Decoding accelerometry for classification and prediction of critically ill patients with severe brain injury.

Our goal is to explore quantitative motor features in critically ill patients with severe brain injury (SBI). We hypothesized that computational decoding of these features would yield information on underlying neurological states and outcomes. Using wearable microsensors placed on all extremities, we recorded a median 24.1 (IQR: 22.8-25.1) hours of high-frequency accelerometry data per patient from a prospective cohort (n = 69) admitted to the ICU with SBI. Models were trained using time-, frequency-, and wavelet-domain features and levels of responsiveness and outcome as labels. The two primary tasks were detection of levels of responsiveness, assessed by motor sub-score of the Glasgow Coma Scale (GCSm), and prediction of functional outcome at discharge, measured with the Glasgow Outcome Scale-Extended (GOSE). Detection models achieved significant (AUC: 0.70 [95% CI: 0.53-0.85]) and consistent (observation windows: 12 min-9 h) discrimination of SBI patients capable of purposeful movement (GCSm > 4). Prediction models accurately discriminated patients of upper moderate disability or better (GOSE > 5) with 2-6 h of observation (AUC: 0.82 [95% CI: 0.75-0.90]). Results suggest that time series analysis of motor activity yields clinically relevant insights on underlying functional states and short-term outcomes in patients with SBI.

Validation of the International Classification of Functioning, Disability and Health Core Sets for traumatic brain injury from Australian community patient perspectives.

OBJECTIVE: To examine the validity of the Comprehensive and Brief International Classification of Functioning, Disability and Health (ICF) Core Sets for Traumatic Brain Injury for patients with traumatic brain injury living in the community in Australia. DESIGN: Qualitative methodology using focus groups and individual interviews. PATIENTS: Community-dwelling adult persons with traumatic brain injury. METHODS: Patients sustaining traumatic brain injury with post-traumatic amnesia between September 2009 and August 2013, selected from the Royal Melbourne Hospital Trauma Registry, were invited to participate in the study. Participants were asked structured questions based on the ICF framework. Digital recordings of the discussions were transcribed in full for linking to the ICF categories. RESULTS: Saturation of data was reached after 5 groups involving 21 participants. Participants identified as relevant 77.7% (n = 108/139) and 100% (n = 23/23) of the Comprehensive and Brief ICF Core Sets for traumatic brain injury, respectively. Additional ICF categories identified in 2 or more groups were: b180 "experience of self and time functions"; b250 "taste function"; b265 "touch function"; b530 "weight maintenance function"; b780 "sensation related to muscles and movement"; and d650 "caring for household objects". CONCLUSION: The study found additional ICF categories to consider and supports the use of the ICF Core Sets for traumatic brain injury in Australian adults in the community.

Fall-related emergency department visits involving alcohol among older adults.

PROBLEM: Falls are the leading cause of injury deaths among adults aged 65 years and older. Characteristics of these falls may vary with alcohol use. OBJECTIVE: Describe and compare characteristics of older adult fall-related emergency department (ED) visits with indication of alcohol to visits with no indication. METHODS: Using nationally-representative 2015 National Electronic Injury Surveillance System-All Injury Program data, we compared demographic characteristics for fall-related ED visits by indication of alcohol consumption. Alcohol-indicated ED visits were matched on age group, sex, treatment month, and treatment day to ED visits with no alcohol indication using a 1:4 ratio and injury characteristics (i.e., diagnosis, body part injured, disposition) were compared. RESULTS AND DISCUSSION: Of 38,640 ED records, 906 (1.9%) indicated use of alcohol. Fall-related ED visits among women were less likely to indicate alcohol (1.0%) compared to ED visits among men (3.8%). ED visits indicating alcohol decreased with age from 4.1% for those 65-74 years to 1.5% for those 75-84 and <1% for those 85+. After controlling for age-group, sex, and month and day of treatment, 17.0% of ED visits with no alcohol indication had a traumatic brain injury compared to 34.8% of alcohol-indicated ED visits. Practical applications: Alcohol-indicated fall ED visits resulted in more severe head injury than those that did not indicate alcohol. To determine whether alcohol use should be part of clinical risk assessment for older adult falls, more routinely collected data and detailed information on the amount of alcohol consumed at the time of the fall are needed.

COVID-19 pathways for brain and heart injury in comorbidity patients: A role of medical imaging and artificial intelligence-based COVID severity classification: A review.

