Radiological Parameters to Predict Hemorrhagic Progression of Traumatic Contusional Brain Injury

A machine learning model to predict neurological deterioration after mild traumatic brain injury in older adults

Objective

Neurological deterioration after mild traumatic brain injury (TBI) has been recognized as a poor prognostic factor. Early detection of neurological deterioration would allow appropriate monitoring and timely therapeutic interventions to improve patient outcomes. In this study, we developed a machine learning model to predict the occurrence of neurological deterioration after mild TBI using information obtained on admission.

Methods

This was a retrospective cohort study of data from the Think FAST registry, a multicenter prospective observational study of elderly TBI patients in Japan. Patients with an admission Glasgow Coma Scale (GCS) score of 12 or below or who underwent surgical treatment immediately upon admission were excluded. Neurological deterioration was defined as a decrease of 2 or more points from a GCS score of 13 or more within 24 h of hospital admission. The model predictive accuracy was judged with the area under the receiver operating characteristic curve (AUROC) and the area under the precision-recall curve (AUPRC), and the Youden index was used to determine the cutoff value.

Results

A total of 421 of 721 patients registered in the Think FAST registry between December 2019 and May 2021 were included in our study, among whom 25 demonstrated neurological deterioration. Among several machine learning algorithms, eXtreme Gradient Boosting (XGBoost) demonstrated the highest predictive accuracy in cross-validation, with an AUROC of 0.81 (±0.07) and an AUPRC of 0.33 (±0.08). Through SHapley Additive exPlanations (SHAP) analysis, five important features (D-dimer, fibrinogen, acute subdural hematoma thickness, cerebral contusion size, and systolic blood pressure) were identified and used to construct a better performing model (cross-validation AUROC of 0.84 and AUPRC of 0.34; testing data AUROC of 0.77 and AUPRC of 0.19). At the cutoff value from the Youden index, the model showed a sensitivity, specificity, and positive predictive value of 60, 96, and 38%, respectively. When neurosurgeons attempted to predict neurological deterioration using the same testing data, their values were 20, 94, and 19%, respectively.

Conclusion

In this study, our predictive model showed an acceptable performance in detecting neurological deterioration after mild TBI. Further validation through prospective studies is necessary to confirm these results.

Prediction of prognosis in patients with cerebral contusions based on machine learning

Traumatic brain injury (TBI) is a global issue and a major cause of patient mortality, and cerebral contusions (CCs) is a common primary TBI. The haemorrhagic progression of a contusion (HPC) poses a significant risk to patients' lives, and effectively predicting changes in haematoma volume is an urgent clinical challenge that needs to be addressed. As a branch of artificial intelligence, machine learning (ML) can proficiently handle a wide range of complex data and identify connections between data for tasks such as prediction and decision making. We collected data from 673 CCs patients who were hospitalized in the neurosurgery department of The First Affiliated Hospital of Wannan Medical College (Yijishan Hospital of Wannan Medical College) from September 2019 to September 2022. Selecting three popular machine learning algorithms, Decision Tree (DT), Random Forest (RF), and Multilayer Perceptron (MLP) to predict hematoma. Machine learning algorithms were run on the Python 3.9 platform. The model was evaluated for sensitivity, specificity, F1 score, accuracy, receiver operating characteristic (ROC) curves, and the area under the receiver operating characteristic curve (AUC). Using sensitivity as the evaluation metric, the best model is DT model. The DT model included the initial haematoma volume, GCS score, Fib level, blood sugar level, multiple CCs, Male, PT, blood sodium level and PLT count. The evaluation indicators of the DT model were as follows: sensitivity = 0.9545 (0.857, 1.0), specificity = 0.9803 (0.9602, 0.9952), F1 score = 0.8936 (0.7742, 0.9778), accuracy = 0.9778 (0.9556, 0.9956), and AUC-ROC = 0.9674 (0.9143, 0.9975). The DT model is the machine learning algorithm most closely aligned with the research objectives, allowing for the scientific and effective prediction of hematoma changes.

