Predicting outcome after traumatic brain injury: development and international validation of prognostic scores based on admission characteristics

Mortality prediction in severe traumatic brain injury using traditional and machine learning algorithms

Prognostic prediction of traumatic brain injury (TBI) in patients is crucial in clinical decision and health care policy making. This study aimed to develop and validate prediction models for in-hospital mortality after severe traumatic brain injury (sTBI). We developed and validated logistic regression (LR), LASSO regression, and machine learning (ML) algorithms including support vector machines (SVM) and XGBoost models. Fifty-four candidate predictors were included. Model performance was expressed in terms of discrimination (C-statistic) and calibration (intercept and slope). For model development, 2804 patients with sTBI in the Collaborative European NeuroTrauma Effectiveness Research in TBI (CENTER-TBI) China Registry study were included. External validation was performed in 1113 patients with sTBI in the CENTER-TBI European Registry study. XGBoost achieved high discrimination in mortality prediction, and it outperformed logistic and LASSO regression. The XGBoost model established in this study also outperformed prediction models currently available, including the International Mission for Prognosis and Analysis of Clinical Trials (IMPACT) core and International Mission for Prognosis and Analysis of Clinical Trials (CRASH) basic models. When including 54 variables, XGBoost and SVM reached C-statistics of 0.87 (95% confidence interval [CI]: 0.81-0.92) and 0.85 (95% CI: 0.79-0.90) at internal validation, and 0.88 (95% CI: 0.87-0.88) and 0.86 (95% CI: 0.85-0.87) at external validation, respectively. A simplified version of XGBoost and SVM using 26 variables selected by recursive feature elimination (RFE) reached C-statistics of 0.87 (95% CI: 0.82-0.92) and 0.86 (95% CI: 0.80-0.91) at internal validation, and 0.87 (95% CI: 0.87-0.88) and 0.87 (95% CI: 0.86-0.87) at external validation, respectively. However, when the number of variables included decreased, the difference between ML and LR diminished. All the prediction models can be accessed via a web-based calculator. Glasgow Coma Scale (GCS) score, age, pupillary light reflex, Injury Severity Score (ISS) for brain region, and the presence of acute subdural hematoma were the five strongest predictors for mortality prediction. The study showed that ML techniques such as XGBoost may capture information hidden in demographic and clinical predictors of patients with sTBI and yield more precise predictions compared with LR approaches.

Surgery for acute subdural hematoma: the value of pre-emptive decompressive craniectomy by propensity score analysis

BACKGROUND

Acute subdural hematomas (ASDH) are found frequently following traumatic brain injury (TBI) and they are considered the most lethal type of mass lesions. The decision to perform a procedure to evacuate ASDH and the approach, either via craniotomy or decompressive craniectomy (DC), remains controversial.

METHODS

We reviewed a prospectively collected series of 343 moderate to severe TBI patients in whom ASDH was the main lesion (ASDH volumes ≥10 cc). Patients with early comfort measures (early mortality prediction >50% and not ICP monitored), bilateral ASDH or the presence of another intracranial hematoma with volumes exceeding two times the volume of the ASDH were excluded. Among them, 112 were managed conservatively, 65 underwent ASDH evacuation by craniotomy and 166 by DC (103 pre-emptive DC, 63 obligatory DC). We calculated the average treatment effect by propensity score (PS) analysis using the following covariates: age, year, hypoxia, shock, pupils, major extracranial injury, motor score, midline shift, ASDH volume, swelling, intraventricular and subarachnoid hemorrhage presence. Then, multivariable binary regression and ordinal logistic regression analysis were performed to estimate associations between predictors and mortality and 12 months-GOS respectively. The patients' inverse probability weights were included as an independent variable in both regression models.

RESULTS

The main variables associated with outcome were year, age, falls from patient´s own height, hypoxia, early deterioration, pupillary abnormalities, basal cistern effacement, compliance to ICP monitoring guidelines and type of surgical approach (craniotomy and pre-emptive DC).

CONCLUSIONS

According to sliding dichotomy analysis, we found that patients in the intermediate or worst bands of unfavorable outcome prognosis seemed to achieve better than expected outcome if they underwent pre-emptive DC rather than craniotomy.

ICP, CPP, and PRx in traumatic brain injury and aneurysmal subarachnoid hemorrhage: association of insult intensity and duration with clinical outcome

OBJECTIVE

The primary aim of this study was to determine the combined effect of insult intensity and duration of intracranial pressure (ICP), cerebral perfusion pressure (CPP), and pressure reactivity index (PRx) on outcome measured with the Glasgow Outcome Scale-Extended (GOS-E) in patients with traumatic brain injury (TBI) or aneurysmal subarachnoid hemorrhage (aSAH).

METHODS

This observational study included all TBI and aSAH patients treated in the neurointensive care unit in Uppsala, Sweden, 2008-2018, with at least 24 hours of ICP monitoring during the first 10 days following injury and available long-term clinical outcome data. ICP, CPP, and PRx insults were visualized as 2D plots to highlight the effects of both insult intensity and duration on patient outcome.

RESULTS

Of 950 included patients, 436 were TBI and 514 aSAH patients. The TBI patients were younger, more often male, and exhibited worse neurological status at admission, but recovered more favorably than the aSAH patients. There was a transition from good to poor outcome with ICP above 15-20 mm Hg in both TBI and aSAH. The two diagnoses had opposite CPP patterns. In TBI patients, CPP episodes at or below 80 mm Hg were generally favorable, whereas CPP episodes above 80 mm Hg were favorable in the aSAH patients. In the TBI patients there was a transition from good to poor outcome when PRx exceeded zero, but no evident transition was found in the aSAH cohort.

CONCLUSIONS

The insult intensity and duration plots formulated in this study illustrate the similarities and differences between TBI and aSAH patients. In particular, aSAH patients may benefit from much higher CPP targets than TBI patients.

Identification of Demographic and Clinical Prognostic Factors in Traumatic Intraventricular Hemorrhage

BACKGROUND

The presence of traumatic intraventricular hemorrhage (tIVH) following traumatic brain injury (TBI) is associated with worse neurological outcome. The mechanisms by which patients with tIVH have worse outcome are not fully understood and research is ongoing, but foundational studies that explore prognostic factors within tIVH populations are also lacking. This study aimed to further identify and characterize demographic and clinical variables within a subset of patients with TBI and tIVH that may be implicated in tIVH outcome.

METHODS

In this observational study, we reviewed a large prospective TBI database to determine variables present on admission that predicted neurological outcome 6 months after injury. A review of 7,129 patients revealed 211 patients with tIVH on admission and 6-month outcome data. Hypothesized risk factors were tested in univariate analyses with significant variables (p < 0.05) included in logistic and linear regression models. Following the addition of either the Rotterdam computed tomography or Glasgow Coma Scale (GCS) score, we employed a backward selection process to determine significant variables in each multivariate model.

RESULTS

Our study found that that hypotension (odds ratio [OR] = 0.35, 95% confidence interval [CI] = 0.13-0.94, p = 0.04) and the hemoglobin level (OR = 1.33, 95% CI = 1.09-1.63, p = 0.006) were significant predictors in the Rotterdam model, whereas only the hemoglobin level (OR = 1.29, 95% CI = 1.06-1.56, p = 0.01) was a significant predictor in the GCS model.

CONCLUSIONS

This study represents one of the largest investigations into prognostic factors for patients with tIVH and demonstrates that admission hemoglobin level and hypotension are associated with outcomes in this patient population. These findings add value to established prognostic scales, could inform future predictive modeling studies, and may provide potential direction in early medical management of patients with tIVH.

Effect of Red Cell Distribution Width on the Prognosis of Patients with Traumatic Brain Injury: A Retrospective Cohort Study

BACKGROUND

The link between red cell distribution width (RDW) and prognosis of traumatic brain injury (TBI) is controversial. Whether RDW can increase the prognostic value of established predictors remains unknown. This study aimed to provide supportive evidence for the prognostic value of RDW.

METHODS

Clinical data of 1488 patients with TBI were extracted from the Multiparameter Intelligent Monitoring in Intensive Care III database and classified into 2 groups: 1) one with RDW <14.5% (n = 1061) and 2) the other with RDW ≥14.5% (n = 427). Multivariable logistic regression models were used to estimate the relationship between RDW and outcomes. Stratified analyses and interactions were also performed. We compared the area under the receiver operating characteristic curve of the International Mission for Prognoses and Clinical Trial Design in TBI (IMPACT) core and extended models with and without RDW.

RESULTS

After adjusting for confounding factors, RDW was an independent risk consideration for TBI prognoses; the odds ratios were 1.62 (95% confidence interval (CI): 1.05, 2.50) and 1.89 (95% CI: 1.35, 2.64) for hospital mortality and 6-month mortality, respectively. This association was crucial for patients with a Glasgow Coma Score of 3-12 (odds ratio, 2.79; 95% CI: 1.33, 5.87). For 6-month mortality, when RDW was added to the core and extended IMPACT models, the area under the receiver operating characteristic curve increased from 0.833 to 0.851 (P = 0.001) and from 0.842 to 0.855 (P = 0.002), respectively.

CONCLUSIONS

Elevated RDW is an independent risk consideration for hospital and 6-month mortality rates. When RDW was added to the IMPACT core and extended models, it improved its predictive ability for 6-month mortality in patients with TBI.

Mechanical Ventilation in Patients with Traumatic Brain Injury: Is it so Different?

