Use of Support Vector Machines Approach via ComBat Harmonized Diffusion Tensor Imaging for the Diagnosis and Prognosis of Mild Traumatic Brain Injury: A CENTER-TBI Study

Magnetic resonance imaging in traumatic brain injury: a survey of clinical practitioners' experiences and views on current practice and obstacles

INTRODUCTION

Magnetic resonance imaging (MRI) has revolutionized our capacity to examine brain alterations in traumatic brain injury (TBI). However, little is known about the level of implementation of MRI techniques in clinical practice in TBI and associated obstacles.

METHODS

A diverse set of health professionals completed 19 multiple choice and free text survey questions.

RESULTS

Of the 81 respondents, 73.4% reported that they acquire/order MRI scans in TBI patients, and 66% indicated they would prefer MRI be more often used with this cohort. The greatest impediment for MRI usage was scanner availability (57.1%). Less than half of respondents (42.1%) indicated that they perform advanced MRI analysis. Factors such as dedicated experts within the team (44.4%) and user-friendly MRI analysis tools (40.7%), were listed as potentially helpful to implement advanced MRI analyses in clinical practice.

CONCLUSION

Results suggest a wide variability in the purpose, timing, and composition of the scanning protocol of clinical MRI after TBI. Three recommendations are described to broaden implementation of MRI in clinical practice in TBI: 1) development of a standardized multimodal MRI protocol; 2) future directions for the use of advanced MRI analyses; 3) use of low-field MRI to overcome technical/practical issues with high-field MRI.

Potential Applications and Ethical Considerations for Artificial Intelligence in Traumatic Brain Injury Management

Artificial intelligence (AI) systems have emerged as promising tools for rapidly identifying patterns in large amounts of healthcare data to help guide clinical decision making, as well as to assist with medical education and the planning of research studies. Accumulating evidence suggests AI techniques may be particularly useful for aiding the diagnosis and clinical management of traumatic brain injury (TBI)-a considerably heterogeneous neurologic condition that can be challenging to detect and treat. However, important methodological and ethical concerns with the use of AI in medicine necessitate close monitoring and regulation of these techniques as advancements continue. The purpose of this narrative review is to provide an overview of common AI techniques in medical research and describe recent studies on the possible clinical applications of AI in the context of TBI. Finally, the review describes the ethical challenges with the use of AI in medicine, as well as guidelines from the White House, the Department of Defense (DOD), the National Academies of Sciences, Engineering, and Medicine (NASEM), and other organizations on the appropriate uses of AI in research.

Imaging Findings in Acute Traumatic Brain Injury: a National Institute of Neurological Disorders and Stroke Common Data Element-Based Pictorial Review and Analysis of Over 4000 Admission Brain Computed Tomography Scans from the Collaborative European NeuroTrauma Effectiveness Research in Traumatic Brain Injury (CENTER-TBI) Study

In 2010, the National Institute of Neurological Disorders and Stroke (NINDS) created a set of common data elements (CDEs) to help standardize the assessment and reporting of imaging findings in traumatic brain injury (TBI). However, as opposed to other standardized radiology reporting systems, a visual overview and data to support the proposed standardized lexicon are lacking. We used over 4000 admission computed tomography (CT) scans of patients with TBI from the Collaborative European NeuroTrauma Effectiveness Research in Traumatic Brain Injury (CENTER-TBI) study to develop an extensive pictorial overview of the NINDS TBI CDEs, with visual examples and background information on individual pathoanatomical lesion types, up to the level of supplemental and emerging information (e.g., location and estimated volumes). We documented the frequency of lesion occurrence, aiming to quantify the relative importance of different CDEs for characterizing TBI, and performed a critical appraisal of our experience with the intent to inform updating of the CDEs. In addition, we investigated the co-occurrence and clustering of lesion types and the distribution of six CT classification systems. The median age of the 4087 patients in our dataset was 50 years (interquartile range, 29-66; range, 0-96), including 238 patients under 18 years old (5.8%). Traumatic subarachnoid hemorrhage (45.3%), skull fractures (37.4%), contusions (31.3%), and acute subdural hematoma (28.9%) were the most frequently occurring CT findings in acute TBI. The ranking of these lesions was the same in patients with mild TBI (baseline Glasgow Coma Scale [GCS] score 13-15) compared with those with moderate-severe TBI (baseline GCS score 3-12), but the frequency of occurrence was up to three times higher in moderate-severe TBI. In most TBI patients with CT abnormalities, there was co-occurrence and clustering of different lesion types, with significant differences between mild and moderate-severe TBI patients. More specifically, lesion patterns were more complex in moderate-severe TBI patients, with more co-existing lesions and more frequent signs of mass effect. These patients also had higher and more heterogeneous CT score distributions, associated with worse predicted outcomes. The critical appraisal of the NINDS CDEs was highly positive, but revealed that full assessment can be time consuming, that some CDEs had very low frequencies, and identified a few redundancies and ambiguity in some definitions. Whilst primarily developed for research, implementation of CDE templates for use in clinical practice is advocated, but this will require development of an abbreviated version. In conclusion, with this study, we provide an educational resource for clinicians and researchers to help assess, characterize, and report the vast and complex spectrum of imaging findings in patients with TBI. Our data provides a comprehensive overview of the contemporary landscape of TBI imaging pathology in Europe, and the findings can serve as empirical evidence for updating the current NINDS radiologic CDEs to version 3.0.