Artificial intelligence (AI) has penetrated the field of medicine, particularly the field of radiology. Since its emergence, the highly virulent coronavirus disease 2019 (COVID-19) has infected over 10 million people, leading to over 500,000 deaths as of July 1st, 2020. Since the outbreak began, almost 28,000 articles about COVID-19 have been published (https://pubmed.ncbi.nlm.nih.gov); however, few have explored the role of imaging and artificial intelligence in COVID-19 patients-specifically, those with comorbidities. This paper begins by presenting the four pathways that can lead to heart and brain injuries following a COVID-19 infection. Our survey also offers insights into the role that imaging can play in the treatment of comorbid patients, based on probabilities derived from COVID-19 symptom statistics. Such symptoms include myocardial injury, hypoxia, plaque rupture, arrhythmias, venous thromboembolism, coronary thrombosis, encephalitis, ischemia, inflammation, and lung injury. At its core, this study considers the role of image-based AI, which can be used to characterize the tissues of a COVID-19 patient and classify the severity of their infection. Image-based AI is more important than ever as the pandemic surges and countries worldwide grapple with limited medical resources for detection and diagnosis.

Correlation between optic nerve sheath diameter and Rotterdam computer tomography scoring in pediatric brain injury.

BACKGROUND: Pediatric head trauma is the most common presentation to emergency departments. Increased intracranial pressure (ICP) may lead to secondary brain damage in head trauma and early diagnosis of increased ICP is very important. Measurement of optic nerve sheath diameter (ONSD) is a method that can be used for determining increased ICP. In this study, we aimed to evaluate the relationship between optic nerve sheath diameter (ONSD) and Rotterdam computer tomography scores (RCTS) in pediatric patients for severe head trauma. METHODS: During January 2017-April 2018, medical records and imaging findings of children aged 0-18 years who underwent computed tomography (CT) imaging for head trauma (n=401) and non-traumatic (convulsions, respiratory disorders, headache) (n=255) complaints, totally 656 patient were evaluated retrospectively. Patients' age, sex, presentation and trauma type (high energy-low energy) were identified. Non-traumatic patients with normal cranial CT findings were considered as the control group. CT findings of traumatic brain injury were scored according to Rotterdam criteria. Patients were divided into groups according to their age as follows: 0-3 years, 3-6 years, 6-12 years and 12-18 years. RESULTS: In our study, tomographic reference measurements of the ONSD in pediatric cases were presented according to age. There was a statistically significant difference between ONSD of severe traumatic patients and the control group. Correlation between RCTS and ONSD was determined and age-specific cut-off values of ONSD for severe traumatic scores (score 4-5-6) were presented. CONCLUSION: In our study, reference ONSDs of the pediatric population for CT imaging was indicated. Our study also showed that ONSD measurement is a parameter that can be used in addition to the RCTS to determine the prognosis of the patient in severe head trauma, by reflecting increased intracranial pressure.

Comparison of cranial ultrasound and MRI for detecting BRAIN injury in extremely preterm infants and correlation with neurological outcomes at 1 and 3 years.

This study aimed to investigate the accuracy of different grades of brain injuries on serial and term equivalent age (TEA)-cranial ultrasound imaging (cUS) as compared to TEA magnetic resonance imaging (MRI) in extremely preterm infants < 28 weeks, and determine the predictive value of imaging abnormalities on neurodevelopmental outcome at 1 and 3 years. Seventy-five infants were included in the study. Severe TEA-cUS injury had high positive predictive value-PPV (100%) for predicting severe MRI injury compared to mild to moderate TEA-cUS injury or severe injury on worst cranial ultrasound scan. Absence of moderate to severe injury on TEA cUS or worst serial cUS was a good predictor of a normal MRI (negative predictive values > 93%). Severe grade 3 injuries on TEA-US had high predictive values in predicting abnormal neurodevelopment at both 1 and 3 years of age (PPV 100%). All grades of MRI and worst serial cUS injuries poorly predicted abnormal neurodevelopment at 1 and 3 years. Absence of an injury either on a cranial ultrasound or an MRI did not predict a normal outcome. Multiple logistic regression did not show a significant correlation between imaging injury and neurodevelopmental outcomes.Conclusion: This study demonstrates that TEA cUS can reliably identify severe brain abnormalities that would be seen on MRI imaging and positively predict abnormal neurodevelopment at both 1 and 3 years. Although MRI can pick up more subtle abnormalities that may be missed on cUS, their predictive value on neurodevelopmental impairment is poor. Normal cUS and MRI scan may not exclude abnormal neurodevelopment. Routine TEA-MRI scan provides limited benefit in predicting abnormal neurodevelopment in extremely preterm infants. What is Known: • Preterm neonates are at increased risk of white matter and other brain injuries, which may be associated with adverse neurodevelopmental outcome. • MRI is the most accurate method in detecting white matter injuries. What is New: • TEA-cUS can reliably detect severe brain injuries on MRI, but not mild/moderate lesions as well as abnormal neurodevelopment at 1 and 3 years. • TEA-MRI brain injury is poor in predicting abnormal neurodevelopment at 1 and 3 years and normal cUS or MRI brain injury may not guarantee normal neurodevelopment.