Patients with traumatic brain injury (TBI) frequently require invasive mechanical ventilation and admission to an intensive care unit. Ventilation of patients with TBI poses unique clinical challenges, and careful attention is required to ensure that the ventilatory strategy (including selection of appropriate tidal volume, plateau pressure, and positive end-expiratory pressure) does not cause significant additional injury to the brain and lungs. Selection of ventilatory targets may be guided by principles of lung protection but with careful attention to relevant intracranial effects. In patients with TBI and concomitant acute respiratory distress syndrome (ARDS), adjunctive strategies include sedation optimization, neuromuscular blockade, recruitment maneuvers, prone positioning, and extracorporeal life support. However, these approaches have been largely extrapolated from studies in patients with ARDS and without brain injury, with limited data in patients with TBI. This narrative review will summarize the existing evidence for mechanical ventilation in patients with TBI. Relevant literature in patients with ARDS will be summarized, and where available, direct data in the TBI population will be reviewed. Next, practical strategies to optimize the delivery of mechanical ventilation and determine readiness for extubation will be reviewed. Finally, future directions for research in this evolving clinical domain will be presented, with considerations for the design of studies to address relevant knowledge gaps.

Prediction of motor function in patients with traumatic brain injury using genetic algorithms modified back propagation neural network: A data-based study

Objective

Traumatic brain injury (TBI) is one of the leading causes of death and disability worldwide. In this study, the characteristics of the patients, who were admitted to the China Rehabilitation Research Center, were elucidated in the TBI database, and a prediction model based on the Fugl-Meyer assessment scale (FMA) was established using this database.

Methods

A retrospective analysis of 463 TBI patients, who were hospitalized from June 2016 to June 2020, was performed. The data of the patients used for this study included the age and gender of the patients, course of TBI, complications, and concurrent dysfunctions, which were assessed using FMA and other measures. The information was collected at the time of admission to the hospital and 1 month after hospitalization. After 1 month, a prediction model, based on the correlation analyses and a 1-layer genetic algorithms modified back propagation (GA-BP) neural network with 175 patients, was established to predict the FMA. The correlations between the predicted and actual values of 58 patients (prediction set) were described.

Results

Most of the TBI patients, included in this study, had severe conditions (70%). The main causes of the TBI were car accidents (56.59%), while the most common complication and dysfunctions were hydrocephalus (46.44%) and cognitive and motor dysfunction (65.23 and 63.50%), respectively. A total of 233 patients were used in the prediction model, studying the 11 prognostic factors, such as gender, course of the disease, epilepsy, and hydrocephalus. The correlation between the predicted and the actual value of 58 patients was R ² = 0.95.

Conclusion

The genetic algorithms modified back propagation neural network can predict motor function in patients with traumatic brain injury, which can be used as a reference for risk and prognosis assessment and guide clinical decision-making.

Prognosis prediction in traumatic brain injury patients using machine learning algorithms

Predicting treatment outcomes in traumatic brain injury (TBI) patients is challenging worldwide. The present study aimed to achieve the most accurate machine learning (ML) algorithms to predict the outcomes of TBI treatment by evaluating demographic features, laboratory data, imaging indices, and clinical features. We used data from 3347 patients admitted to a tertiary trauma centre in Iran from 2016 to 2021. After the exclusion of incomplete data, 1653 patients remained. We used ML algorithms such as random forest (RF) and decision tree (DT) with ten-fold cross-validation to develop the best prediction model. Our findings reveal that among different variables included in this study, the motor component of the Glasgow coma scale, the condition of pupils, and the condition of cisterns were the most reliable features for predicting in-hospital mortality, while the patients' age takes the place of cisterns condition when considering the long-term survival of TBI patients. Also, we found that the RF algorithm is the best model to predict the short-term mortality of TBI patients. However, the generalized linear model (GLM) algorithm showed the best performance (with an accuracy rate of 82.03 ± 2.34) in predicting the long-term survival of patients. Our results showed that using appropriate markers and with further development, ML has the potential to predict TBI patients' survival in the short- and long-term.

Rapid prediction of secondary neurologic decline after traumatic brain injury: a data analytic approach

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.

Early EEG monitoring predicts clinical outcome in patients with moderate to severe traumatic brain injury

There is a need for reliable predictors in patients with moderate to severe traumatic brain injury to assist clinical decision making. We assess the ability of early continuous EEG monitoring at the intensive care unit (ICU) in patients with traumatic brain injury (TBI) to predict long term clinical outcome and evaluate its complementary value to current clinical standards. We performed continuous EEG measurements in patients with moderate to severe TBI during the first week of ICU admission. We assessed the Extended Glasgow Outcome Scale (GOSE) at 12 months, dichotomized into poor (GOSE 1-3) and good (GOSE 4-8) outcome. We extracted EEG spectral features, brain symmetry index, coherence, aperiodic exponent of the power spectrum, long range temporal correlations, and broken detailed balance. A random forest classifier using feature selection was trained to predict poor clinical outcome based on EEG features at 12, 24, 48, 72 and 96 h after trauma. We compared our predictor with the IMPACT score, the best available predictor, based on clinical, radiological and laboratory findings. In addition we created a combined model using EEG as well as the clinical, radiological and laboratory findings. We included hundred-seven patients. The best prediction model using EEG parameters was found at 72 h after trauma with an AUC of 0.82 (0.69-0.92), specificity of 0.83 (0.67-0.99) and sensitivity of 0.74 (0.63-0.93). The IMPACT score predicted poor outcome with an AUC of 0.81 (0.62-0.93), sensitivity of 0.86 (0.74-0.96) and specificity of 0.70 (0.43-0.83). A model using EEG and clinical, radiological and laboratory parameters resulted in a better prediction of poor outcome (p < 0.001) with an AUC of 0.89 (0.72-0.99), sensitivity of 0.83 (0.62-0.93) and specificity of 0.85 (0.75-1.00). EEG features have potential use for predicting clinical outcome and decision making in patients with moderate to severe TBI and provide complementary information to current clinical standards.

Time Course and Clinical Significance of Hematoma Expansion in Moderate-to-Severe Traumatic Brain Injury: An Observational Cohort Study

BACKGROUND

Preventing intracranial hematoma expansion has been advertised as a possible treatment opportunity in traumatic brain injury (TBI). However, the time course of hematoma expansion, and whether the expansion affects outcome, remains poorly understood. In light of this, the aim of this study was to use 3D volume rendering to determine how traumatic intracranial hematomas expand over time and evaluate its impact on outcome.

METHODS

Single-center, population-based, observational cohort study of adults with moderate-to-severe TBI. Hematoma expansion was defined as the change in hematoma volume from the baseline computed tomography scan until the lesion had stopped progressing. Volumes were calculated by using semiautomated volumetric segmentation. Functional outcome was measured by using the 12 month Glasgow outcome scale (GOS).

RESULTS

In total, 643 patients were included. The mean baseline hematoma volume was 4.2 ml, and the subsequent mean hematoma expansion was 3.8 ml. Overall, 33% of hematomas had stopped progressing within 3 h, and 94% of hematomas had stopped progressing within 24 h of injury. Contusions expanded significantly more, and for a longer period of time, than extra-axial hematomas. There was a significant dose-response relationship between hematoma expansion and 12 month GOS, even after adjusting for known outcome predictors, with every 1-ml increase in hematoma volume associated with a 6% increased risk of 1-point GOS deduction.

CONCLUSIONS

Hematoma expansion is a driver of unfavorable outcome in TBI, with small changes in hematoma volume also impacting functional outcome. This study also proposes a wider window of opportunity to prevent lesion progression than what has previously been suggested.

Microfluidics for Profiling miRNA Biomarker Panels in AI-Assisted Cancer Diagnosis and Prognosis

Early detection of cancers and their precise subtyping are essential to patient stratification and effective cancer management. Data-driven identification of expression biomarkers coupled with microfluidics-based detection shows promise to revolutionize cancer diagnosis and prognosis. MicroRNAs play key roles in cancers and afford detection in tissue and liquid biopsies. In this review, we focus on the microfluidics-based detection of miRNA biomarkers in AI-based models for early-stage cancer subtyping and prognosis. We describe various subclasses of miRNA biomarkers that could be useful in machine-based predictive modeling of cancer staging and progression. Strategies for optimizing the feature space of miRNA biomarkers are necessary to obtain a robust signature panel. This is followed by a discussion of the issues in model construction and validation towards producing Software-as-Medical-Devices (SaMDs). Microfluidic devices could facilitate the multiplexed detection of miRNA biomarker panels, and an overview of the different strategies for designing such microfluidic systems is presented here, with an outline of the detection principles used and the corresponding performance measures. Microfluidics-based profiling of miRNAs coupled with SaMD represent high-performance point-of-care solutions that would aid clinical decision-making and pave the way for accessible precision personalized medicine.

Prognostic Models for Traumatic Brain Injury Have Good Discrimination but Poor Overall Model Performance for Predicting Mortality and Unfavorable Outcomes

BACKGROUND

The most extensively validated prognostic models for traumatic brain injury (TBI) are the Corticoid Randomization after Significant Head Injury (CRASH) and International Mission on Prognosis and Analysis of Clinical Trials (IMPACT). Model characteristics outside of area under the curve (AUC) are rarely reported.

OBJECTIVE

To report the discriminative validity and overall model performance of the CRASH and IMPACT models for prognosticating death at 14 days (CRASH) and 6 months (IMPACT) and unfavorable outcomes at 6 months after TBI.

METHODS

This retrospective cohort study included prospectively collected patients with severe TBI treated at a single level I trauma center (n = 467). CRASH and IMPACT percent risk values for the given outcome were computed. Unfavorable outcome was defined as a Glasgow Outcome Scale-Extended score of 1 to 4 at 6 months. Binary logistic regressions and receiver operating characteristic analyses were used to differentiate patients from the CRASH and IMPACT prognostic models.

