Utility of serum chemokine-like factor 1 as a biomarker of severity and prognosis after severe traumatic brain injury: A prospective observational study.

BACKGROUND: Chemokine-like factor 1 (CKLF1) may be involved in the inflammatory response and secondary brain injury after severe traumatic brain injury (sTBI). We determined serum CKLF1 levels of sTBI patients to further investigate the correlation of CKLF1 levels with disease severity, functional prognosis, and 180-day mortality of sTBI. METHODS: Serum CKLF1 levels were measured at admission in 119 sTBI patients and at entry into study in 119 healthy controls. Serum CKLF levels of 50 patients were also quantified at days 1-3, 5, and 7 after admission. Glasgow coma scale (GCS) scores and Rotterdam computerized tomography (CT) classification were utilized to assess disease severity. Extended Glasgow outcome scale (GOSE) scores were recorded to evaluate function prognosis at 180 days after sTBI. Relations of serum CKLF1 levels to 180-day poor prognosis (GOSE scores of 1-4) and 180-day mortality were analyzed using univariate analysis, followed by multivariate analysis. Receiver-operating characteristic (ROC) curve was built to investigate prognostic predictive capability. RESULTS: Serum CKLF1 levels of sTBI patients increased at admission, peaked at day 2, and then gradually decreased; they were significantly higher during the 7 days after sTBI than in healthy controls. Differences of areas under ROC curve (areas under the curve [AUCs]) were not significant among the six time points. Multivariate analysis showed that serum CKLF1 levels were independently correlated with GCS scores, Rotterdam CT classification, and GOSE scores. Serum CKLF1 levels were significantly higher in non-survivors than in survivors and in poor prognosis patients than in good prognosis patients. Serum CKLF1 levels independently predicted 180-day poor prognosis and 180-day mortality, and had high 180-day prognosis and mortality predictive abilities, and their AUCs were similar to those of GCS scores and Rotterdam CT classification. Combination model containing serum CKLF1, GCS scores, and Rotterdam CT classification performed more efficiently than any of them alone in predicting mortality and poor prognosis. The models were visually described using nomograms, which were comparatively stable under calibration curve and were relatively of clinical benefit under decision curve. CONCLUSION: Serum CKLF1 levels are significantly associated with disease severity, poor 180-day prognosis, and 180-day mortality in sTBI patients. Hence, complement CKLF1 may serve as a potential prognostic biomarker of sTBI.

Traumatic Brain Injuries: Manifestations, Evaluation, Management, and Outcomes.

The Psychiatric Consultation Service at Massachusetts General Hospital sees medical and surgical inpatients with comorbid psychiatric symptoms and conditions. During their twice-weekly rounds, Dr Stern and other members of the Consultation Service discuss diagnosis and management of hospitalized patients with complex medical or surgical problems who also demonstrate psychiatric symptoms or conditions. These discussions have given rise to rounds reports that will prove useful for clinicians practicing at the interface of medicine and psychiatry.Prim Care Companion CNS Disord 2024;26(3):23f03667. Author affiliations are listed at the end of this article.

Serum exosomes miR-206 and miR-549a-3p as potential biomarkers of traumatic brain injury.

Traumatic brain injury (TBI) is one of the leading causes of death and disability worldwide. However, effective diagnostic, therapeutic and prognostic biomarkers are still lacking. Our research group previously revealed through high-throughput sequencing that the serum exosomes miR-133a-3p, miR-206, and miR-549a-3p differ significantly in severe TBI (sTBI), mild or moderate TBI (mTBI), and control groups. However, convincing experimental evidence is lacking. To solve this problem, we used qPCR in this study to further verify the expression levels of serum exosomes miR-133a-3p, miR-206 and miR-549a-3p in TBI patients. The results showed that the serum exosomes miR-206 and miR-549a-3p showed good predictive value as biomarkers of TBI. In addition, in order to further verify whether serum exosomes miR-206 and miR-549a-3p can be used as potential biomarkers in patients with TBI and to understand the mechanism of their possible effects, we further determined the contents of SOD, BDNF, VEGF, VEGI, NSE and S100ß in the serum of TBI patients. The results showed that, serum exosomes miR-206 and miR-549a-3p showed good correlation with BDNF, NSE and S100ß. In conclusion, serum exosomes miR-206 and miR-549a-3p have the potential to serve as potential biomarkers in patients with TBI.

Brain tissue oxygen partial pressure monitoring and prognosis of patients with traumatic brain injury: a meta-analysis.

