A data-driven approach for evaluating multi-modal therapy in traumatic brain injury.
Ontology highlight
ABSTRACT:
SUBMITTER: Haefeli J
PROVIDER: S-EPMC5311970 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:ObjectivesBig data analytics can potentially benefit the assessment and management of complex neurological conditions by extracting information that is difficult to identify manually. In this study, we evaluated the performance of commonly used supervised machine learning algorithms in the classification of patients with traumatic brain injury (TBI) history from those with stroke history and/or normal EEG.MethodsSupport vector machine (SVM) and K-nearest neighbors (KNN) models were generated with a diverse feature set from Temple EEG Corpus for both two-class classification of patients with TBI history from normal subjects and three-class classification of TBI, stroke and normal subjects.ResultsFor two-class classification, an accuracy of 0.94 was achieved in 10-fold cross validation (CV), and 0.76 in independent validation (IV). For three-class classification, 0.85 and 0.71 accuracy were reached in CV and IV respectively. Overall, linear discriminant analysis (LDA) feature selection and SVM models consistently performed well in both CV and IV and for both two-class and three-class classification. Compared to normal control, both TBI and stroke patients showed an overall reduction in coherence and relative PSD in delta frequency, and an increase in higher frequency (alpha, mu, beta and gamma) power. But stroke patients showed a greater degree of change and had additional global decrease in theta power.ConclusionsOur study suggests that EEG data-driven machine learning can be a useful tool for TBI classification.SignificanceOur study provides preliminary evidence that EEG ML algorithm can potentially provide specificity to separate different neurological conditions.
| S-EPMC9513823 | biostudies-literature
Project description:Traumatic brain injury (TBI) is a complex injury that has a multi-faceted recovery process. The current "gold standard" for classifying severity of TBI symptoms is the Glasgow Outcome Scale (GOSE), a crude measure of overall dysfunction after TBI. Exploratory factor analysis performed on TRACK-TBI Pilot (N = 297) identified candidate multi-variate outcome measures of neuropsychological impairment and cognitive speed and flexibility at 6 months post-TBI that were confirmed in data from the COBRIT study (N = 645) using confirmatory factor analysis. These new outcome measures were used as the dependent variables in an ordinal logistic regression model, using common data elements (CDE) collected in the emergency department as independent variables, including basic demographics, socioeconomic status, medical history, and measures of blood alcohol and blood pressure. We directly compared these prediction models with the GOSE as the 6-month outcome variable and found that in both the TRACK-TBI pilot and COBRIT studies, both neuropsychiatric complications (approx. 36.0% and 22.3% variance explained) and cognitive speed and flexibility (approx. 33.9% and 24.5% variance explained) were better explained by the prediction model, compared with GOSE (approx. 19.9% and 14.4% variance explained), respectively. While differences in overall distributions of impairment between TRACK-TBI pilot and COBRIT exist and should be explored further for applications of these prediction models, we think these multi-variate end-points more accurately characterize patients' functioning at six-months post-TBI. A multi-variate assessment of end-points seems especially important for characterizing TBI outcomes in cases where gross impairment, such as those measured by the GOSE, may be less evident.
| S-EPMC8020558 | biostudies-literature
Project description:[18F]AV-1451 (aka 18F-Flortaucipir, [18F]T807) was developed for positron-emission tomography (PET) imaging of paired helical filaments of hyperphosphorylated tau, which are of interest in a range of neuropathologies, including traumatic brain injury (TBI). Magnetic resonance imaging (MRI) techniques like diffusion tensor imaging (DTI) and resting state functional connectivity assess structural and functional characteristics of the brain, complementing the molecular information that can be obtained by PET. The goal herein was to explore the utility of such multi-modal imaging in a case series based on a population of TBI subjects. This study probes the interrelationship between tau deposition, white matter integrity, and gray matter functional connectivity across the spectrum of TBI. Nineteen subjects (11 controls, five former contact sports athletes, one automotive accident, and two with military-related injury) underwent [18F]AV-1451 PET and magnetic resonance scanning procedures. [18F]AV-1451 distribution volume ratio (DVR) was estimated using the Logan method and the cerebellum as a reference region. Diffusion tractography images and fractional anisotropy (FA) images were generated using diffusion toolkit and FSL. Resting-state functional MRI (fMRI) analysis was based on a graph theory metric, namely weighted degree centrality. TBI subjects showed greater heterogeneity in [18F]AV-1451 DVR when compared with control subjects. In a subset of TBI subjects, areas with high [18F]AV-1451 binding corresponded with increased FA and diminished white matter tract density in DTI. Functional MRI results exhibited an increase in functional connectivity, particularly among local connections, in the areas where tau aggregates were more prevalent. In a case series of a diverse group of TBI subjects, brain regions with elevated tau burden exhibited increased functional connectivity as well as decreased white matter integrity. These findings portray molecular, microstructural, and functional corollaries of TBI that spatially coincide and can be measured in the living human brain using noninvasive neuroimaging techniques.
