scholarly journals Machine Learning Classification of Mild Traumatic Brain Injury Using Whole-Brain Functional Activity: A Radiomics Analysis

2021 ◽  
Vol 2021 ◽  
pp. 1-7
Author(s):  
Xiaoping Luo ◽  
Dezhao Lin ◽  
Shengwei Xia ◽  
Dongyu Wang ◽  
Xinmang Weng ◽  
...  

Objectives. To investigate the classification performance of support vector machine in mild traumatic brain injury (mTBI) from normal controls. Methods. Twenty-four mTBI patients (15 males and 9 females; mean age, 38.88 ± 13.33 years) and 24 age and sex-matched normal controls (13 males and 11 females; mean age, 40.46 ± 11.4 years) underwent resting-state functional MRI examination. Seven imaging parameters, including amplitude of low-frequency fluctuation (ALFF), fractional amplitude of low-frequency fluctuation (fALFF), regional homogeneity (ReHo), degree centrality (DC), voxel-mirrored homotopic connectivity (VMHC), long-range functional connectivity density (FCD), and short-range FCD, were entered into the classification model to distinguish the mTBI from normal controls. Results. The ability for any single imaging parameters to distinguish the two groups is lower than multiparameter combinations. The combination of ALFF, fALFF, DC, VMHC, and short-range FCD showed the best classification performance for distinguishing the two groups with optimal AUC value of 0.778, accuracy rate of 81.11%, sensitivity of 88%, and specificity of 75%. The brain regions with the highest contributions to this classification mainly include bilateral cerebellum, left orbitofrontal cortex, left cuneus, left temporal pole, right inferior occipital cortex, bilateral parietal lobe, and left supplementary motor area. Conclusions. Multiparameter combinations could improve the classification performance of mTBI from normal controls by using the brain regions associated with emotion and cognition.

2014 ◽  
Vol 2014 ◽  
pp. 1-4 ◽  
Author(s):  
Yongkang Liu ◽  
Tianyao Wang ◽  
Xiao Chen ◽  
Jianhua Zhang ◽  
Guoxing Zhou ◽  
...  

Purpose. Detecting brain regions characterizing mild traumatic brain injury (mTBI) by combining Tract-Based Spatial Statistics (TBSS) and Graphical-model-based Multivariate Analysis (GAMMA).Materials and Methods. This study included 39 mTBI patients and 28 normal controls. Local research ethics committee approved this prospective study. Diffusion-tensor imaging was performed in mTBI patients within 7 days of injury. Skeletonized fractional anisotropy (FA) maps were generated by using TBSS. Brain regions characterizing mTBI were detected by GAMMA.Results. Two clusters of lower frontal white matter FA were present in mTBI patients. We constructed classifiers based on FA values in these two clusters to differentiate mTBI and controls. The mean accuracy, sensitivity, and specificity, across five different classifiers, were 0.80, 0.94, and 0.61, respectively.Conclusions. Combining TBSS and GAMMA can detect neuroimaging biomarkers characterizing mTBI.


2018 ◽  
Vol 120 (3) ◽  
pp. 1318-1322 ◽  
Author(s):  
Alia L. Yasen ◽  
Jolinda Smith ◽  
Anita D. Christie

Animal models of mild traumatic brain injury (mTBI) suggest that metabolic changes in the brain occur immediately after a mechanical injury to the head. Proton magnetic resonance spectroscopy (1H-MRS) can be used to determine relative concentrations of metabolites in vivo in the human brain. The purpose of this study was to determine concentrations of glutamate and GABA in the brain acutely after mTBI and throughout 2 mo of recovery. Concentrations of glutamate and GABA were obtained using 1H-MRS in nine individuals who had suffered an mTBI and nine control individuals in two brain regions of interest: the primary motor cortex (M1), and the dorsolateral prefrontal cortex (DLPFC), and at three different time points postinjury: 72 h, 2 wk, and 2 mo postinjury. There were no differences between groups in concentrations of glutamate or GABA, or the ratio of glutamate to GABA, in M1. In the DLPFC, glutamate concentration was lower in the mTBI group compared with controls at 72 h postinjury (d = 1.02), and GABA concentration was lower in the mTBI group at 72 h and 2 wk postinjury (d = 0.81 and d = 1.21, respectively). The ratio of glutamate to GABA in the DLPFC was higher in the mTBI group at 2 wk postinjury (d = 1.63). These results suggest that changes in glutamate and GABA concentrations in the brain may be region-specific and may depend on the amount of time that has elapsed postinjury. NEW & NOTEWORTHY To our knowledge, this is the first study to examine neurotransmitter concentrations in vivo at multiple time points throughout recovery from mild traumatic brain injury in humans.