An updated review for clinical and radiological predictors of acute intraparenchymal hematoma progression in cerebral contusion

Backgrounds

The rapid expansion of an intraparenchymal hematoma following cerebral contusion often results in high mortality rates and a poor prognosis. Effective tools are essential for predicting and monitoring the incidence of traumatic intraparenchymal hematoma (tICH) and identifying patients at high risk of tICH expansion. This enables timely surgical interventions and appropriate medical management. Recently, numerous novel predictive tools have been developed and employed to predict tICH progression. Therefore, this review aims to outline the latest advancements in predicting tICH expansion.

Methods

To find relevant studies, a search was conducted on PubMed and Google Scholar for articles published from January 2020 to April 2024. The search string used was (Cerebral Contusion) AND (Intraparenchymal Hematoma Progression OR Parenchymal Hematoma Expansion OR Intracerebral Hemorrhage Progression) AND (Predictor or Forecasting Tool).

Results

In this narrative review, we focused on various radiological, clinical, and innovative indicators of acute tICH progression that have been developed and/or validated in recently years. Additionally, we explore the impact of tICH progression on long-term outcomes, suggesting potential avenues for future research. The spread of depolarization in the cortex could be a key factor in forecasting and controlling the growth of tICH in the times ahead.

Conclusions

This study offers a comprehensive look at various cutting-edge imaging predictors, inflammatory indices, and integrated predictors that can aid neurosurgeons in categorizing, handling, and treating high-risk patients with acute tICH expansion.

A Nomogram to Predict Intracranial Hypertension in Moderate Traumatic Brain Injury Patients

OBJECTIVE

Patients with moderate traumatic brain injury (mTBI) are under the threat of intracranial hypertension (IHT). However, it is unclear which mTBI patient will develop IHT and should receive intracranial pressure (ICP)-lowering treatment or invasive ICP monitoring after admission. The purpose of the present study was to develop and validate a prediction model that estimates the risk of IHT in mTBI patients.

METHODS

Baseline data collected on admission of 296 mTBI patients with Glasgow Coma Scale (GCS) score of 9-11 was collected and analyzed. Multivariable logistic regression modeling with backward stepwise elimination was used to develop a prediction model for IHT. The discrimination efficacy, calibration efficacy, and clinical utility of the prediction model were evaluated. Finally, the prediction model was validated in a separate cohort of 122 patients from 3 hospitals.

RESULTS

Four independent prognostic factors for IHT were identified: GCS score, Marshall head computed tomography score, injury severity score, and location of contusion. The C-statistic of the prediction model in internal validation was 84.30% (95% CI: 0.794-0.892). The area under the curve for the prediction model in external validation was 82.80% (95% CI: 0.747-0.909).

CONCLUSIONS

A prediction model based on baseline parameters was found to be highly sensitive in distinguishing mTBI patients with GCS score of 9-11 who would suffer IHT. The high discriminative ability of the prediction model supports its use in identifying mTBI patients with GCS score of 9-11 who need ICP-lowering therapy or invasive ICP monitoring.

Imaging predictors of hemorrhagic progression of a contusion after traumatic brain injury: a systematic review and meta-analysis

The hemorrhagic progression of a contusion (HPC) after Traumatic brain injury (TBI) is one of the important causes of death in trauma patients. The purpose of this meta-analysis was to evaluate the predictive effect of imaging features of Computed tomography (CT) on HPC after TBI. A comprehensive systematic search was performed using PubMed, EMBASE, and WEB OF SCIENCE databases to identify all relevant literature. A total of 8 studies involving 2543 patients were included in this meta-analysis. Meta-analysis showed that subarachnoid hemorrhage (OR 3.28; 95% CI 2.57-4.20), subdural hemorrhage (OR 4.35; 95% CI 3.29-5.75), epidural hemorrhage (OR 1.47;95% CI 1.15-1.89), contrast extravasation (OR 11.81; 95% CI 4.86-28.71) had a predictive effect on the occurrence of HPC. Skull fracture (OR 1.64; 95% CI 0.84-3.19) showed no statistical significance, and midline displacement > 5 mm (OR 4.66; 95% CI 1.87-11.62) showed high heterogeneity. The results of this meta-analysis showed that some imaging features were effective predictors of HPC after TBI. Well-designed prospective studies are needed to more accurately assess the effective predictors of HPC after TBI.