To assess whether monitoring brain tissue oxygen partial pressure (PbtO2) or employing intracranial pressure (ICP)/cerebral perfusion pressure (CCP)-guided management improves patient outcomes, including mortality, hospital length of stay (LOS), mean daily ICP and mean daily CCP during the intensive care unit(ICU)stay. We searched the Web of Science, EMBASE, PubMed, Cochrane Library, and MEDLINE databases until December 12, 2023. Prospective randomized controlled and cohort studies were included. A meta-analysis was performed for the primary outcome measure, mortality, following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Eleven studies with a total of 37,492 patients were included. The mortality in the group with PbtO2 was 29.0% (odds ratio: 0.73;95% confidence interval [CI]:0.56-0.96; P = 0.03; I = 55%), demonstrating a significant benefit. The overall hospital LOS was longer in the PbtO2 group than that in the ICP/CPP group (mean difference:2.03; 95% CI:1.03-3.02; P<0.0001; I = 39%). The mean daily ICP in the PbtO2 monitoring group was lower than that in the ICP/CPP group (mean difference:-1.93; 95% CI: -3.61 to -0.24; P = 0.03; I = 41%). Moreover, PbtO2 monitoring did not improve the mean daily CPP (mean difference:2.43; 95%CI: -1.39 to 6.25;P = 0.21; I = 56%).Compared with ICP/CPP monitoring, PbtO2 monitoring reduced the mortality and the mean daily ICP in patients with severe traumatic brain injury; however, no significant effect was noted on the mean daily CPP. In contrast, ICP/CPP monitoring alone was associated with a short hospital stay.

Refining outcome prediction after traumatic brain injury with machine learning algorithms.

Outcome after traumatic brain injury (TBI) is typically assessed using the Glasgow outcome scale extended (GOSE) with levels from 1 (death) to 8 (upper good recovery). Outcome prediction has classically been dichotomized into either dead/alive or favorable/unfavorable outcome. Binary outcome prediction models limit the possibility of detecting subtle yet significant improvements. We set out to explore different machine learning methods with the purpose of mapping their predictions to the full 8 grade scale GOSE following TBI. The models were set up using the variables: age, GCS-motor score, pupillary reaction, and Marshall CT score. For model setup and internal validation, a total of 866 patients could be included. For external validation, a cohort of 369 patients were included from Leuven, Belgium, and a cohort of 573 patients from the US multi-center ProTECT III study. Our findings indicate that proportional odds logistic regression (POLR), random forest regression, and a neural network model achieved accuracy values of 0.3-0.35 when applied to internal data, compared to the random baseline which is 0.125 for eight categories. The models demonstrated satisfactory performance during external validation in the data from Leuven, however, their performance were not satisfactory when applied to the ProTECT III dataset.

Applicability and clinical utility of the German rivermead post-concussion symptoms questionnaire in proxies of children after traumatic brain injury: an instrument validation study.

BACKGROUND: The German Rivermead Post-Concussion Symptoms Questionnaire (RPQ) can be used to assess post-concussion symptoms (PCS) after traumatic brain injury (TBI) in adults, adolescents, and children. METHODS: In this study, we examined the psychometric properties of the German RPQ proxy version (N = 146) for children (8-12 years) after TBI at the item, total and scale score level. Construct validity was analyzed using rank correlations with the proxy-assessed Post-Concussion Symptoms Inventory (PCSI-P), the Patient Health Questionnaire 9 (PHQ-9), and the Generalized Anxiety Disorder Scale 7 (GAD-7). Furthermore, sensitivity testing was performed concerning subjects' sociodemographic and injury-related characteristics. Differential item functioning (DIF) was analyzed to assess the comparability of RPQ proxy ratings for children with those for adolescents. RESULTS: Good internal consistency was demonstrated regarding Cronbach's α (0.81-0.90) and McDonald's ω (0.84-0.92). The factorial validity of a three-factor model was superior to the original one-factor model. Proxy ratings of the RPQ total and scale scores were strongly correlated with the PCSI-P (ϱ = 0.50-0.69), as well as moderately to strongly correlated with the PHQ-9 (ϱ = 0.49-0.65) and the GAD-7 (ϱ = 0.44-0.64). The DIF analysis revealed no relevant differences between the child and adolescent proxy versions. CONCLUSIONS: The German RPQ proxy is a psychometrically reliable and valid instrument for assessing PCS in children after TBI. Therefore, RPQ self- and proxy-ratings can be used to assess PCS in childhood as well as along the lifespan of an individual after TBI.