2018 ◽  
pp. 110-119

Primary Objectives: By extending the scope of knowledge of the primary care optometrist, the brain injury population will have expanded access to entry level neurooptometric care by optometric providers who have a basic understanding of their neurovisual problems, be able to provide some treatment and know when to refer to their colleagues who have advanced training in neuro-optometric rehabilitation.


2021 ◽  
Vol 6 (1) ◽  
pp. e000717
Author(s):  
Panu Teeratakulpisarn ◽  
Phati Angkasith ◽  
Thanakorn Wannakul ◽  
Parichat Tanmit ◽  
Supatcha Prasertcharoensuk ◽  
...  

BackgroundAlthough there are eight factors known to indicate a high risk of intracranial hemorrhage (ICH) in mild traumatic brain injury (TBI), identification of the strongest of these factors may optimize the utility of brain CT in clinical practice. This study aimed to evaluate the predictors of ICH based on baseline characteristics/mode of injury, indications for brain CT, and a combination of both to determine the strongest indicator.MethodsThis was a descriptive, retrospective, analytical study. The inclusion criteria were diagnosis of mild TBI, high risk of ICH, and having undergone a CT scan of the brain. The outcome of the study was any type of ICH. Stepwise logistic regression analysis was used to find the strongest predictors according to three models: (1) injury pattern and baseline characteristics, (2) indications for CT scan of the brain, and (3) a combination of models 1 and 2.ResultsThere were 100 patients determined to be at risk of ICH based on indications for CT of the brain in patients with acute head injury. Of these, 24 (24.00%) had ICH. Model 1 found that injury due to motor vehicle crash was a significant predictor of ICH, with an adjusted OR (95% CI) of 11.53 (3.05 to 43.58). Models 2 and 3 showed Glasgow Coma Scale (GCS) score of 13 to 14 after 2 hours of observation and open skull or base of skull fracture to be independent predictors, with adjusted OR (95% CI) of 11.77 (1.32 to 104.96) and 5.88 (1.08 to 31.99) according to model 2.DiscussionOpen skull or base of skull fracture and GCS score of 13 to 14 after 2 hours of observation were the two strongest predictors of ICH in mild TBI.Level of evidenceIII.


2021 ◽  
Vol 18 (1) ◽  
Author(s):  
Huazhen Chen ◽  
Karl Kevala ◽  
Elma Aflaki ◽  
Juan Marugan ◽  
Hee-Yong Kim

Abstract Background Repetitive mild traumatic brain injury (mTBI) can result in chronic visual dysfunction. G-protein receptor 110 (GPR110, ADGRF1) is the target receptor of N-docosahexaenoylethanolamine (synaptamide) mediating the anti-neuroinflammatory function of synaptamide. In this study, we evaluated the effect of an endogenous and a synthetic ligand of GPR110, synaptamide and (4Z,7Z,10Z,13Z,16Z,19Z)-N-(2-hydroxy-2-methylpropyl) docosa-4,7,10,13,16,19-hexaenamide (dimethylsynaptamide, A8), on the mTBI-induced long-term optic tract histopathology and visual dysfunction using Closed-Head Impact Model of Engineered Rotational Acceleration (CHIMERA), a clinically relevant model of mTBI. Methods The brain injury in wild-type (WT) and GPR110 knockout (KO) mice was induced by CHIMERA applied daily for 3 days, and GPR110 ligands were intraperitoneally injected immediately following each impact. The expression of GPR110 and proinflammatory mediator tumor necrosis factor (TNF) in the brain was measured by using real-time quantitative reverse transcription polymerase chain reaction (qRT-PCR) in an acute phase. Chronic inflammatory responses in the optic tract and visual dysfunction were assessed by immunostaining for Iba-1 and GFAP and visual evoked potential (VEP), respectively. The effect of GPR110 ligands in vitro was evaluated by the cyclic adenosine monophosphate (cAMP) production in primary microglia isolated from adult WT or KO mouse brains. Results CHIMERA injury acutely upregulated the GPR110 and TNF gene level in mouse brain. Repetitive CHIMERA (rCHIMERA) increased the GFAP and Iba-1 immunostaining of glia cells and silver staining of degenerating axons in the optic tract with significant reduction of N1 amplitude of visual evoked potential at up to 3.5 months after injury. Both GPR110 ligands dose- and GPR110-dependently increased cAMP in cultured primary microglia with A8, a ligand with improved stability, being more effective than synaptamide. Intraperitoneal injection of A8 at 1 mg/kg or synaptamide at 5 mg/kg significantly reduced the acute expression of TNF mRNA in the brain and ameliorated chronic optic tract microgliosis, astrogliosis, and axonal degeneration as well as visual deficit caused by injury in WT but not in GPR110 KO mice. Conclusion Our data demonstrate that ligand-induced activation of the GPR110/cAMP system upregulated after injury ameliorates the long-term optic tract histopathology and visual impairment caused by rCHIMERA. Based on the anti-inflammatory nature of GPR110 activation, we suggest that GPR110 ligands may have therapeutic potential for chronic visual dysfunction associated with mTBI.