RESULTS

All models had low R 2 values (0.17-0.23) with AUC values from 0.77 to 0.81 and overall accuracies ranging from 72.4% to 78.3%. Sensitivity (35.3-50.0) and positive predictive values (66.7-69.2) were poor in the CRASH models, while specificity (52.3-53.1) and negative predictive values (58.1-63.6) were poor in IMPACT models. All models had unacceptable false positive rates (20.8%-33.3%).

CONCLUSION

Our results were consistent with previous literature regarding discriminative validity (AUC = 0.77-0.81). However, accuracy and false positive rates of both the CRASH and IMPACT models were poor.

Evolution of Making Clinical Predictions in Neurosurgery

Prediction of clinical outcomes is an essential task for every physician. Physicians may base their clinical prediction of an individual patient on their intuition and on scientific material such as studies presenting population risks and studies reporting on risk factors (prognostic factors). A relatively new and more informative approach for making clinical predictions relies on the use of statistical models that simultaneously consider multiple predictors that provide an estimate of the patient's absolute risk of an outcome. There is a growing body of literature in the neurosurgical field reporting on clinical prediction models. These tools have high potential in supporting (not replacing) neurosurgeons with their prediction of a patient's outcome. If used sensibly, these tools pave the way for more informed decision-making with or for individual patients. Patients and their significant others want to know their risk of the anticipated outcome, how it is derived, and the uncertainty associated with it. Learning from these prediction models and communicating the output to others has become an increasingly important skill neurosurgeons have to master. This article describes the evolution of making clinical predictions in neurosurgery, synopsizes key phases for the generation of a useful clinical prediction model, and addresses some considerations when deploying and communicating the results of a prediction model. The paper is illustrated with multiple examples from the neurosurgical literature, including predicting arachnoid cyst rupture, predicting rebleeding in patients suffering from aneurysmal subarachnoid hemorrhage, and predicting survival in glioblastoma patients.

A Systematic Review on Traumatic Brain Injury Pathophysiology and Role of Herbal Medicines in its Management

BACKGROUND

Traumatic brain injury (TBI) is a worldwide problem. Almost about sixtynine million people sustain TBI each year all over the world. Repetitive TBI linked with increased risk of neurodegenerative disorder such as Parkinson, Alzheimer, traumatic encephalopathy. TBI is characterized by primary and secondary injury and exerts a severe impact on cognitive, behavioral, psychological and other health problem. There were various proposed mechanism to understand complex pathophysiology of TBI but still there is a need to explore more about TBI pathophysiology. There are drugs present for the treatment of TBI in the market but there is still need of more drugs to develop for better and effective treatment of TBI, because no single drug is available which reduces the further progression of this injury.

OBJECTIVE

The main aim and objective of structuring this manuscript is to design, develop and gather detailed data regarding about the pathophysiology of TBI and role of medicinal plants in its treatment.

METHOD

This study is a systematic review conducted between January 1995 to June 2021 in which a consultation of scientific articles from indexed periodicals was carried out in Science Direct, United States National Library of Medicine (Pubmed), Google Scholar, Elsvier, Springer and Bentham.

RESULTS

A total of 54 studies were analyzed, on the basis of literature survey in the research area of TBI.

CONCLUSION

Recent studies have shown the potential of medicinal plants and their chemical constituents against TBI therefore, this review targets the detailed information about the pathophysiology of TBI and role of medicinal plants in its treatment.

Measuring long-term outcomes after injury: current issues and future directions

Maximizing long-term outcomes for patients following injury is the next challenge in the delivery of patient-centered trauma care. The following review outlines three important components in trauma outcomes: (1) data gathering and monitoring, (2) the impact of traumatic brain injury, and (3) trajectories in recovery and identifies knowledge gaps and areas for needed future research.

Performance of CRASH and IMPACT Prognostic Models for Traumatic Brain Injury at 12 and 24 Months Post-Injury

The Corticoid Randomization after Significant Head Injury (CRASH) and International Mission for Prognosis and Analysis of Clinical Trials (IMPACT) prognostic models are the most reported prognostic models for traumatic brain injury (TBI) in the scientific literature. However, these models were developed and validated to predict 6-month unfavorable outcome and mortality, and growing evidence supports continuous improvements in functional outcome after severe TBI up to 2 years post-injury. The purpose of this study was to evaluate CRASH and IMPACT model performance beyond 6 months post-injury to include 12 and 24 months post-injury. Discriminative validity remained consistent over time and comparable to earlier recovery time points (area under the curve = 0.77-0.83). Both models had poor fit for unfavorable outcomes, explaining less than one quarter of the variation in outcomes for severe TBI patients. The CRASH model had significant values for the Hosmer-Lemeshow test at 12 and 24 months, indicating poor model fit past the previous validation point. There is concern in the scientific literature that TBI prognostic models are being used by neurotrauma clinicians to support clinical decision making despite the goal of the models' development being to support research study design. The results of this study indicate that the CRASH and IMPACT models should not be used in routine clinical practice because of poor model fit that worsens over time and the large, unexplained variance in outcomes.

Prognostic value of global deep white matter DTI metrics for 1-year outcome prediction in ICU traumatic brain injury patients: an MRI-COMA and CENTER-TBI combined study

PURPOSE

A reliable tool for outcome prognostication in severe traumatic brain injury (TBI) would improve intensive care unit (ICU) decision-making process by providing objective information to caregivers and family. This study aimed at designing a new classification score based on magnetic resonance (MR) diffusion metrics measured in the deep white matter between day 7 and day 35 after TBI to predict 1-year clinical outcome.

METHODS

Two multicenter cohorts (29 centers) were used. MRI-COMA cohort (NCT00577954) was split into MRI-COMA-Train (50 patients enrolled between 2006 and mid-2014) and MRI-COMA-Test (140 patients followed up in clinical routine from 2014) sub-cohorts. These latter patients were pooled with 56 ICU patients (enrolled from 2014 to 2020) from CENTER-TBI cohort (NCT02210221). Patients were dichotomised depending on their 1-year Glasgow outcome scale extended (GOSE) score: GOSE 1-3, unfavorable outcome (UFO); GOSE 4-8, favorable outcome (FO). A support vector classifier incorporating fractional anisotropy and mean diffusivity measured in deep white matter, and age at the time of injury was developed to predict whether the patients would be either UFO or FO.

RESULTS

The model achieved an area under the ROC curve of 0.93 on MRI-COMA-Train training dataset, and 49% sensitivity for 96.8% specificity in predicting UFO and 58.5% sensitivity for 97.1% specificity in predicting FO on the pooled MRI-COMA-Test and CENTER-TBI validation datasets.

CONCLUSION

The model successfully identified, with a specificity compatible with a personalized decision-making process in ICU, one in two patients who had an unfavorable outcome at 1 year after the injury, and two-thirds of the patients who experienced a favorable outcome.

Early sedation in traumatic brain injury: a multicentre international observational study

Objectives: We aimed to investigate the use of sedation in patients with severe traumatic brain injury (TBI), focusing on the choice of sedative agent, dose, duration, and their association with clinical outcomes. Design: Multinational, multicentre, retrospective observational study. Settings: 14 trauma centres in Europe, Australia and the United Kingdom. Participants: A total of 262 adult patients with severe TBI and intracranial pressure monitoring. Main outcome measures: We described how sedative agents were used in this population. The primary outcome was 60-day mortality according to the use of different sedative agents. Secondary outcomes included intensive care unit and hospital length of stay, and the Extended Glasgow Outcome Scale at hospital discharge. Results: Propofol and midazolam were the most commonly used sedatives. Propofol was more common than midazolam as first line therapy (35.4% v 25.6% respectively). Patients treated with propofol had similar Acute Physiology and Chronic Health Evaluation (APACHE) II and International Mission for Prognosis and Analysis of Clinical Trials in Traumatic Brain Injury (IMPACT) scores to patients treated with midazolam, but lower Injury Severity Score (ISS) (median, 26 [IQR, 22-38] v 34 [IQR, 26-44]; P = 0.001). The use of propofol was more common in heavier patients, and midazolam use was strongly associated with opioid co-administration (OR, 12.9; 95% CI, 3.47-47.95; P < 0.001). Sixty-day mortality and hospital mortality were predicted by a higher IMPACT score (P < 0.001) and a higher ISS (P < 0.001), but, after adjustment, were not related to the choice of sedative agent. Conclusions: Propofol was used more often than midazolam, and large doses were common for both sedatives. The first choice was highly variable, was affected by injury severity, and was not independently associated with 60-day mortality.

Association between cerebrovascular reactivity in adult traumatic brain injury and improvement in patient outcome over time: an exploratory analysis

BACKGROUND

Impaired cerebrovascular reactivity following moderate/severe traumatic brain injury (TBI) has emerged as a key potential driver of morbidity and mortality. However, the major contributions to the literature so far have been solely focused on single point measures of long-term outcome. Therefore, it remains unknown whether cerebrovascular reactivity impairment, during the acute phase of TBI, is associated with failure to improve in outcome across time.

METHODS

Cerebrovascular reactivity was measured using three intracranial pressure-based surrogate metrics. For each patient, % time spent above various literature-defined thresholds was calculated. Patients were dichotomized based on outcome transition into Improved vs Not Improved between 1 and 3 months, 3 and 6 months, and 1 and 6 months, based on the Glasgow Outcome Scale-Extended (GOSE). Univariate and multivariable logistic regression analyses were performed, adjusting for the International Mission for Prognosis and Analysis of Clinical Trials (IMPACT) variables.