[Use of invasive intracranial pressure monitoring in patients with severe traumatic brain injury]. / Ispol'zovanie invazivnogo monitoringa vnutricherepnogo davleniya u patsientov s tyazheloi cherepno-mozgovoi travmoi.

OBJECTIVE: To evaluate the effectiveness of the use of invasive intracranial pressure (ICP) monitoring on treatment outcomes in patients with severe traumatic brain injury (TBI). MATERIAL AND METHODS: We analyzed 50 case histories of patients with severe TBI who received treatment in the Krasnoyarsk Regional Clinical Hospital for the period 2021-2022. Comparisons were made between patients with and without invasive intraventricular ICP monitoring. RESULTS: With the same initial condition of patients, ICP monitoring allows for a faster and more timely response to changes in the clinical condition, which significantly affects the clinical outcome. CONCLUSION: The use of invasive ICP monitoring improves the outcome of treatment of patients with severe TBI and justifies the money spent on it.

Trauma diagnostic-related target proteins and their detection techniques.

Trauma is a significant health issue that not only leads to immediate death in many cases but also causes severe complications, such as sepsis, thrombosis, haemorrhage, acute respiratory distress syndrome and traumatic brain injury, among trauma patients. Target protein identification technology is a vital technique in the field of biomedical research, enabling the study of biomolecular interactions, drug discovery and disease treatment. It plays a crucial role in identifying key protein targets associated with specific diseases or biological processes, facilitating further research, drug design and the development of treatment strategies. The application of target protein technology in biomarker detection enables the timely identification of newly emerging infections and complications in trauma patients, facilitating expeditious medical interventions and leading to reduced post-trauma mortality rates and improved patient prognoses. This review provides an overview of the current applications of target protein identification technology in trauma-related complications and provides a brief overview of the current target protein identification technology, with the aim of reducing post-trauma mortality, improving diagnostic efficiency and prognostic outcomes for patients.

Prevalence of Cardiovascular Conditions After Traumatic Brain Injury: A Comparison Between the Traumatic Brain Injury Model Systems and the National Health and Nutrition Examination Survey.

BACKGROUND: The purpose of this study is to compare the prevalence of self-reported cardiovascular conditions among individuals with moderate to severe traumatic brain injury (TBI) to a propensity-matched control cohort. METHODS AND RESULTS: A cross-sectional study described self-reported cardiovascular conditions (hypertension, congestive heart failure [CHF], myocardial infarction [MI], and stroke) from participants who completed interviews between January 2015 and March 2020 in 2 harmonized large cohort studies, the TBI Model Systems and the National Health and Nutrition Examination Survey. Mixed-effect logistic regression models were used to compare the prevalence of cardiovascular conditions after 1:1 propensity-score matching based on age, sex, race, ethnicity, body mass index, education level, and smoking status. The final sample was 4690 matched pairs. Individuals with TBI were more likely to report hypertension (odds ratio [OR], 1.18 [95% CI, 1.08-1.28]) and stroke (OR, 1.70 [95% CI, 1.56-1.98]) but less likely to report CHF (OR, 0.81 [95% CI, 0.67-0.99]) or MI (OR, 0.66 [95% CI, 0.55-0.79]). There was no difference in rate of CHF or MI for those ≤50 years old; however, rates of CHF and MI were lower in the TBI group for individuals >50 years old. Over 65% of individuals who died before the first follow-up interview at 1 year post-TBI were >50 years old, and those >50 years old were more likely to die of heart disease than those ≤50 years old (17.6% versus 8.6%). CONCLUSIONS: Individuals with moderate to severe TBI had an increased rate of self-reported hypertension and stroke but lower rate of MI and CHF than uninjured adults, which may be due to survival bias.

Accuracy of Early Neuroprognostication in Pediatric Severe Traumatic Brain Injury.