Serum lipidome associates with neuroimaging features in patients with traumatic brain injury

Acute traumatic brain injury (TBI) is associated with substantial abnormalities in lipid biology, including changes in the structural lipids that are present in the myelin in the brain. We investigated the relationship between traumatic microstructural changes in white matter from magnetic resonance imaging (MRI) and quantitative lipidomic changes from blood serum. The study cohort included 103 patients from the Collaborative European NeuroTrauma Effectiveness Research in TBI (CENTER-TBI) study. Diffusion tensor fitting generated fractional anisotropy (FA) and mean diffusivity (MD) maps for the MRI scans while ultra-high-performance liquid chromatography quadrupole time-of-flight mass spectrometry was applied to analyze the lipidome. Increasing severity of TBI was associated with higher MD and lower FA values, which scaled with different lipidomic signatures. There appears to be consistent patterns of lipid changes associating with the specific microstructure changes in the CNS white matter, but also regional specificity, suggesting that blood-based lipidomics may provide an insight into the underlying pathophysiology of TBI.

Longitudinal Associations Between Persistent Post-Concussion Symptoms and Blood Biomarkers of Inflammation and CNS-Injury After Mild Traumatic Brain Injury

The aim of our study was to investigate the biological underpinnings of persistent post-concussion symptoms (PPCS) at 3 months following mild traumatic brain injury (mTBI). Patients (n = 192, age 16-60 years) with mTBI, defined as Glasgow Coma Scale (GCS) score between 13 and 15, loss of consciousness (LOC) <30 min, and post-traumatic amnesia (PTA) <24 h were included. Blood samples were collected at admission (within 72 h), 2 weeks, and 3 months. Concentrations of blood biomarkers associated with central nervous system (CNS) damage (glial fibrillary acidic protein [GFAP], neurofilament light [NFL], and tau) and inflammation (interferon gamma [IFNγ], interleukin [IL]-8, eotaxin, macrophage inflammatory protein-1-beta [MIP]-1β, monocyte chemoattractant protein [MCP]-1, interferon-gamma-inducible protein [IP]-10, IL-17A, IL-9, tumor necrosis factor [TNF], basic fibroblast growth factor [FGF]-basic platelet-derived growth factor [PDGF], and IL-1 receptor antagonist [IL-1ra]) were obtained. Demographic and injury-related factors investigated were age, sex, GCS score, LOC, PTA duration, traumatic intracranial finding on magnetic resonance imaging (MRI; within 72 h), and extracranial injuries. Delta values, that is, time-point differences in biomarker concentrations between 2 weeks minus admission and 3 months minus admission, were also calculated. PPCS was assessed with the British Columbia Post-Concussion Symptom Inventory (BC-PSI). In single variable analyses, longer PTA duration and a higher proportion of intracranial findings on MRI were found in the PPCS group, but no single biomarker differentiated those with PPCS from those without. In multi-variable models, female sex, longer PTA duration, MRI findings, and lower GCS scores were associated with increased risk of PPCS. Inflammation markers, but not GFAP, NFL, or tau, were associated with PPCS. At admission, higher concentrations of IL-8 and IL-9 and lower concentrations of TNF, IL-17a, and MCP-1 were associated with greater likelihood of PPCS; at 2 weeks, higher IL-8 and lower IFNγ were associated with PPCS; at 3 months, higher PDGF was associated with PPCS. Higher delta values of PDGF, IL-17A, and FGF-basic at 2 weeks compared with admission, MCP-1 at 3 months compared with admission, and TNF at 2 weeks and 3 months compared with admission were associated with greater likelihood of PPCS. Higher IL-9 delta values at both time-point comparisons were negatively associated with PPCS. Discriminability of individual CNS-injury and inflammation biomarkers for PPCS was around chance level, whereas the optimal combination of biomarkers yielded areas under the curve (AUCs) between 0.62 and 0.73. We demonstrate a role of biological factors on PPCS, including both positive and negative effects of inflammation biomarkers that differed based on sampling time-point after mTBI. PPCS was associated more with acute inflammatory processes, rather than ongoing inflammation or CNS-injury biomarkers. However, the modest discriminative ability of the models suggests other factors are more important in the development of PPCS.

Fluid biomarkers and neuroimaging in mild traumatic brain injury: current uses and potential future directions for clinical use in emergency medicine

Mild traumatic brain injury is a common presentation to the emergency department, with current management often focusing on determining whether a patient requires a CT head scan and/or neurosurgical intervention. There is a growing appreciation that approximately 20%-40% of patients, including those with a negative (normal) CT, will develop ongoing symptoms for months to years, often termed post-concussion syndrome. Owing to the requirement for improved diagnostic and prognostic mechanisms, there has been increasing evidence concerning the utility of both imaging and blood biomarkers.Blood biomarkers offer the potential to better risk stratify patients for requirement of neuroimaging than current clinical decisions rules. However, improved assessment of the clinical utility is required prior to wide adoption. MRI, using clinical sequences and advanced quantitative methods, can detect lesions not visible on CT in up to 30% of patients that may explain, at least in part, some of the ongoing problems. The ability of an acute biomarker (be it imaging, blood or other) to highlight those patients at greater risk of ongoing deficits would allow for greater personalisation of follow-up care and resource allocation.We discuss here both the current evidence and the future potential clinical usage of blood biomarkers and advanced MRI to improve diagnostic pathways and outcome prediction following mild traumatic brain injury.