Cortical Response to the Natural Speech Envelope Correlates with Neuroimaging Evidence of Cognition in Severe Brain Injury.

Recent studies identify severely brain-injured patients with limited or no behavioral responses who successfully perform functional magnetic resonance imaging (fMRI) or electroencephalogram (EEG) mental imagery tasks [1-5]. Such tasks are cognitively demanding [1]; accordingly, recent studies support that fMRI command following in brain-injured patients associates with preserved cerebral metabolism and preserved sleep-wake EEG [5, 6]. We investigated the use of an EEG response that tracks the natural speech envelope (NSE) of spoken language [7-22] in healthy controls and brain-injured patients (vegetative state to emergence from minimally conscious state). As audition is typically preserved after brain injury, auditory paradigms may be preferred in searching for covert cognitive function [23-25]. NSE measures are obtained by cross-correlating EEG with the NSE. We compared NSE latencies and amplitudes with and without consideration of fMRI assessments. NSE latencies showed significant and progressive delay across diagnostic categories. Patients who could carry out fMRI-based mental imagery tasks showed no statistically significant difference in NSE latencies relative to healthy controls; this subgroup included patients without behavioral command following. The NSE may stratify patients with severe brain injuries and identify those patients demonstrating "cognitive motor dissociation" (CMD) [26] who show only covert evidence of command following utilizing neuroimaging or electrophysiological methods that demand high levels of cognitive function. Thus, the NSE is a passive measure that may provide a useful screening tool to improve detection of covert cognition with fMRI or other methods and improve stratification of patients with disorders of consciousness in research studies.

Catastrophic Non-Survivable Brain Injury Care-Role 2/3.

A catastrophic brain injury is defined as any brain injury that is expected to result in permanent loss of all brain function above the brain stem level. These clinical recommendations will help stabilize the patient so that they may be safely evacuated from theater. In addition to cardiovascular and hemodynamic goals, special attention must be paid to their endocrine dysfunction and its treatment-specifically steroid, insulin and thyroxin (t4) replacement while evaluating for and treating diabetes insipidus. Determining the futility of care coupled with resource management must also be made at each echelon. Logistical coordination and communication is paramount to expedite these patients to higher levels of care so that there is an increased probability of reuniting them with their family.

Neurosurgery and Medical Management of Severe Head Injury.

Management of the patient with moderate to severe brain injury in any environment can be time consuming and resource intensive. In the austere or hostile environment, the challenges to deliver care to this patient population are magnified. These guidelines have been developed by acknowledging commonly recognized recommendations for neurosurgical and neuro-critical care patients and augmenting those evaluations and interventions based on the experience of neurosurgeons, trauma surgeons, and intensivists who have delivered care during recent coalition conflicts.

Neuroimaging Radiological Interpretation System for Acute Traumatic Brain Injury.

The purpose of the study was to develop an outcome-based NeuroImaging Radiological Interpretation System (NIRIS) for patients with acute traumatic brain injury (TBI) that would standardize the interpretation of noncontrast head computer tomography (CT) scans and consolidate imaging findings into ordinal severity categories that would inform specific patient management actions and that could be used as a clinical decision support tool. We retrospectively identified all patients transported to our emergency department by ambulance or helicopter for whom a trauma alert was triggered per established criteria and who underwent a noncontrast head CT because of suspicion of TBI, between November 2015 and April 2016. Two neuroradiologists reviewed the noncontrast head CTs and assessed the TBI imaging common data elements (CDEs), as defined by the National Institutes of Health (NIH). Using descriptive statistics and receiver operating characteristic curve analyses to identify imaging characteristics and associated thresholds that best distinguished among outcomes, we classified patients into five mutually exclusive categories: 0-discharge from the emergency department; 1-follow-up brain imaging and/or admission; 2-admission to an advanced care unit; 3-neurosurgical procedure; 4-death up to 6 months after TBI. Sensitivity of NIRIS with respect to each patient's true outcome was then evaluated and compared with that of the Marshall and Rotterdam scoring systems for TBI. In our cohort of 542 patients with TBI, NIRIS was developed to predict discharge (182 patients), follow-up brain imaging/admission (187 patients), need for advanced care unit (151 patients), neurosurgical procedures (10 patients), and death (12 patients). NIRIS performed similarly to the Marshall and Rotterdam scoring systems in terms of predicting death. We developed an interpretation system for neuroimaging using the CDEs that informs specific patient management actions and could be used as a clinical decision support tool for patients with TBI. Our NIRIS classification, with evidence-based grouping of the CDEs into actionable categories, will need to be validated in different TBI populations.