RESULTS

Seventy-eight patients from the Winnipeg Acute TBI Database were included in this study. On univariate logistic regression analysis, higher % time with cerebrovascular reactivity metrics above clinically defined thresholds was associated with a lack of clinical improvement between 1 and 3 months and 1 and 6 months post injury (p < 0.05). These relationships held true on multivariable logistic regression analysis.

CONCLUSION

Our study demonstrates that impaired cerebrovascular reactivity, during the acute phase of TBI, is associated with failure to improve clinically over time. These preliminary findings highlight the significance that cerebrovascular reactivity monitoring carries in outcome recovery association in moderate/severe TBI.

The Clinical Importance of Optic Nerve Sheath Diameter in Patients with Traumatic Brain Injury: Preliminary Report

Objective

Traumatic brain injury (TBI) is a serious health problem that is related to an increased mortality. In cases of severe TBI, the prediction of prognosis is essential. The enlargement of the optic nerve sheath diameter (ONSD) shows an increased intracranial pressure and is associated with poor outcomes. In this study, we aimed to evaluate the prognostic value of ONSD in patients with severe TBI.

Methods

Forty-four patients with severe TBI were retrospectively enrolled in the study. The patients were divided into two groups: survivors (n=17) and non-survivors (n=27). Baseline characteristics, clinical data, Glasgow coma scale (GCS) on hospital admission, brain computed tomography (CT) results, injury severity score (ISS), and Marshall score were recorded for all patients. ONSD was calculated at 3 mm distance from the globe, immediately below the sclera.

Results

The ONSD on the initial CT was significantly higher in non-survivors compared with survivors (6.83±1.40 vs. 6.40±1.36, p<0.05). In addition, ISS and Marshall score were significantly higher, whereas GCS was significantly lower in non-survivors. ONSD was positively correlated with Marshall score (r=0.332, p<0.05). Receiver operating characteristics analysis demonstrated that ONSD ≥6.61 had a sensitivity of 70.4% and specificity of 64.7% for predicting mortality. It was shown that ONSD ≥6.61 had a 4.3-fold increased risk for in-hospital mortality (odds ratio: 4.35; 95% confidence interval: 1.195-15.865; p<0.05).

Conclusions

The enlargement of ONSD on initial CT was detected to be associated with increased in-hospital mortality in patients with severe TBI.

Predicting mortality in moderate-severe TBI patients without early withdrawal of life-sustaining treatments including ICU complications: The MYSTIC-score

PURPOSE

To develop and internally validate the MortalitY in Moderate-Severe TBI plus ICU Complications (MYSTIC)-Score to predict in-hospital mortality of msTBI patients without early (<24 h) withdrawal-of-life-sustaining treatments.

METHODS

We analyzed data from a Neuro-Trauma Intensive Care Unit prospectively collected between 11/2009-5/2019. Consecutive adult msTBI patients were included if Glasgow Coma Scale≤12, and neither died nor had withdrawal-of-life-sustaining treatments within 24 h of admission (n = 485). Using univariate and multivariable logistic regression in a random-split cohort approach (2/3 derivation;1/3 validation), we identified independent predictors of in-hospital mortality while adjusting for validated predictors of mortality (IMPACT-variables). We constructed the MYSTIC-Score and examined discrimination and calibration.

RESULTS

The MYSTIC-Score included the ICU complications brain edema, herniation, systemic inflammatory response syndrome, sepsis, acute kidney injury, cardiac arrest, and urinary tract infection. In the derivation cohort(n = 324), discrimination and calibration were excellent (area-under-the-receiver-operating-curve [AUC-ROC] = 0.95;Hosmer-Lemeshow p-value = 0.09, with p > 0.05 indicating good calibration). Internal validation revealed an AUC-ROC = 0.93 and Hosmer-Lemeshow-p-value = 0.76 (n = 161).

CONCLUSIONS

Certain ICU complications are independent predictors of in-hospital mortality and strengthen outcome prediction in msTBI when combined with validated admission predictors of mortality. However, external validation is needed to determine robustness and practical applicability of our model given the high potential for residual confounders.

The effect of Vitamins C and E on clinical outcomes of patients with severe traumatic brain injury: A propensity score matching study

Background

The aim of this study was to assess the effect of Vitamins C and E on mortality, intensive care unit (ICU) length of stay, and Glasgow Outcome Scale-Extended (GOS-E) score of traumatic brain injury (TBI) patients.

Methods

Using data from records of patients in a retrospective cohort study, we included 1321 TBI patients, 269 treated and 1052 untreated, aged over 18 years with information on exposure (i.e., Vitamins C and E) and confounders. Age, Glasgow Coma Scale, pupil status, Rotterdam classification, blood sugar, blood pressure, international normalized ratio, and comorbidity of patients were considered as the confounding factors. Endpoints were GOS-E on follow-up, mortality, and ICU length of stay. Propensity score matching was performed to adjust the confounders.

Results

Based on the average treatment effect estimates, the use of Vitamins C and E reduced the risk of mortality (risk difference [RD]: -0.07; 95% confidence interval [CI]: -0.14--0.003) and reduced the length of ICU stay (RD -1.77 95% CI:-3.71-0.16). Furthermore, our results showed that GOS-E was improved significantly (RD: 0.09, 95% CI : 0.03-0.16).

Conclusion

Our study suggests that using Vitamins C and E could decrease mortality and length of ICU stay and improve the GOS-E score and functions of the patients with severe TBI. As they are safe and inexpensive medications, they can be used in routine practice in ICUs to improve the outcomes of TBI patients.

External validation of the Glasgow coma scale-pupils in low- to middle-income country patients with traumatic brain injury: Could “motor score-pupil” have higher prognostic value?

Background:

The objective of this study is to validate the admission Glasgow coma scale (GCS) associated with pupil response (GCS-P) to predict traumatic brain injury (TBI) patient’s outcomes in a low- to middle-income country and to compare its performance with that of a simplified model combining the better motor response of the GCS and the pupilar response (MS-P).

Methods:

This is a prospective cohort of patients with TBI in a tertiary trauma reference center in Brazil. Predictive values of the GCS, GCS-P, and MS-P were evaluated and compared for 14 day and in-hospital mortality outcomes and length of hospital stay (LHS).

Results:

The study enrolled 447 patients. MS-P demonstrated better discriminative ability than GCS to predict mortality (AUC 0.736 × 0.658; P < 0.001) and higher AUC than GCS-P (0.736 × 0.704, respectively; P = 0.073). For hospital mortality, MS-P demonstrated better discrimination than GCS (AUC, 0.750 × 0.682; P < 0.001) and higher AUC than GCS-P (0.750 × 0.714; P = 0.027). Both scores were good predictors of LHS (r2 = 0.084 [GCS-P] × 0.079 [GCS] × 0.072 [MS-P]).

Conclusion:

The predictive value of the GCS, GCS-P, and MS-P scales was demonstrated, thus contributing to its external validation in low- to middle-income country.

Traumatic brain injury: progress and challenges in prevention, clinical care, and research

Traumatic brain injury (TBI) has the highest incidence of all common neurological disorders, and poses a substantial public health burden. TBI is increasingly documented not only as an acute condition but also as a chronic disease with long-term consequences, including an increased risk of late-onset neurodegeneration. The first Lancet Neurology Commission on TBI, published in 2017, called for a concerted effort to tackle the global health problem posed by TBI. Since then, funding agencies have supported research both in high-income countries (HICs) and in low-income and middle-income countries (LMICs). In November 2020, the World Health Assembly, the decision-making body of WHO, passed resolution WHA73.10 for global actions on epilepsy and other neurological disorders, and WHO launched the Decade for Action on Road Safety plan in 2021. New knowledge has been generated by large observational studies, including those conducted under the umbrella of the International Traumatic Brain Injury Research (InTBIR) initiative, established as a collaboration of funding agencies in 2011. InTBIR has also provided a huge stimulus to collaborative research in TBI and has facilitated participation of global partners. The return on investment has been high, but many needs of patients with TBI remain unaddressed. This update to the 2017 Commission presents advances and discusses persisting and new challenges in prevention, clinical care, and research.

In LMICs, the occurrence of TBI is driven by road traffic incidents, often involving vulnerable road users such as motorcyclists and pedestrians. In HICs, most TBI is caused by falls, particularly in older people (aged ≥65 years), who often have comorbidities. Risk factors such as frailty and alcohol misuse provide opportunities for targeted prevention actions. Little evidence exists to inform treatment of older patients, who have been commonly excluded from past clinical trials—consequently, appropriate evidence is urgently required. Although increasing age is associated with worse outcomes from TBI, age should not dictate limitations in therapy. However, patients injured by low-energy falls (who are mostly older people) are about 50% less likely to receive critical care or emergency interventions, compared with those injured by high-energy mechanisms, such as road traffic incidents.

Mild TBI, defined as a Glasgow Coma sum score of 13–15, comprises most of the TBI cases (over 90%) presenting to hospital. Around 50% of adult patients with mild TBI presenting to hospital do not recover to pre-TBI levels of health by 6 months after their injury. Fewer than 10% of patients discharged after presenting to an emergency department for TBI in Europe currently receive follow-up. Structured follow-up after mild TBI should be considered good practice, and urgent research is needed to identify which patients with mild TBI are at risk for incomplete recovery.

