINDING: AI-based devices, including those with EMG-based robotic hands, have demonstrated significant improvements in upper limb motor function with a reduction of spasticity in stroke patients, reporting long-lasting results.
J. Clin. Med., 2024 • November 25, 2024
This study uses artificial neural networks to predict rehabilitation outcomes in spinal cord injury patients, focusing on the impact of psychological variables. The model considers clinical and demogr...
KEY FINDING: Psychological factors accounted for 36.3% of the total predictive weight for functional outcomes in SCI patients.
Korean J Neurotrauma, 2024 • December 24, 2024
AI technology, especially machine learning, is revolutionizing the management of spinal cord injuries by enhancing diagnosis, treatment, prognosis, and rehabilitation. Deep learning models improve dia...
KEY FINDING: AI improves diagnostic accuracy by identifying subtle lesions or fiber tract disruptions often missed by human radiologists and integrates multimodal data for comprehensive diagnosis.
Scientific Reports, 2025 • January 13, 2025
This study explores the protective effect of prior exercise against neuropathic pain (NP) in rats by examining protein expression changes in the spinal dorsal horn using proteomic analysis. The findin...
KEY FINDING: Prior exercise significantly increased the mechanical withdrawal threshold (MWT) and thermal withdrawal latency (TWL) in rats with CCI, indicating a reduction in pain sensitivity.
Genome Medicine, 2025 • January 24, 2025
The study investigates the molecular mechanisms behind resistance exercise-induced recovery in incomplete SCI patients and in mice. Multi-omics analyses reveal that resistance exercise modulates the c...
KEY FINDING: Resistance exercise, especially isotonic exercise, improves muscle strength, walking ability, and balance in individuals with incomplete SCI.
PLOS ONE, 2025 • February 27, 2025
This study investigated the role of anoikis-related genes in neuropathic pain (NP), particularly in lumbar disc herniation (LDH). Machine learning algorithms identified six key genes (HGF, MMP13, ABL1...
KEY FINDING: Six key anoikis-related genes (HGF, MMP13, ABL1, ELANE, FASN, and LINC00324) were identified as having diagnostic value for NP.
Scientific Reports, 2025 • March 13, 2025
This study developed a combined radiomics and clinical model to predict the prognosis of cSCI patients six months post-injury. The model integrates radiomic features extracted using Pyradiomics and Re...
KEY FINDING: The SVM classifier achieved the highest AUC of 1.000 in the training set and 0.915 in the testing set for radiomics models.
Arch Phys Med Rehabil, 2022 • April 1, 2022
This study aimed to determine if functional ambulation measures could be accurately classified using clinical measures, demographics, personal factors, and limb accelerations during sleep in individua...
KEY FINDING: Combining limb accelerations (LA), clinical data, and demographic information resulted in the highest accuracy in classifying functional ambulation outcomes.