Commonalities in epileptogenic processes from different acute brain insults: Do they translate?

The most common forms of acquired epilepsies arise following acute brain insults such as traumatic brain injury, stroke, or central nervous system infections. Treatment is effective for only 60%-70% of patients and remains symptomatic despite decades of effort to develop epilepsy prevention therapies. Recent preclinical efforts are focused on likely primary drivers of epileptogenesis, namely inflammation, neuron loss, plasticity, and circuit reorganization. This review suggests a path to identify neuronal and molecular targets for clinical testing of specific hypotheses about epileptogenesis and its prevention or modification. Acquired human epilepsies with different etiologies share some features with animal models. We identify these commonalities and discuss their relevance to the development of successful epilepsy prevention or disease modification strategies. Risk factors for developing epilepsy that appear common to multiple acute injury etiologies include intracranial bleeding, disruption of the blood-brain barrier, more severe injury, and early seizures within 1 week of injury. In diverse human epilepsies and animal models, seizures appear to propagate within a limbic or thalamocortical/corticocortical network. Common histopathologic features of epilepsy of diverse and mostly focal origin are microglial activation and astrogliosis, heterotopic neurons in the white matter, loss of neurons, and the presence of inflammatory cellular infiltrates. Astrocytes exhibit smaller K+ conductances and lose gap junction coupling in many animal models as well as in sclerotic hippocampi from temporal lobe epilepsy patients. There is increasing evidence that epilepsy can be prevented or aborted in preclinical animal models of acquired epilepsy by interfering with processes that appear common to multiple acute injury etiologies, for example, in post-status epilepticus models of focal epilepsy by transient treatment with a trkB/PLCγ1 inhibitor, isoflurane, or HMGB1 antibodies and by topical administration of adenosine, in the cortical fluid percussion injury model by focal cooling, and in the albumin posttraumatic epilepsy model by losartan. Preclinical studies further highlight the roles of mTOR1 pathways, JAK-STAT3, IL-1R/TLR4 signaling, and other inflammatory pathways in the genesis or modulation of epilepsy after brain injury. The wealth of commonalities, diversity of molecular targets identified preclinically, and likely multidimensional nature of epileptogenesis argue for a combinatorial strategy in prevention therapy. Going forward, the identification of impending epilepsy biomarkers to allow better patient selection, together with better alignment with multisite preclinical trials in animal models, should guide the clinical testing of new hypotheses for epileptogenesis and its prevention.

[Patterns of brain injury in neonatal hypoxic-ischemic encephalopathy on magnetic resonance imaging: recommendations on classification].

Although there are unified criteria for the clinical diagnosis and grading of neonatal hypoxic-ischemic encephalopathy (HIE), clinical features and neuropathological patterns vary considerably among the neonates with HIE due to birth asphyxia in the same classification. The patterns and progression of brain injury in HIE, which is closely associated with long-term neurodevelopment outcomes, can be well shown on magnetic resonance imaging (MRI), but different sequences may lead to different MRI findings at the same time. It is suggested that diffusion-weighted imaging sequence be selected at 2-4 days after birth, and the conventional MRI sequence at 4-8 days. The major patterns of brain injury in HIE on MRI are as follows: injury of the thalamus and basal ganglia and posterior limbs of the internal capsules; watershed injury involving the cortical and subcortical white matter; focal or multifocal minimal white matter injury; extensive whole brain injury. Severe acute birth asphyxia often leads to deep grey matter injury (thalamus and basal ganglia), and the brain stem may also be involved; the pyramidal tract is the most susceptible white matter fiber tract; repetitive or intermittent hypoxic-ischemic insults, with inflammation or hypoglycemia, usually cause injuries in the watershed area and deep white matter. It is worth noting that sometimes the pattern of brain injury among those described above cannot be determined exactly, but rather a predominant one is identified; not all cases of HIE have characteristic MRI findings.

Rhythmic EEG patterns in extremely preterm infants: Classification and association with brain injury and outcome.