The selection of patients for CT is an important triage decision in mild TBI since it allows early identification of lesions that can trigger hospital admission or life-saving surgery. Current decision making for deciding on CT is inefficient, with 90–95% of scanned patients showing no intracranial injury but being subjected to radiation risks. InTBIR studies have shown that measurement of blood-based biomarkers adds value to previously proposed clinical decision rules, holding the potential to improve efficiency while reducing radiation exposure. Increased concentrations of biomarkers in the blood of patients with a normal presentation CT scan suggest structural brain damage, which is seen on MR scanning in up to 30% of patients with mild TBI. Advanced MRI, including diffusion tensor imaging and volumetric analyses, can identify additional injuries not detectable by visual inspection of standard clinical MR images. Thus, the absence of CT abnormalities does not exclude structural damage—an observation relevant to litigation procedures, to management of mild TBI, and when CT scans are insufficient to explain the severity of the clinical condition.

Although blood-based protein biomarkers have been shown to have important roles in the evaluation of TBI, most available assays are for research use only. To date, there is only one vendor of such assays with regulatory clearance in Europe and the USA with an indication to rule out the need for CT imaging for patients with suspected TBI. Regulatory clearance is provided for a combination of biomarkers, although evidence is accumulating that a single biomarker can perform as well as a combination. Additional biomarkers and more clinical-use platforms are on the horizon, but cross-platform harmonisation of results is needed. Health-care efficiency would benefit from diversity in providers.

In the intensive care setting, automated analysis of blood pressure and intracranial pressure with calculation of derived parameters can help individualise management of TBI. Interest in the identification of subgroups of patients who might benefit more from some specific therapeutic approaches than others represents a welcome shift towards precision medicine. Comparative-effectiveness research to identify best practice has delivered on expectations for providing evidence in support of best practices, both in adult and paediatric patients with TBI.

Progress has also been made in improving outcome assessment after TBI. Key instruments have been translated into up to 20 languages and linguistically validated, and are now internationally available for clinical and research use. TBI affects multiple domains of functioning, and outcomes are affected by personal characteristics and life-course events, consistent with a multifactorial bio-psycho-socio-ecological model of TBI, as presented in the US National Academies of Sciences, Engineering, and Medicine (NASEM) 2022 report. Multidimensional assessment is desirable and might be best based on measurement of global functional impairment. More work is required to develop and implement recommendations for multidimensional assessment. Prediction of outcome is relevant to patients and their families, and can facilitate the benchmarking of quality of care. InTBIR studies have identified new building blocks (eg, blood biomarkers and quantitative CT analysis) to refine existing prognostic models. Further improvement in prognostication could come from MRI, genetics, and the integration of dynamic changes in patient status after presentation.

Neurotrauma researchers traditionally seek translation of their research findings through publications, clinical guidelines, and industry collaborations. However, to effectively impact clinical care and outcome, interactions are also needed with research funders, regulators, and policy makers, and partnership with patient organisations. Such interactions are increasingly taking place, with exemplars including interactions with the All Party Parliamentary Group on Acquired Brain Injury in the UK, the production of the NASEM report in the USA, and interactions with the US Food and Drug Administration. More interactions should be encouraged, and future discussions with regulators should include debates around consent from patients with acute mental incapacity and data sharing. Data sharing is strongly advocated by funding agencies. From January 2023, the US National Institutes of Health will require upload of research data into public repositories, but the EU requires data controllers to safeguard data security and privacy regulation. The tension between open data-sharing and adherence to privacy regulation could be resolved by cross-dataset analyses on federated platforms, with the data remaining at their original safe location. Tools already exist for conventional statistical analyses on federated platforms, however federated machine learning requires further development. Support for further development of federated platforms, and neuroinformatics more generally, should be a priority.

This update to the 2017 Commission presents new insights and challenges across a range of topics around TBI: epidemiology and prevention (section 1 ); system of care (section 2 ); clinical management (section 3 ); characterisation of TBI (section 4 ); outcome assessment (section 5 ); prognosis (Section 6 ); and new directions for acquiring and implementing evidence (section 7 ). Table 1 summarises key messages from this Commission and proposes recommendations for the way forward to advance research and clinical management of TBI.

Performance of the IMPACT and Helsinki models for predicting 6-month outcomes in a cohort of patients with traumatic brain injury undergoing cranial surgery

Background and aim

Prediction models for patients with traumatic brain injury (TBI) require generalizability and should apply to different settings. We aimed to validate the IMPACT and Helsinki prognostic models in patients with TBI who underwent cranial surgery in a Chinese center.

Methods

This validation study included 607 surgical patients with moderate to severe TBI (Glasgow Coma Scale [GCS] score ≤12) who were consecutively admitted to the Neurotrauma Center of People's Liberation Army (PLANC), China, between 2009 and 2021. The IMPACT models (core, extended and lab) and the Helsinki CT clinical model were used to estimate 6-month mortality and unfavorable outcomes. To assess performance, we studied discrimination and calibration.

Results

In the PLANC database, the observed 6-month mortality rate was 28%, and the 6-month unfavorable outcome was 52%. Significant differences in case mix existed between the PLANC cohort and the development populations for the IMPACT and, to a lesser extent, for the Helsinki models. Discrimination of the IMPACT and Helsinki models was excellent, with most AUC values ≥0.80. The highest values were found for the IMPACT lab model (AUC 0.87) and the Helsinki CT clinical model (AUC 0.86) for the prediction of unfavorable outcomes. Overestimation was found for all models, but the degree of miscalibration was lower in the Helsinki CT clinical model.

Conclusion

In our population of surgical TBI patients, the IMPACT and Helsinki CT clinical models demonstrated good performance, with excellent discrimination but suboptimal calibration. The good discrimination confirms the validity of the predictors, but the poorer calibration suggests a need to recalibrate the models to specific settings.

Haemoglobin transfusion threshold in traumatic brain injury optimisation (HEMOTION): a multicentre, randomised, clinical trial protocol

INTRODUCTION

Traumatic brain injury (TBI) is the leading cause of mortality and long-term disability in young adults. Despite the high prevalence of anaemia and red blood cell transfusion in patients with TBI, the optimal haemoglobin (Hb) transfusion threshold is unknown. We undertook a randomised trial to evaluate whether a liberal transfusion strategy improves clinical outcomes compared with a restrictive strategy.

METHODS AND ANALYSIS

HEMOglobin Transfusion Threshold in Traumatic Brain Injury OptimizatiON is an international pragmatic randomised open label blinded-endpoint clinical trial. We will include 742 adult patients admitted to an intensive care unit (ICU) with an acute moderate or severe blunt TBI (Glasgow Coma Scale ≤12) and a Hb level ≤100 g/L. Patients are randomly allocated using a 1:1 ratio, stratified by site, to a liberal (triggered by Hb ≤100 g/L) or a restrictive (triggered by Hb ≤70 g/L) transfusion strategy applied from the time of randomisation to the decision to withdraw life-sustaining therapies, ICU discharge or death. Primary and secondary outcomes are assessed centrally by trained research personnel blinded to the intervention. The primary outcome is the Glasgow Outcome Scale extended at 6 months. Secondary outcomes include overall functional independence measure, overall quality of life (EuroQoL 5-Dimension 5-Level; EQ-5D-5L), TBI-specific quality of life (Quality of Life after Brain Injury; QOLIBRI), depression (Patient Health Questionnaire; PHQ-9) and mortality.

ETHICS AND DISSEMINATION

This trial is approved by the CHU de Québec-Université Laval research ethics board (MP-20-2018-3706) and ethic boards at all participating sites. Our results will be published and shared with relevant organisations and healthcare professionals.

TRIAL REGISTRATION NUMBER

NCT03260478.

The Characteristics of Withdrawal or Withholding of Life-Sustaining Treatment in Severe Traumatic Brain Injury: A Single Japanese Institutional Study

OBJECTIVES

There is little evidence on the factors influencing the decision to withdraw or continue life-sustaining treatment in the setting of severe traumatic brain injury in Japanese institutions. We investigated the factors associated with the withdrawal or withholding of life-sustaining treatment (WLST) for severe traumatic brain injury at a single Japanese institution.

METHODS

A total of 161 patients with severe traumatic brain injury were retrospectively reviewed. Patient characteristics and injury types were compared between patients with and without the WLST.

RESULTS

Of the 161 patients, 87 (54%) died and 52 (32%) decided to undergo WLST. In 98% of the WLST cases, the decision was made within 24 h of admission. The mean duration between WLST and death was 2 days. The predicted probabilities for mortality and unfavorable outcomes were highest in patients with WLST within 24 h. Patients with WLST were older and had a higher frequency of falls on the ground, ischemic heart disease, and acute subdural hemorrhage than those without WLST.

CONCLUSIONS

The decisions of almost all WLST cases were made within 24 h of admission for severe traumatic brain injury in a Japanese institution because of Japanese patients' religious and cultural backgrounds.

The Relationship Between Trauma Scoring Systems and Outcomes in Patients With Severe Traumatic Brain Injury

OBJECTIVE

This study investigated the relationship between trauma scoring systems and outcomes in patients with severe traumatic brain injury (TBI).

METHODS

From January 2018 to June 2021, 1,122 patients with severe TBI were registered in the Korean Neuro-Trauma Data Bank System. Among them, 697 patients with data on trauma scoring systems were included in the study. According to the Glasgow Outcome Scale-Extended score, the patients were divided into unfavorable and favorable outcome groups. The abbreviated injury scale (AIS), injury severity score (ISS), revised trauma score (RTS), and trauma and injury severity score (TRISS) were evaluated.