| S-EPMC6857466 | biostudies-literature
Project description:Frontotemporal dementia in genetic forms is highly heterogeneous and begins many years to prior symptom onset, complicating disease understanding and treatment development. Unifying methods to stage the disease during both the presymptomatic and symptomatic phases are needed for the development of clinical trials outcomes. Here we used the contrastive trajectory inference (cTI), an unsupervised machine learning algorithm that analyzes temporal patterns in high-dimensional large-scale population datasets to obtain individual scores of disease stage. We used cross-sectional MRI data (gray matter density, T1/T2 ratio as a proxy for myelin content, resting-state functional amplitude, gray matter fractional anisotropy, and mean diffusivity) from 383 gene carriers (269 presymptomatic and 115 symptomatic) and a control group of 253 noncarriers in the Genetic Frontotemporal Dementia Initiative. We compared the cTI-obtained disease scores to the estimated years to onset (age-mean age of onset in relatives), clinical, and neuropsychological test scores. The cTI based disease scores were correlated with all clinical and neuropsychological tests (measuring behavioral symptoms, attention, memory, language, and executive functions), with the highest contribution coming from mean diffusivity. Mean cTI scores were higher in the presymptomatic carriers than controls, indicating that the method may capture subtle pre-dementia cerebral changes, although this change was not replicated in a subset of subjects with complete data. This study provides a proof of concept that cTI can identify data-driven disease stages in a heterogeneous sample combining different mutations and disease stages of genetic FTD using only MRI metrics.
| S-EPMC8933323 | biostudies-literature
Project description:Traumatic brain injury (TBI) affects how the brain functions in the short and long term. Resulting patient outcomes across physical, cognitive, and psychological domains are complex and often difficult to predict. Major challenges to developing personalized treatment for TBI include distilling large quantities of complex data and increasing the precision with which patient outcome prediction (prognoses) can be rendered. We developed and applied interpretable machine learning methods to TBI patient data. We show that complex data describing TBI patients' intake characteristics and outcome phenotypes can be distilled to smaller sets of clinically interpretable latent factors. We demonstrate that 19 clusters of TBI outcomes can be predicted from intake data, a ~ 6× improvement in precision over clinical standards. Finally, we show that 36% of the outcome variance across patients can be predicted. These results demonstrate the importance of interpretable machine learning applied to deeply characterized patients for data-driven distillation and precision prognosis.
| S-EPMC10692236 | biostudies-literature
Project description:BACKGROUND:Diffuse traumatic brain injury (TBI) is known to lead to microstructural changes within both white and grey matter detected in vivo with diffusion tensor imaging (DTI). Numerous studies have shown alterations in fractional anisotropy (FA) and mean diffusivity (MD) within prominent white matter tracts, but few have linked these to changes within the grey matter with confirmation via histological assessment. This is especially important as alterations in the grey matter may be predictive of long-term functional deficits. METHODS:A total of 33 male Sprague Dawley rats underwent severe closed-head TBI. Eight animals underwent tensor-based morphometry (TBM) and DTI at baseline (pre-TBI), 24 hours (24 h), 7, 14, and 30 days post-TBI. Immunohistochemical analysis for the detection of ionised calcium-binding adaptor molecule 1 (IBA1) to assess microglia number and percentage of activated cells, ?-amyloid precursor protein (APP) as a marker of axonal injury, and myelin basic protein (MBP) to investigate myelination was performed at each time-point. RESULTS:DTI showed significant alterations in FA and RD in numerous white matter tracts including the corpus callosum, internal and external capsule, and optic tract and in the grey-matter in the cortex, thalamus, and hippocampus, with the most significant effects observed at 14 D post-TBI. TBM confirmed volumetric changes within the hippocampus and thalamus. Changes in DTI were in line with significant axonal injury noted at 24 h post-injury via immunohistochemical analysis of APP, with widespread microglial activation seen within prominent white matter tracts and the grey matter, which persisted to 30 D within the hippocampus and thalamus. Microstructural alterations in MBP+ve fibres were also noted within the hippocampus and thalamus, as well as the cortex. CONCLUSION:This study confirms the widespread effects of diffuse TBI on white matter tracts which could be detected via DTI and extends these findings to key grey matter regions, with a comprehensive investigation of the whole brain. In particular, the hippocampus and thalamus appear to be vulnerable to ongoing pathology post-TBI, with DTI able to detect these alterations supporting the clinical utility in evaluating these regions post-TBI.
| S-EPMC6931220 | biostudies-literature
Project description:Traumatic brain injury (TBI) is a major public health issue. The complexity of TBI has precluded the use of effective therapies. Hyperbaric oxygen therapy (HBOT) has been shown to be neuroprotective in multiple neurological disorders, but its efficacy in the management of TBI remains controversial. This review focuses on HBOT applications within the context of experimental and clinical TBI. We also discuss its potential neuroprotective mechanisms. Early or delayed multiple sessions of low atmospheric pressure HBOT can reduce intracranial pressure, improve mortality, as well as promote neurobehavioral recovery. The complimentary, synergistic actions of HBOT include improved tissue oxygenation and cellular metabolism, anti-apoptotic, and anti-inflammatory mechanisms. Thus HBOT may serve as a promising neuroprotective strategy that when combined with other therapeutic targets for TBI patients which could improve long-term outcomes.