Management of Antithrombotic Drugs in Patients with Isolated Traumatic Brain Injury: An Intersociety Consensus Document

BACKGROUND

All available recommendations about the management of antithrombotic therapies (ATs) in patients who experienced traumatic brain injury (TBI) are mainly based on expert opinion because of the lack of strength in the available evidence-based medicine. Currently, the withdrawal and the resumption of AT in these patients is empirical, widely variable, and based on the individual assessment of the attending physician. The main difficulty is to balance the thrombotic and hemorrhagic risks to improve patient outcome.

METHODS

Under the endorsement of the Neurotraumatology Section of Italian Society of Neurosurgery, the Italian Society for the Study about Haemostasis and Thrombosis, the Italian Society of Anaesthesia, Analgesia, Resuscitation, and Intensive Care, and the European Association of Neurosurgical Societies, a working group (WG) of clinicians completed two rounds of questionnaires, using the Delphi method, in a multidisciplinary setting. A table for thrombotic and bleeding risk, with a dichotomization in high risk and low risk, was established before questionnaire administration. In this table, the risk is calculated by matching different isolated TBI (iTBI) scenarios such as acute and chronic subdural hematomas, extradural hematoma, brain contusion (intracerebral hemorrhage), and traumatic subarachnoid hemorrhage with patients under active AT treatment. The registered indication could include AT primary prevention, cardiac valve prosthesis, vascular stents, venous thromboembolism, and atrial fibrillation.

RESULTS

The WG proposed a total of 28 statements encompassing the most common clinical scenarios about the withdrawal of antiplatelets, vitamin K antagonists, and direct oral anticoagulants in patients who experienced blunt iTBI. The WG voted on the grade of appropriateness of seven recommended interventions. Overall, the panel reached an agreement for 20 of 28 (71%) questions, deeming 11 of 28 (39%) as appropriate and 9 of 28 (32%) as inappropriate interventions. The appropriateness of intervention was rated as uncertain for 8 of 28 (28%) questions.

CONCLUSIONS

The initial establishment of a thrombotic and/or bleeding risk scoring system can provide a vital theoretical basis for the evaluation of effective management in individuals under AT who sustained an iTBI. The listed recommendations can be implemented into local protocols for a more homogeneous strategy. Validation using large cohorts of patients needs to be developed. This is the first part of a project to update the management of AT in patients with iTBI.

Predictive models for occurrence of expansive intracranial hematomas and surgical evacuation outcomes in traumatic brain injury patients in Uganda: A prospective cohort study

BACKGROUND

Hematoma expansion is a common manifestation of acute intracranial hemorrhage (ICH) which is associated with poor outcomes and functional status. Objective We determined the prevalence of expansive intracranial hematomas (EIH) and assessed the predictive model for EIH occurrence and surgical evacuation outcomes in patients with traumatic brain injury (TBI) in Uganda. Methods We recruited adult patients with TBI with intracranial hematomas in a prospective cohort study. Data analysis using logistic regression to identify relevant risk factors, assess the interactions between variables, and developing a predictive model for EIH occurrence and surgical evacuation outcomes in TBI patients was performed. The predictive accuracies of these algorithms were compared using the area under the receiver operating characteristic curve (AUC). A p-values of < 0.05 at a 95% Confidence interval (CI) was considered significant. Results A total of 324 study participants with intracranial hemorrhage were followed up for 6 months after surgery. About 59.3% (192/324) had expansive intracranial hemorrhage. The study participants with expansive intracranial hemorrhage had poor quality of life at both 3 and 6-months with p < 0.010 respectively. Among the 5 machine learning algorithms, the random forest performed the best in predicting EIH in both the training cohort (AUC = 0.833) and the validation cohort (AUC = 0.734). The top five features in the random forest algorithm-based model were subdural hematoma, diffuse axonal injury, systolic and diastolic blood pressure, association between depressed fracture and subdural hematoma. Other models demonstrated good discrimination with AUC for intraoperative complication (0.675) and poor discrimination for mortality (0.366) after neurosurgical evacuation in TBI patients. Conclusion Expansive intracranial hemorrhage is common among patients with traumatic brain injury in Uganda. Early identification of patients with subdural hematoma, diffuse axonal injury, systolic and diastolic blood pressure, association between depressed fracture and subdural hematoma, were crucial in predicting EIH and intraoperative complications.