BACKGROUND: Children with severe traumatic brain injury (sTBI) are at risk for neurological sequelae impacting function. Clinicians are tasked with neuroprognostication to assist in decision-making. We describe a single-center study assessing clinicians' neuroprognostication accuracy. METHODS: Clinicians of various specialties caring for children with sTBI were asked to predict their patients' functioning three to six months postinjury. Clinicians were asked to participate in the study if their patient had survived but not returned to baseline between day 4 and 7 postinjury. The outcome tool utilized was the functional status scale (FSS), ranging from 6 to 30 (best-worst function). Predicted scores were compared with actual scores three to six months postinjury. Lin concordance correlation coefficients were used to estimate agreement between predicted and actual FSS. Outcome was dichotomized as good (FSS 6 to 8) or poor (FSS ≥9). Positive and negative predictive values for poor outcome were calculated. Pessimistic prognostic prediction was defined as predicted worse outcome by ≥3 FSS points. Demographic and clinical variables were collected. RESULTS: A total of 107 surveys were collected on 24 patients. Two children died. Fifteen children had complete (FSS = 6) or near-complete (FSS = 7) recovery. Mean predicted and actual FSS scores were 10.8 (S.D. 5.6) and 8.6 (S.D. 4.1), respectively. Predicted FSS scores were higher than actual scores (P < 0.001). Eight children had collective pessimistic prognostic prediction. CONCLUSIONS: Clinicians predicted worse functional outcomes, despite high percentage of patients with near-normal function at follow-up clinic. Certain patient and provider factors were noted to impact accuracy and need to be studied in larger cohorts.

Traumatic brain injury, race, ethnicity and cognition in newly diagnosed persons with multiple sclerosis.

We sought to determine whether a history of traumatic brain injury (TBI) could explain the lower symbol digit modalities test (SDMT) scores observed among newly diagnosed multiple sclerosis (MS) and control participants identifying as Black or Hispanic versus white in the MS Sunshine Study (n = 1172). 330 (29.2 %) participants reported a history of ≥1 TBI. Accounting for TBI did not explain the significant independent associations between having MS, being Black or Hispanic and lower SDMT. The pervasive effects of systemic racism in the United States remain the best explanation for the lower SDMT scores observed in Black and Hispanic participants.

Management of Head Trauma.

Traumatic brain injury (TBI) represents a heterogenous spectrum of disease. It is essential to rapidly assess a patient's neurologic status and implement measures to prevent secondary brain injury. Intracranial hypertension, a common sequela of TBI, is managed in a tiered and systematic fashion, starting with the least invasive and moving toward the most invasive. TBI has long-lasting effects on patients and their families and represents a substantial financial and social influence on society. Research regarding the prognosis and treatment of TBI is essential to limit the influence of this widespread disease.

Predictive value of the Trauma Rating Index in Age, Glasgow Coma Scale, Respiratory rate and Systolic blood pressure score (TRIAGES) for the short-term mortality of older patients with isolated traumatic brain injury: a retrospective cohort study.

OBJECTIVES: This study aimed to evaluate the effectiveness of the Trauma Rating Index in Age, Glasgow Coma Scale, Respiratory rate and Systolic blood pressure score (TRIAGES) in predicting 24-hour in-hospital mortality among patients aged 65 years and older with isolated traumatic brain injury (TBI). DESIGN: A retrospective, single-centre cohort study. SETTING: This study was conducted at a government-run tertiary comprehensive hospital. PARTICIPANTS: This study included 982 patients aged 65 years or older with isolated TBI, who were admitted to the emergency department between 1 January 2020 and 31 December 2021. INTERVENTIONS: None. PRIMARY OUTCOME: 24-hour in-hospital mortality was the primary outcome. RESULTS: Among the 982 patients, 8.75% died within 24 hours of admission. The non-survivors typically had higher TRIAGES and lower GCS scores. Logistic regression showed significant associations of both TRIAGES and GCS with mortality; the adjusted ORs were 1.98 (95% CI 1.74 to 2.25) for TRIAGES and 0.72 (95% CI 0.68 to 0.77) for GCS. Receiver operating characteristic (ROC) analysis indicated an area under the ROC curve of 0.86 for GCS and 0.88 for TRIAGES, with a significant difference (p=0.012). However, precision-recall curve (PRC) analysis revealed an area under the PRC of 0.38 for GCS and 0.47 for TRIAGES, without a significant difference (p=0.107). CONCLUSIONS: The TRIAGES system is a promising tool for predicting 24-hour in-hospital mortality in older patients with TBI, demonstrating comparable or slightly superior efficacy to the GCS. Further multicentre studies are recommended for validation.

Efficacy of a virtual reality-based cognitive interactive training program for children with traumatic brain injuries: study protocol for a parallel-group randomized controlled trial.