RESULTS

The AIS head score was higher in the unfavorable outcome group than in the favorable outcome group (4.39 vs. 4.06, p<0.001). ISS was also higher in the unfavorable outcome group (27.27 vs. 24.22, p=0.001). The RTS and TRISS were higher in the favorable outcome group (RTS, 4.74 vs. 5.45, p<0.001; TRISS, 48.05 vs. 71.02, p<0.001). In comparing the survival and death groups, the ISS was lower in the survival group (25.76 vs. 27.29, p=0.036). Furthermore, RTS was higher in the survival group (5.26 vs. 4.54, p<0.001), as was TRISS (62.11 vs. 44.91, p<0.001).

CONCLUSION

Trauma scoring systems, including ISS, RTS, and TRISS, provide tools for quantifying posttraumatic risk and can be used to predict prognosis. Among these, TRISS is an indicator of the predicted survival rate and is considered a clinically useful tool for predicting unfavorable and favorable outcomes in patients with severe TBI.

A Machine Learning-Based Prognostic Model for the Prediction of Early Death After Traumatic Brain Injury: Comparison with the Corticosteroid Randomization After Significant Head Injury (CRASH) Model

BACKGROUND

Machine learning (ML) has been used to predict the outcomes of traumatic brain injury. However, few studies have reported the use of ML models to predict early death. This study aimed to develop ML models for early death prediction and to compare performance with the corticosteroid randomization after significant head injury (CRASH) model.

METHODS

We retrospectively reviewed traumatic brain injury patients between February 2017 and August 2021. The patients were randomly assigned to a training set and a test set. Predictive variables included clinical findings, laboratory values, and computed tomography findings. The ML models (random forest, support vector machine [SVM], logistic regression) were developed with the training set. The CRASH model is a prognostic model that was developed based on 10,008 patients included in the CRASH trial. The ML and CRASH models were applied to the test set to evaluate the performance.

RESULTS

A total of 423 patients were included; 317 and 106 patients were randomly assigned to the training and test sets, respectively. The area under the curve was highest in the SVM (0.952, 95% confidence interval = 0.906-0.990) and lowest in the CRASH model (0.942, 95% confidence interval = 0.886-0.999). There were no significant differences between the area under the curves of the ML and CRASH models (P = 0.899 for random forest vs. the CRASH model, P = 0.760 for SVM vs. the CRASH model, P = 0.806 for logistic regression vs. the CRASH model).

CONCLUSIONS

The ML models may have comparable performances compared to the CRASH model despite being developed with a smaller sample size.

Postpartum depression: a developed and validated model predicting individual risk in new mothers

Postpartum depression (PPD) is a serious condition associated with potentially tragic outcomes, and in an ideal world PPDs should be prevented. Risk prediction models have been developed in psychiatry estimating an individual's probability of developing a specific condition, and recently a few models have also emerged within the field of PPD research, although none are implemented in clinical care. For the present study we aimed to develop and validate a prediction model to assess individualized risk of PPD and provide a tentative template for individualized risk calculation offering opportunities for additional external validation of this tool. Danish population registers served as our data sources and PPD was defined as recorded contact to a psychiatric treatment facility (ICD-10 code DF32-33) or redeemed antidepressant prescriptions (ATC code N06A), resulting in a sample of 6,402 PPD cases (development sample) and 2,379 (validation sample). Candidate predictors covered background information including cohabitating status, age, education, and previous psychiatric episodes in index mother (Core model), additional variables related to pregnancy and childbirth (Extended model), and further health information about the mother and her family (Extended+ model). Results indicated our recalibrated Extended model with 14 variables achieved highest performance with satisfying calibration and discrimination. Previous psychiatric history, maternal age, low education, and hyperemesis gravidarum were the most important predictors. Moving forward, external validation of the model represents the next step, while considering who will benefit from preventive PPD interventions, as well as considering potential consequences from false positive and negative test results, defined through different threshold values.

The S-100B level, intracranial pressure, body temperature, and transcranial blood flow velocities predict the outcome of the treatment of severe brain injury

This study evaluates the applicability of S100B levels, mean maximum velocity (Vmean) over time, pulsatility index (PI), intracranial pressure (ICP), and body temperature (T) for the prediction of the treatment of patients with traumatic brain injury (TBI). Sixty patients defined by the Glasgow Coma Scale score ≤ 8 were stratified using the Glasgow Coma Scale into 2 groups: favorable (FG: Glasgow Outcome Scale ≥ 4) and unfavorable (UG: Glasgow Outcome Scale < 4). The S100B concentration was at the time of hospital admission. Vmean was measured using transcranial Doppler. PI was derived from a transcranial Doppler examination. T was measured in the temporal artery. The differences in mean between FG and UG were tested using a bootstrap test of 10,000 repetitions with replacement. Changes in S100B, Vmean, PI, ICP, and T levels stratified by the group were calculated using the one-way aligned rank transform for nonparametric factorial analysis of variance. The reference ranges for the levels of S100B, Vmean, and PI were 0.05 to 0.23 µg/L, 30.8 to 73.17 cm/s, and 0.62 to 1.13, respectively. Both groups were defined by an increase in Vmean, a decrease in S100B, PI, and ICP levels; and a virtually constant T. The unfavorable outcome is defined by significantly higher levels of all parameters, except T. A favorable outcome is defined by S100B < 3 mg/L, PI < 2.86, ICP > 25 mm Hg, and Vmean > 40 cm/s. The relationships provided may serve as indicators of the results of the TBI treatment.

Machine learning predicts improvement of functional outcomes in traumatic brain injury patients after inpatient rehabilitation

Survivors of traumatic brain injury (TBI) have an unpredictable clinical course. This unpredictability makes clinical resource allocation for clinicians and anticipatory guidance for patients difficult. Historically, experienced clinicians and traditional statistical models have insufficiently considered all available clinical information to predict functional outcomes for a TBI patient. Here, we harness artificial intelligence and apply machine learning and statistical models to predict the Functional Independence Measure (FIM) scores after rehabilitation for traumatic brain injury (TBI) patients. Tree-based algorithmic analysis of 629 TBI patients admitted to a large acute rehabilitation facility showed statistically significant improvement in motor and cognitive FIM scores at discharge.

Basal cisternostomy for traumatic brain injury: A case report of unexpected good recovery

In subarachnoid hemorrhage following traumatic brain injury (TBI), the high intracisternal pressure drives the cerebrospinal fluid into the brain parenchyma, causing cerebral edema. Basal cisternostomy involves opening the basal cisterns to atmospheric pressure and draining cerebrospinal fluid in an attempt to reverse the edema. We describe a case of basal cisternostomy combined with decompressive craniectomy. A 35-year-old man with severe TBI following a road vehicle accident presented with acute subdural hematoma, Glasgow coma scale score of 6, fixed pupils and no corneal response. Opening of the basal cisterns and placement of a temporary cisternal drain led to immediate relaxation of the brain. The patient had a Glasgow coma scale score of 15 on postoperative day 6 and was discharged on day 10. We think basal cisternostomy is a feasible and effective procedure that should be considered in the management of TBI.

Prognostic value of day-of-injury plasma GFAP and UCH-L1 concentrations for predicting functional recovery after traumatic brain injury in patients from the US TRACK-TBI cohort: an observational cohort study

BACKGROUND

The prognostic value of glial fibrillary acidic protein (GFAP) and ubiquitin C-terminal hydrolase L1 (UCH-L1) as day-of-injury predictors of functional outcome after traumatic brain injury is not well understood. GFAP is a protein found in glial cells and UCH-L1 is found in neurons, and these biomarkers have been cleared to aid in decision making regarding whether brain CT should be performed after traumatic brain injury. We aimed to quantify their prognostic accuracy and investigate whether these biomarkers contribute novel prognostic information to existing clinical models.

METHODS

We enrolled patients from the Transforming Research and Clinical Knowledge in Traumatic Brain Injury (TRACK-TBI) observational cohort study. TRACK-TBI includes patients 17 years and older who are evaluated for TBI at 18 US level 1 trauma centres. All patients receive head CT at evaluation, have adequate visual acuity and hearing preinjury, and are fluent in either English or Spanish. In our analysis, we included participants aged 17-90 years who had day-of-injury plasma samples for measurement of GFAP and UCH-L1 and completed 6-month assessments for outcome due to traumatic brain injury with the Glasgow Outcome Scale-Extended (GOSE-TBI). Biomarkers were analysed as continuous variables and in quintiles. This study is registered with ClinicalTrials.gov, NCT02119182.

FINDINGS

We enrolled 2552 patients from Feb 26, 2014, to Aug 8, 2018. Of the 1696 participants with brain injury and data available at baseline and at 6 months who were included in the analysis, 120 (7·1%) died (GOSE-TBI=1), 235 (13·9%) had an unfavourable outcome (ie, GOSE-TBI ≤4), 1135 (66·9%) had incomplete recovery (ie, GOSE-TBI <8), and 561 (33·1%) recovered fully (ie, GOSE-TBI=8). The area under the curve (AUC) of GFAP for predicting death at 6 months in all patients was 0·87 (95% CI 0·83-0·91), for unfavourable outcome was 0·86 (0·83-0·89), and for incomplete recovery was 0·62 (0·59-0·64). The corresponding AUCs for UCH-L1 were 0·89 (95% CI 0·86-0·92) for predicting death, 0·86 (0·84-0·89) for unfavourable outcome, and 0·61 (0·59-0·64) for incomplete recovery at 6 months. AUCs were higher for participants with traumatic brain injury and Glasgow Coma Scale (GCS) score of 3-12 than for those with GCS score of 13-15. Among participants with GCS score of 3-12 (n=353), adding GFAP and UCH-L1 (alone or combined) to each of the three International Mission for Prognosis and Analysis of Clinical Trials in traumatic brain injury models significantly increased their AUCs for predicting death (AUC range 0·90-0·94) and unfavourable outcome (AUC range 0·83-0·89). However, among participants with GCS score of 13-15 (n=1297), adding GFAP and UCH-L1 to the UPFRONT study model modestly increased the AUC for predicting incomplete recovery (AUC range 0·69-0·69, p=0·025).