2020 ◽  
Vol 14 ◽  
Author(s):  
Francesca Buhagiar ◽  
Melinda Fitzgerald ◽  
Jason Bell ◽  
Fiona Allanson ◽  
Carmela Pestell

Background: Mild traumatic brain injury (mTBI) results from an external force to the head or body causing neurophysiological changes within the brain. The number and severity of symptoms can vary, with some individuals experiencing rapid recovery, and others having persistent symptoms for months to years, impacting their quality of life. Current rehabilitation is limited in its ability to treat persistent symptoms and novel approaches are being sought to improve outcomes following mTBI. Neuromodulation is one technique used to encourage adaptive neuroplasticity within the brain.Objective: To systematically review the literature on the efficacy of neuromodulation in the mTBI population.Method: A systematic review was conducted using Medline, Embase, PsycINFO, PsycARTICLES and EBM Review. Preferred Reporting Items for Systematic Reviews and the Synthesis Without Meta-analysis reporting guidelines were used and a narrative review of the selected studies was completed. Fourteen articles fulfilled the inclusion criteria which were published in English, investigating an adult sample and using a pre- and post-intervention design. Studies were excluded if they included non-mild TBI severities, pediatric or older adult populations.Results: Thirteen of fourteen studies reported positive reductions in mTBI symptomatology following neuromodulation. Specifically, improvements were reported in post-concussion symptom ratings, headaches, dizziness, depression, anxiety, sleep disturbance, general disability, cognition, return to work and quality of life. Normalization of working memory activation patterns, vestibular field potentials, hemodynamics of the dorsolateral prefrontal cortex and excessive delta wave activity were also seen. The studies reviewed had several methodological limitations including small, heterogenous samples and varied intervention protocols, limiting generalisability. Further research is required to understand the context in which neuromodulation may be beneficial.Conclusions: While these positive effects are observed, limitations included unequal representation of neuromodulation modalities in the literature, and lack of literature describing the efficacy of neuromodulation on the development or duration of persistent mTBI symptoms. Better clarity regarding neuromodulation efficacy could have a significant impact on mTBI patients, researchers, clinicians, and policy makers, facilitating a more productive post-mTBI population. Despite the limitations, the literature indicates that neuromodulation warrants further investigation. PROSPERO registration number: CRD42020161279.


Author(s):  
Mari A. Allison ◽  
Yun Seok Kang ◽  
Matthew R. Maltese ◽  
John H. Bolte ◽  
Kristy B. Arbogast

Recent studies have shown that mild traumatic brain injury (mTBI) can have long-term neurological consequences and may cause permanent damage to the brain [1,2]. Given estimates that millions of these injuries occur each year [3], this knowledge has created a demand for countermeasures to prevent mTBI. In order to create countermeasures, the biomechanical inputs leading to mTBI, which are still a matter of debate, must be better understood in both children and adults.


Biofeedback ◽  
2009 ◽  
Vol 37 (3) ◽  
pp. 108-111
Author(s):  
Jay Gunkelman

Abstract Mild traumatic brain injury is often missed in the course of treating other injuries. This failure to identify the brain injury can be critically important, even life threatening. This report shows one such case in which the brain injury was overlooked, possibly because of the differential effect of age on the severity of the damage incurred from what appeared to be a mild trauma. Distant to the time of the injury, deficits in speech fluency and word finding led the individual to seek further evaluation, and imaging studies revealed a large subdural hematoma. CT scan images are included.


2015 ◽  
Vol 30 (1) ◽  
pp. 21-28 ◽  
Author(s):  
David X. Cifu ◽  
Joanna R. Wares ◽  
Kathy W. Hoke ◽  
Paul A. Wetzel ◽  
George Gitchel ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document