OBJECTIVE: Classify rhythmic EEG patterns in extremely preterm infants and relate these to brain injury and outcome. METHODS: Retrospective analysis of 77 infants born <28 weeks gestational age (GA) who had a 2-channel EEG during the first 72 h after birth. Patterns detected by the BrainZ seizure detection algorithm were categorized: ictal discharges, periodic epileptiform discharges (PEDs) and other waveforms. Brain injury was assessed with sequential cranial ultrasound (cUS) and MRI at term-equivalent age. Neurodevelopmental outcome was assessed with the BSITD-III (2 years) and WPPSI-III-NL (5 years). RESULTS: Rhythmic patterns were observed in 62.3% (ictal 1.3%, PEDs 44%, other waveforms 86.3%) with multiple patterns in 36.4%. Ictal discharges were only observed in one and excluded from further analyses. The EEG location of the other waveforms (p<0.05), but not PEDs (p=0.238), was significantly associated with head position. No relation was found between the median total duration of each pattern and injury on cUS and MRI or cognition at 2 and 5 years. CONCLUSIONS: Clear ictal discharges are rare in extremely preterm infants. PEDs are common but their significance is unclear. Rhythmic waveforms related to head position are likely artefacts. SIGNIFICANCE: Rhythmic EEG patterns may have a different significance in extremely preterm infants.

Not every trauma patient with a radiographic head injury requires transfer for neurosurgical evaluation: Application of the brain injury guidelines to patients transferred to a level 1 trauma center.

BACKGROUND: Patients with radiographically-identified traumatic brain injury are often transferred to our regional trauma center for neurosurgical evaluation, yet few injuries require neurosurgical intervention. Transfer is costly, inconvenient, and potentially risky in inclement weather. We propose that previously-published brain injury guidelines (BIG)1 can help to determine which patients could avoid mandatory transfer. METHODS: Retrospective chart review of patients transferred between January 2012 and December 2013 was performed. Patients were classified as having minor (BIG 1), moderate (BIG 2), or severe (BIG 3) head injuries based on previously-published guidelines. Patient characteristics and outcomes were compared. RESULTS: No BIG 1 patients deteriorated or required surgical intervention. One BIG 2 patient required a non-emergent operation and another was readmitted with a worsened injury. In the BIG 3 group, 11.9% required neurosurgical procedures and 20% died. CONCLUSIONS: The BIG classification can help stratify patients for whom transfer is considered.

The First Six Years of Building and Implementing a Return-to-Work Service for Patients with Acquired Brain Injury. The Rapid-Return-to-Work-Cohort-Study.

Background and objective Despite large activity worldwide in building and implementing new return-to-work (RTW) services, few studies have focused on how such implementation processes develop. The aim of this study was to examine the development in patient and service characteristics the first six years of implementing a RTW service for persons with acquired brain injury (ABI). Methods The study was designed as a cohort study (n=189). Data were collected by questionnaires, filled out by the service providers. The material was divided into, and analyzed with, two implementation phases. Non-parametrical statistical methods and hierarchical regression analyses were applied on the material. Results The number of patients increased significantly, and the patient group became more homogeneous. Both the duration of the service, and the number of consultations and group session days were significantly reduced. Conclusion The patient group became more homogenous, but also significantly larger during the first six years of building the RTW service. At the same time, the duration of the service decreased. This study therefore questions if there is a lack of consensus on the intensity of work rehabilitation for this group.

Intimate Partner Violence and Traumatic Brain Injury: State of the Science and Next Steps.

Women who receive traumatic brain injuries (TBI) from intimate partner violence (IPV) are gaining attention; however, research studies are lacking in this area. A review of literature conducted on TBI from IPV found prevalence of 60% to 92% of abused women obtaining a TBI directly correlated with IPV. Adverse overlapping health outcomes are associated with both TBI and IPV. Genetic predisposition and epigenetic changes can occur after TBI and add increased vulnerability to receiving and inflicting a TBI. Health care providers and community health workers need awareness of the link between IPV/TBI to provide appropriate treatment and improve the health of women and families.

Computerized "Learn-As-You-Go" classification of traumatic brain injuries using NEISS narrative data.

One important routine task in injury research is to effectively classify injury circumstances into user-defined categories when using narrative text. However, traditional manual processes can be time consuming, and existing batch learning systems can be difficult to utilize by novice users. This study evaluates a "Learn-As-You-Go" machine-learning program. When using this program, the user trains classification models and interactively checks on accuracy until a desired threshold is reached. We examined the narrative text of traumatic brain injuries (TBIs) in the National Electronic Injury Surveillance System (NEISS) and classified TBIs into sport and non-sport categories. Our results suggest that the DUALIST "Learn-As-You-Go" program, which features a user-friendly online interface, is effective in injury narrative classification. In our study, the time frame to classify tens of thousands of narratives was reduced from a few days to minutes after approximately sixty minutes of training.