INTERPRETATION

In addition to their known diagnostic value, day-of-injury GFAP and UCH-L1 plasma concentrations have good to excellent prognostic value for predicting death and unfavourable outcome, but not for predicting incomplete recovery at 6 months. These biomarkers contribute the most prognostic information for participants presenting with a GCS score of 3-12.

FUNDING

US National Institutes of Health, National Institute of Neurologic Disorders and Stroke, US Department of Defense, One Mind, US Army Medical Research and Development Command.

Prediction of early prognosis after traumatic brain injury by multifactor model

AIMS

To design a model to predict the early prognosis of patients with traumatic brain injury (TBI) based on parameters that can be quickly obtained in emergency conditions from medical history, physical examination, and supplementary examinations.

METHODS

The medical records of TBI patients who were hospitalized in two medical institutions between June 2015 and June 2021 were collected and analyzed. Patients were divided into the training set, validation set, and testing set. The possible predictive indicators were screened after analyzing the data of patients in the training set. Then prediction models were found based on the possible predictive indicators in the training set. Data of patients in the validation set and the testing set was provided to validate the predictive values of the models.

RESULTS

Age, Glasgow coma scale score, Apolipoprotein E genotype, damage area, serum C-reactive protein, and interleukin-8 (IL-8) levels, and Marshall computed tomography score were found associated with early prognosis of TBI patients. The accuracy of the early prognosis prediction model (EPPM) was 80%, and the sensitivity and specificity of the EPPM were 78.8% and 80.8% in the training set. The accuracy of the EPPM was 79%, and the sensitivity and specificity of the EPPM were 66.7% and 86.2% in the validation set. The accuracy of the early EPPM was 69.1%, and the sensitivity and specificity of the EPPM were 67.9% and 77.8% in the testing set.

CONCLUSION

Prediction models integrating general information, clinical manifestations, and auxiliary examination results may provide a reliable and rapid method to evaluate and predict the early prognosis of TBI patients.

Prognostic Models in Severe Traumatic Brain Injury: A Systematic Review and Meta-analysis

This review aimed to analyze the results of investigations that performed external validation or that compared prognostic models to identify the models and their variations that showed the best performance in predicting mortality, survival, and unfavorable outcome after severe traumatic brain injury. Pubmed, Embase, Scopus, Web of Science, Cumulative Index to Nursing and Allied Health Literature, Google Scholar, TROVE, and Open Grey databases were searched. A total of 1616 studies were identified and screened, and 15 studies were subsequently included for analysis after applying the selection criteria. The Corticosteroid Randomization After Significant Head Injury (CRASH) and International Mission for Prognosis and Analysis of Clinical Trials in Traumatic Brain Injury (IMPACT) models were the most externally validated among studies of severe traumatic brain injury. The results of the review showed that most publications encountered an area under the curve ≥ 0.70. The area under the curve meta-analysis showed similarity between the CRASH and IMPACT models and their variations for predicting mortality and unfavorable outcomes. Calibration results showed that the variations of CRASH and IMPACT models demonstrated adequate calibration in most studies for both outcomes, but without a clear indication of uncertainties in the evaluations of these models. Based on the results of this meta-analysis, the choice of prognostic models for clinical application may depend on the availability of predictors, characteristics of the population, and trauma care services.

Development and validation of a prediction nomogram for a 6-month unfavorable prognosis in traumatic brain-injured patients undergoing primary decompressive craniectomy: An observational study

Objective

This study was designed to develop and validate a risk-prediction nomogram to predict a 6-month unfavorable prognosis in patients with traumatic brain-injured (TBI) undergoing primary decompressive craniectomy (DC).

Methods

The clinical data of 391 TBI patients with primary DC who were admitted from 2012 to 2020 were reviewed, from which 274 patients were enrolled in the training group, while 117 were enrolled in the internal validation group, randomly. The external data sets containing 80 patients were obtained from another hospital. Independent predictors of the 6-month unfavorable prognosis were analyzed using multivariate logistic regression. Furthermore, a nomogram prediction model was constructed using R software. After evaluation of the model, internal and external validations were performed to verify the efficiency of the model using the area under the receiver operating characteristic curves and the calibration plots.

Results

In multivariate analysis, age(p = 0.001), Glasgow Score Scale (GCS) (p < 0.001), operative blood loss of >750 ml (p = 0.045), completely effaced basal cisterns (p < 0.001), intraoperative hypotension(p = 0.001), and activated partial thromboplastin time (APTT) of >36 (p = 0.012) were the early independent predictors for 6-month unfavorable prognosis in patients with TBI after primary DC. The AUC for the training, internal, and external validation cohorts was 0.93 (95%CI, 0.89–0.96, p < 0.0001), 0.89 (95%CI, 0.82–0.94, p < 0.0001), and 0.90 (95%CI, 0.84–0.97, p < 0.0001), respectively, which indicated that the prediction model had an excellent capability of discrimination. Calibration of the model was exhibited by the calibration plots, which showed an optimal concordance between the predicted 6-month unfavorable prognosis probability and actual probability in both training and validation cohorts.

Conclusion

This prediction model for a 6-month unfavorable prognosis in patients with TBI undergoing primary DC can evaluate the prognosis accurately and enhance the early identification of high-risk patients.

Predicting Clinical Outcomes 7-10 Years after Severe Traumatic Brain Injury: Exploring the Prognostic Utility of the IMPACT Lab Model and Cerebrospinal Fluid UCH-L1 and MAP-2

BACKGROUND

Severe traumatic brain injury (TBI) is a major contributor to disability and mortality in the industrialized world. Outcomes of severe TBI are profoundly heterogeneous, complicating outcome prognostication. Several prognostic models have been validated for acute prediction of 6-month global outcomes following TBI (e.g., morbidity/mortality). In this preliminary observational prognostic study, we assess the utility of the International Mission on Prognosis and Analysis of Clinical Trials in TBI (IMPACT) Lab model in predicting longer term global and cognitive outcomes (7-10 years post injury) and the extent to which cerebrospinal fluid (CSF) biomarkers enhance outcome prediction.

METHODS

Very long-term global outcome was assessed in a total of 59 participants (41 of whom did not survive their injuries) using the Glasgow Outcome Scale-Extended and Disability Rating Scale. More detailed outcome information regarding cognitive functioning in daily life was collected from 18 participants surviving to 7-10 years post injury using the Cognitive Subscale of the Functional Independence Measure. A subset (n = 10) of these participants also completed performance-based cognitive testing (Digit Span Test) by telephone. The IMPACT lab model was applied to determine its prognostic value in relation to very long-term outcomes as well as the additive effects of acute CSF ubiquitin C-terminal hydrolase-L1 (UCH-L1) and microtubule associated protein 2 (MAP-2) concentrations.

RESULTS

The IMPACT lab model discriminated favorable versus unfavorable 7- to 10-year outcome with an area under the receiver operating characteristic curve of 0.80. Higher IMPACT lab model risk scores predicted greater extent of very long-term morbidity (β = 0.488 p = 0.000) as well as reduced cognitive independence (β =  - 0.515, p = 0.034). Acute elevations in UCH-L1 levels were also predictive of lesser independence in cognitive activities in daily life at very long-term follow-up (β = 0.286, p = 0.048). Addition of two CSF biomarkers significantly improved prediction of very long-term neuropsychological performance among survivors, with the overall model (including IMPACT lab score, UCH-L1, and MAP-2) explaining 89.6% of variance in cognitive performance 7-10 years post injury (p = 0.008). Higher acute UCH-L1 concentrations were predictive of poorer cognitive performance (β =  - 0.496, p = 0.029), whereas higher acute MAP-2 concentrations demonstrated a strong cognitive protective effect (β = 0.679, p = 0.010).

CONCLUSIONS

Although preliminary, results suggest that existing prognostic models, including models with incorporation of CSF markers, may be applied to predict outcome of severe TBI years after injury. Continued research is needed examining early predictors of longer-term outcomes following TBI to identify potential targets for clinical trials that could impact long-ranging functional and cognitive outcomes.

Prognostic Value of Serum Procalcitonin Based Model in Moderate to Severe Traumatic Brain Injury Patients

Objective

Procalcitonin (PCT) is an acknowledged marker of systemic inflammatory response. Previous studies have not reached agreement on the association between serum PCT and outcome of traumatic brain injury (TBI) patients. We designed this study to confirm the prognostic value of PCT in isolated TBI and those with extracranial injury, respectively.

Methods

Patients hospitalized in our hospital for moderate-to-severe TBI between March 2015 and December 2019 were included. Logistic regression analysis was performed to validate the association between PCT and in-hospital mortality in these patients. AUC (area under the receiver operating characteristics curve) of PCT and constructed model were calculated and compared.

Results

Among the included 211 patients, 81 patients suffered a poor outcome, with a mortality rate of 38.4%. Non-survivors had a higher level of serum PCT (2.73 vs 0.72, p<0.001) and lower GCS (5 vs 7, p<0.001) on admission than survivors. AUC of single PCT for predicting mortality in isolated TBI and those with extracranial injury were 0.767 and 0.553, respectively. Multivariate logistic regression showed that GCS (OR=0.744, p=0.008), glucose (OR=1.236, p<0.001), cholesterol (OR=0.526, p=0.002), and PCT (OR=1.107, p=0.022) were independently associated with mortality of isolated TBI. The AUC of the prognostic model composed of GCS, glucose, cholesterol, and PCT was 0.868 in isolated TBI.