| S-EPMC3231802 | biostudies-other
Project description:Traumatic brain injury is a major economic burden to hospitals in terms of emergency department visits, hospitalizations, and utilization of intensive care units. Current guidelines for the management of severe traumatic brain injuries are primarily supportive, with an emphasis on surveillance (i.e. intracranial pressure) and preventive measures to reduce morbidity and mortality. There are no direct effective therapies available. Over the last fifteen years, pre-clinical studies in regenerative medicine utilizing cell-based therapy have generated enthusiasm as a possible treatment option for traumatic brain injury. In these studies, stem cells and progenitor cells were shown to migrate into the injured brain and proliferate, exerting protective effects through possible cell replacement, gene and protein transfer, and release of anti-inflammatory and growth factors. In this work, we reviewed the pathophysiological mechanisms of traumatic brain injury, the biological rationale for using stem cells and progenitor cells, and the results of clinical trials using cell-based therapy for traumatic brain injury. Although the benefits of cell-based therapy have been clearly demonstrated in pre-clinical studies, some questions remain regarding the biological mechanisms of repair and safety, dose, route and timing of cell delivery, which ultimately will determine its optimal clinical use.
| S-EPMC4500763 | biostudies-literature
Project description:Secondary neurologic decline (ND) after traumatic brain injury (TBI) is independently associated with outcome, but robust predictors of ND are lacking. In this retrospective analysis of consecutive isolated TBI admissions to the R. Adams Cowley Shock Trauma Center between November 2015 and June 2018, we aimed to develop a triage decision support tool to quantify risk for early ND. Three machine learning models based on clinical, physiologic, or combined characteristics from the first hour of hospital resuscitation were created. Among 905 TBI cases, 165 (18%) experienced one or more ND events (130 clinical, 51 neurosurgical, and 54 radiographic) within 48 h of presentation. In the prediction of ND, the clinical plus physiologic data model performed similarly to the physiologic only model, with concordance indices of 0.85 (0.824-0.877) and 0.84 (0.812-0.868), respectively. Both outperformed the clinical only model, which had a concordance index of 0.72 (0.688-0.759). This preliminary work suggests that a data-driven approach utilizing physiologic and basic clinical data from the first hour of resuscitation after TBI has the potential to serve as a decision support tool for clinicians seeking to identify patients at high or low risk for ND.
| S-EPMC9829683 | biostudies-literature
Project description:Standardization and harmonization of data collection in studies on traumatic brain injury (TBI) is of paramount importance for meta-analyses across studies. Nearly 10 years ago, the first set of Common Data Elements for TBI (TBI-CDEs v1) were introduced to achieve these goals. The TBI-CDEs version 2 were developed in 2012 to broaden the approach to all ages, injury severity, and phases of recovery. We aimed to quantify the degree of harmonization of these data elements in three large, prospective multi-center studies conducted within the International Initiative for TBI Research (InTBIR). Data variables of the Collaborative European NeuroTrauma Effectiveness Research in Traumatic Brain Injury (CENTER-TBI; adult and pediatric patients in Europe and Israel), Transforming Research and Clinical Knowledge in Traumatic Brain Injury (TRACK-TBI; adult and pediatric patients in the U.S.), and Approaches and Decisions in Acute Pediatric TBI (ADAPT; international study on severe pediatric TBI) studies were indexed and matched to the second version of the TBI CDEs. We focused on the CDE sub-categories of "Acute Hospitalized" (AH) and "Moderate/Severe TBI: Rehabilitation (Rehab). All "Core" and "Basic" level CDEs were considered. Closely related elements were reduced to one variable to prevent over-representation. Categorical elements and text elements for the same variable were likewise merged to one element for analysis. Following reduction and merging of related elements, 21 Core, 46 Basic AH, and 50 Basic Rehab elements were deemed harmonizable across studies. Gaps in global applicability were identified for four of the TBI CDEs and many of the outcome instruments, which are only available in the English language. Agreements of Core and Basic study CDEs for the AH domain with the TBI CDEs were respectively 81% and 91% for CENTER-TBI, 76% and 93% for TRACK-TBI, and 85% in ADAPT for both domains. For the domain Rehab, agreement with Basic TBI CDEs was 84% for CENTER-TBI, 94% for TRACK-TBI, and 71% for ADAPT. Non-harmonization was largely caused by absence of the elements in the studies. For elements present, the compatibility of coding with TBI CDEs was 90-99%. The degree of harmonization was greatest between CENTER-TBI and TRACK-TBI with 81-87% overlap within the TBI CDE sub-categories. The high degree of harmonization of study variables among these studies demonstrates the importance and utility of common data elements in TBI research. It also confirms the potential for future meta-analyses across these large studies, especially for CENTER TBI and TRACK TBI. The global applicability of the TBI CDEs needs to be improved for them to become a global standard for TBI research. CENTER-TBI, TRACK-TBI, and ADAPT, along with other studies within the InTBIR Initiative, provide a platform to inform further refinement and internationalization for the next version of the TBI CDEs.
| S-EPMC7249452 | biostudies-literature