BACKGROUND: Traumatic brain injury (TBI) is a leading cause of disability in children. Cognitive rehabilitation for this population is critical for their long-term health outcomes. This trial aims to evaluate the efficacy of a virtual reality-based program (VICT) for training executive functions in children with TBI. METHODS: A parallel group randomized controlled trial will be conducted among up to 32 children with TBI. Children in the intervention group will receive the VICT training while children in the control group will play a comparable VR game without executive function training. Each participant will be assessed at baseline, post-intervention, and 1-month follow-up. Outcomes will include core executive functions, attention, and health-related quality of life measured by computerized tasks or standardized questionnaires. DISCUSSION: Cognitive rehabilitation is among the top healthcare needs for pediatric TBI patients. Virtual reality-based training is promising due to its versatile content, flexibility, and potential cost savings for both patients and providers. Findings of this trial will provide data on the efficacy of the VICT program on core executive functions, attention problems, and health-related quality of life and serve as the empirical foundation for future larger multi-site effectiveness trials. TRIAL REGISTRATION: ClinicalTrials.gov NCT04526639 . Registered on August 18, 2020.

Identification of novel blood-based extracellular vesicles biomarker candidates with potential specificity for traumatic brain injury in polytrauma patients.

Objective: The goal of this study was to identify changes in extracellular vesicles (EV) surface proteins specific to traumatic brain injury (TBI), which could be used as a diagnostic and prognostic tool in polytrauma patients. Summary Background Data: Known serum TBI-specific biomarkers (S100B, NSE, and GFAP), which can predict the severity and outcome of isolated TBI, lose their predictive value in the presence of additional extracranial injuries. Extracellular vesicles (EVs) are released from cells in response to various stimuli and carry specific cargo/surface molecules that could be used for tracking injury-responding cells. Methods: EVs were isolated using size exclusion chromatography (SEC) from the plasma of two groups of patients (with isolated TBI, ISS≥16, AIShead≥4, n=10; and polytraumatized patients without TBI ISS≥16, AIShead=0, n=10) collected in the emergency room and 48 h after trauma. EVs' surface epitope expression was investigated using a neurospecific multiplex flow cytometry assay and compared with healthy controls (n=10). Three enrichments of EV epitopes found to be specific to TBI were validated by western blot. Results: The expression of 10 EV epitopes differed significantly among the patient and control groups, and five of these epitopes (CD13, CD196, MOG, CD133, and MBP) were TBI-specific. The increased expression of CD196, CD13, and MOG-positive EVs was validated by western blot. Conclusion: Our data showed that TBI is characterized by a significant increase of CD13, CD196, MOG, CD133, and MBP-positive EVs in patients' plasma. A high level of MOG-positive EVs negatively correlated with the Glasgow Coma Scale score at admission and could be an indicator of poor neurological status.

Symptoms and Functional Outcomes Among Traumatic Brain Injury Patients 3- to 12-Months Post-Injury.

BACKGROUND: Patients with traumatic brain injury (TBI) experience a variety of physical, cognitive, and affective symptoms. However, the evolution of symptoms, especially during the 3- to 12-month convalescence period (when recovery of function is still possible), is understudied. OBJECTIVE: This study aims to identify symptoms and the relationships with functional outcomes that occur during the 3- to 12-month period after a TBI. METHODS: Participants who were 3 to 12 months post-TBI were recruited from a South Florida TBI clinic from May 2022 to June 2023. Clinical data were obtained from the electronic health record. Participants completed the Brain Injury Association of Virginia Symptom Checklist, Neuro-Quality of Life Cognitive Function, Anxiety, Depression, and Sleep Disturbance assessments to report symptoms, and the Disability Rating Scale and Satisfaction with Life Scale. Descriptive statistics were used to characterize demographics and symptoms. Linear regression was performed to analyze the relationships between symptoms and outcomes. RESULTS: A total of N = 39 patients participated in the study. Memory problems and difficulty concentrating were the most common symptoms. Hospital length of stay, intensive care unit length of stay, cognitive, and physical symptoms were significantly associated with the Disability Rating Scale score. Physical, cognitive, depressive, and anxiety symptoms had significant associations with the Satisfaction with Life Scale. CONCLUSION: Cognitive symptoms should be integrated into the clinical care of rehabilitating TBI patients. Nurses should monitor for physical, affective, and cognitive symptoms during the recovery phase of TBI.

Traumatic Brain Injury, Psychological Trauma Exposure, and Anxious and Depressive Symptoms in a Clinical Population.