Conclusion

PCT is an efficient marker of outcome in isolated moderate-to-severe TBI but not those with extracranial injury. A prognostic model incorporating PCT is useful for clinicians to make early risk stratification for isolated TBI.

Outcome Prediction in Patients with Severe Traumatic Brain Injury Using Deep Learning from Head CT Scans

Background After severe traumatic brain injury (sTBI), physicians use long-term prognostication to guide acute clinical care yet struggle to predict outcomes in comatose patients. Purpose To develop and evaluate a prognostic model combining deep learning of head CT scans and clinical information to predict long-term outcomes after sTBI. Materials and Methods This was a retrospective analysis of two prospectively collected databases. The model-building set included 537 patients (mean age, 40 years ± 17 [SD]; 422 men) from one institution from November 2002 to December 2018. Transfer learning and curriculum learning were applied to a convolutional neural network using admission head CT to predict mortality and unfavorable outcomes (Glasgow Outcomes Scale scores 1-3) at 6 months. This was combined with clinical input for a holistic fusion model. The models were evaluated using an independent internal test set and an external cohort of 220 patients with sTBI (mean age, 39 years ± 17; 166 men) from 18 institutions in the Transforming Research and Clinical Knowledge in Traumatic Brain Injury (TRACK-TBI) study from February 2014 to April 2018. The models were compared with the International Mission on Prognosis and Analysis of Clinical Trials in TBI (IMPACT) model and the predictions of three neurosurgeons. Area under the receiver operating characteristic curve (AUC) was used as the main model performance metric. Results The fusion model had higher AUCs than did the IMPACT model in the prediction of mortality (AUC, 0.92 [95% CI: 0.86, 0.97] vs 0.80 [95% CI: 0.71, 0.88]; P < .001) and unfavorable outcomes (AUC, 0.88 [95% CI: 0.82, 0.94] vs 0.82 [95% CI: 0.75, 0.90]; P = .04) on the internal data set. For external TRACK-TBI testing, there was no evidence of a significant difference in the performance of any models compared with the IMPACT model (AUC, 0.83; 95% CI: 0.77, 0.90) in the prediction of mortality. The Imaging model (AUC, 0.73; 95% CI: 0.66-0.81; P = .02) and the fusion model (AUC, 0.68; 95% CI: 0.60, 0.76; P = .02) underperformed as compared with the IMPACT model (AUC, 0.83; 95% CI: 0.77, 0.89) in the prediction of unfavorable outcomes. The fusion model outperformed the predictions of the neurosurgeons. Conclusion A deep learning model of head CT and clinical information can be used to predict 6-month outcomes after severe traumatic brain injury. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Haller in this issue.

Insulin resistance is associated with an unfavorable outcome among non-diabetic patients with isolated moderate-to-severe traumatic brain injury – A propensity score-matched study

Background

Hyperglycemia is an independent risk factor for the poor prognosis in patients with traumatic brain injury (TBI), and stress-induced impaired insulin function is the major factor of hyperglycemia in non-diabetic patients with TBI. Several types of research suggested that insulin resistance (IR) is related to the poor prognosis of neurocritical ill patients; here we focused on the role of IR in non-diabetic patients after TBI.

Methods

We performed a prospective observational study with the approval of the Ethics Committee of our institute. IR was accessed via the update Homeostasis Model Assessment (HOMA2) of IR, a computer-calculated index by glucose and insulin level. HOMA2 ≥ 1.4 was considered as the threshold of IR according to the previous studies. The glycemic variability (GV) indices were calculated by fingertip blood glucose concentration at an interval of 2 h within 24 h to explore the relationship between IR and GV. The outcome was the 6-month neurological outcome evaluated with the Glasgow outcome scale.

Results

A total of 85 patients with isolated moderate-to-severe TBI (admission GCS ≤ 12) were finally included in our study, 34 (40%) were diagnosed with IR with HOMA2 ≥ 1.4. After propensity score matching (PSM), 22 patients in IR group were matched to 34 patients in non-IR group. Patients with IR suffered increased systemic glycemic variation after isolated moderate-to-severe TBI. IR was a significant factor for the poor prognosis after TBI (OR = 3.25, 95% CI 1.03–10.31, p = 0.041).

Conclusions

The IR estimated by HOMA2 was associated with greater GV and an unfavorable outcome after isolated moderate-to-severe TBI. Ameliorating impaired insulin sensitivity may be a potential therapeutic strategy for the management of TBI patients.

Harmonization-Information Trade-Offs for Sharing Individual Participant Data in Biomedicine

Biomedical practice is evidence-based. Peer-reviewed papers are the primary medium to present evidence and data-supported results to drive clinical practice. However, it could be argued that scientific literature does not contain data, but rather narratives about and summaries of data. Meta-analyses of published literature may produce biased conclusions due to the lack of transparency in data collection, publication bias, and inaccessibility to the data underlying a publication ('dark data'). Co-analysis of pooled data at the level of individual research participants can offer higher levels of evidence, but this requires that researchers share raw individual participant data (IPD). FAIR (findable, accessible, interoperable, and reusable) data governance principles aim to guide data lifecycle management by providing a framework for actionable data sharing. Here we discuss the implications of FAIR for data harmonization, an essential step for pooling data for IPD analysis. We describe the harmonization-information trade-off, which states that the level of granularity in harmonizing data determines the amount of information lost. Finally, we discuss a framework for managing the trade-off and the levels of harmonization. In the coming era of funder mandates for data sharing, research communities that effectively manage data harmonization will be empowered to harness big data and advanced analytics such as machine learning and artificial intelligence tools, leading to stunning new discoveries that augment our understanding of diseases and their treatments. By elevating scientific data to the status of a first-class citizen of the scientific enterprise, there is strong potential for biomedicine to transition from a narrative publication product orientation to a modern data-driven enterprise where data itself is viewed as a primary work product of biomedical research.

Clustering identifies endotypes of traumatic brain injury in an intensive care cohort: a CENTER-TBI study

BACKGROUND

While the Glasgow coma scale (GCS) is one of the strongest outcome predictors, the current classification of traumatic brain injury (TBI) as 'mild', 'moderate' or 'severe' based on this fails to capture enormous heterogeneity in pathophysiology and treatment response. We hypothesized that data-driven characterization of TBI could identify distinct endotypes and give mechanistic insights.

METHODS

We developed an unsupervised statistical clustering model based on a mixture of probabilistic graphs for presentation (< 24 h) demographic, clinical, physiological, laboratory and imaging data to identify subgroups of TBI patients admitted to the intensive care unit in the CENTER-TBI dataset (N = 1,728). A cluster similarity index was used for robust determination of optimal cluster number. Mutual information was used to quantify feature importance and for cluster interpretation.

RESULTS

Six stable endotypes were identified with distinct GCS and composite systemic metabolic stress profiles, distinguished by GCS, blood lactate, oxygen saturation, serum creatinine, glucose, base excess, pH, arterial partial pressure of carbon dioxide, and body temperature. Notably, a cluster with 'moderate' TBI (by traditional classification) and deranged metabolic profile, had a worse outcome than a cluster with 'severe' GCS and a normal metabolic profile. Addition of cluster labels significantly improved the prognostic precision of the IMPACT (International Mission for Prognosis and Analysis of Clinical trials in TBI) extended model, for prediction of both unfavourable outcome and mortality (both p < 0.001).

CONCLUSIONS

Six stable and clinically distinct TBI endotypes were identified by probabilistic unsupervised clustering. In addition to presenting neurology, a profile of biochemical derangement was found to be an important distinguishing feature that was both biologically plausible and associated with outcome. Our work motivates refining current TBI classifications with factors describing metabolic stress. Such data-driven clusters suggest TBI endotypes that merit investigation to identify bespoke treatment strategies to improve care. Trial registration The core study was registered with ClinicalTrials.gov, number NCT02210221 , registered on August 06, 2014, with Resource Identification Portal (RRID: SCR_015582).

Development and Verification of Prognostic Prediction Models for Patients with Brain Trauma Based on Coagulation Function Indexes

Objective

To assess the effect of adding coagulation indices to the currently existing prognostic prediction models of traumatic brain injury (TBI) in the prediction of outcome.

Methods

A total of 210 TBI patients from 2017 to 2019 and 131 TBI patients in 2020 were selected for development and internal verification of the new model. The primary outcomes include death at 14 days and Glasgow Outcome Score (GOS) at 6 months. The performance of each model is evaluated by means of discrimination (area under the curve (AUC)), calibration (Hosmer-Lemeshow (H-L) goodness-of-fit test), and precision (Brier score).

Results

The IMPACT Core model showed better prediction ability than the CRASH Basic model. Adding one coagulation index at a time to the IMPACT Core model, the new combined models IMPACT Core+FIB and IMPACT Core+APTT are optimal for the 6-month unfavorable outcome and 6-month mortality, respectively (AUC, 0.830 and 0.878). The new models were built based on the regression coefficients of the models. Internal verification indicated that for the prediction of 6-month unfavorable outcome and 6-month mortality, both the IMPACT Core+FIB model and the IMPACT Core+APTT model show better discrimination (AUC, 0.823 vs. 0.818 and 0.853 vs. 0.837), better calibration (HL, p = 0.114 and p = 0.317) and higher precision (Brier score, 0.148 vs. 0.141 and 0.147 vs. 0.164), respectively, than the original models.

Conclusion

Our research shows that the combination of the traumatic brain injury prognostic models and coagulation indices can improve the 6-month outcome prediction of patients with TBI.