BACKGROUND: Approximately 90% of adults endorse psychological trauma exposure. However, barriers to assessment of psychological trauma and sequelae include limited access to care, lack of standardized assessments in nonpsychiatric settings, and comorbid diagnoses, such as traumatic brain injury (TBI), that may mimic psychiatric syndromes. OBJECTIVES: This study aims to assess the prevalence rates of psychological trauma exposure and TBI to understand the relationship of these experiences with current psychiatric symptoms. METHODS: This is a cross-sectional study of a convenience sample of adult patients (age 18 years and older) referred for outpatient evaluation at a neuropsychology clinic in the Western United States between September 2021 and October 2022. Patients completed a clinical interview to assess their history of psychological trauma, TBI, and current psychiatric symptoms. RESULTS: A total of 118 patients met inclusion criteria. Patients in the TBI group (n = 83) endorsed significantly higher rates of childhood trauma and prior physical, emotional, and sexual abuse compared with the No TBI group (n = 35). Psychological trauma exposure and TBI significantly predicted current anxiety and depressive symptoms, but there was no interaction between these experiences in predicting current psychiatric symptoms. CONCLUSIONS: Individuals with prior TBI experienced psychological trauma, particularly childhood trauma, at a significantly higher rate than those without TBI. Psychological trauma exposure and TBI independently predicted anxious and depressive symptoms, suggesting both may be viable treatment targets. Evaluation of prior psychological trauma exposure during evaluation of TBI may provide opportunities for trauma-informed care and may allow for improved outpatient treatment planning.

Confounding factors impacting the Glasgow coma score: a literature review.

BACKGROUND: The Glasgow coma score (GCS) is a clinical tool used to measure level of consciousness in traumatic brain injury and other settings. Despite its widespread use, there are many inaccuracies in its reporting. One source of inaccuracy is confounding factors which affect consciousness as well as each sub-score of the GCS. The purpose of this article was to create a comprehensive list of confounding factors in order to improve the accuracy of the GCS and ultimately improve decision-making. METHODS: An English language literature search was conducted discussing GCS and multiple other keywords. Ultimately, 64 out of 3972 articles were included for further analysis. RESULTS: A multitude of confounding factors were identified which may affect consciousness or GCS sub-scores including the eye exam, motor exam and the verbal response. CONCLUSIONS: An up-to-date comprehensive list of confounding factors has been created that may be used to aide in GCS recording in hopes of improving its accuracy and utility.

Utilizing ultra-early continuous physiologic data to develop automated measures of clinical severity in a traumatic brain injury population.

Determination of prognosis in the triage process after traumatic brain injury (TBI) is difficult to achieve. Current severity measures like the Trauma and injury severity score (TRISS) and revised trauma score (RTS) rely on additional information from the Glasgow Coma Scale (GCS) and the Injury Severity Score (ISS) which may be inaccurate or delayed, limiting their usefulness in the rapid triage setting. We hypothesized that machine learning based estimations of GCS and ISS obtained through modeling of continuous vital sign features could be used to rapidly derive an automated RTS and TRISS. We derived variables from electrocardiograms (ECG), photoplethysmography (PPG), and blood pressure using continuous data obtained in the first 15 min of admission to build machine learning models of GCS and ISS (ML-GCS and ML-ISS). We compared the TRISS and RTS using ML-ISS and ML-GCS and its value using the actual ISS and GCS in predicting in-hospital mortality. Models were tested in TBI with systemic injury (head abbreviated injury scale (AIS) ≥ 1), and isolated TBI (head AIS ≥ 1 and other AIS ≤ 1). The area under the receiver operating characteristic curve (AUROC) was used to evaluate model performance. A total of 21,077 cases (2009-2015) were in the training set. 6057 cases from 2016 to 2017 were used for testing, with 472 (7.8%) severe TBI (GCS 3-8), 223 (3.7%) moderate TBI (GCS 9-12), and 5913 (88.5%) mild TBI (GCS 13-15). In the TBI with systemic injury group, ML-TRISS had similar AUROC (0.963) to TRISS (0.965) in predicting mortality. ML-RTS had AUROC (0.823) and RTS had AUROC 0.928. In the isolated TBI group, ML-TRISS had AUROC 0.977, and TRISS had AUROC 0.983. ML-RTS had AUROC 0.790 and RTS had AUROC 0.957. Estimation of ISS and GCS from machine learning based modeling of vital sign features can be utilized to provide accurate assessments of the RTS and TRISS in a population of TBI patients. Automation of these scores could be utilized to enhance triage and resource allocation during the ultra-early phase of resuscitation.