Burden, risk factors, neurosurgical evacuation outcomes, and predictors of mortality among traumatic brain injury patients with expansive intracranial hematomas in Uganda: a mixed methods study design

BACKGROUND

Expansive intracranial hematomas (EIH) following traumatic brain injury (TBI) continue to be a public health problem in Uganda. Data is limited regarding the neurosurgical outcomes of TBI patients. This study investigated the neurosurgical outcomes and associated risk factors of EIH among TBI patients at Mulago National Referral Hospital (MNRH).

METHODS

A total of 324 subjects were enrolled using a prospective cohort study. Socio-demographic, risk factors and complications were collected using a study questionnaire. Study participants were followed up for 180 days. Univariate, multivariable, Cox regression analyses, Kaplan Meir survival curves, and log rank tests were sequentially conducted. P-values of < 0.05 at 95% Confidence interval (CI) were considered to be statistically significant.

RESULTS

Of the 324 patients with intracranial hematomas, 80.6% were male. The mean age of the study participants was 37.5 ± 17.4 years. Prevalence of EIH was 59.3% (0.59 (95% CI: 0.54 to 0.65)). Participants who were aged 39 years and above; PR = 1.54 (95% CI: 1.20 to 1.97; P = 0.001), and those who smoke PR = 1.21 (95% CI: 1.00 to 1.47; P = 0.048), and presence of swirl sign PR = 2.26 (95% CI: 1.29 to 3.95; P = 0.004) were found to be at higher risk for EIH. Kaplan Meier survival curve indicated that mortality at the 16-month follow-up was 53.4% (95% CI: 28.1 to 85.0). Multivariate Cox regression indicated that the predictors of mortality were old age, MAP above 95 mmHg, low GCS, complications such as infection, spasticity, wound dehiscence, CSF leaks, having GOS < 3, QoLIBRI < 50, SDH, contusion, and EIH.

CONCLUSION

EIH is common in Uganda following RTA with an occurrence of 59.3% and a 16-month higher mortality rate. An increased age above 39 years, smoking, having severe systemic disease, and the presence of swirl sign are independent risk factors. Old age, MAP above 95 mmHg, low GCS, complications such as infection, spasticity, wound dehiscence, CSF leaks, having a GOS < 3, QoLIBRI < 50, ASDH, and contusion are predictors of mortality. These findings imply that all patients with intracranial hematomas (IH) need to be monitored closely and a repeat CT scan to be done within a specific period following their initial CT scan. We recommend the development of a protocol for specific surgical and medical interventions that can be implemented for patients at moderate and severe risk for EIH.

Glibenclamide for Brain Contusions: Contextualizing a Promising Clinical Trial Design that Leverages an Imaging-Based TBI Endotype

TBI heterogeneity is recognized as a major impediment to successful translation of therapies that could improve morbidity and mortality after injury. This heterogeneity exists on multiple levels including primary injury, secondary injury/host-response, and recovery. One widely accepted type of primary-injury related heterogeneity is pathoanatomic-the intracranial compartment that is predominantly affected, which can include any combination of subdural, subarachnoid, intraparenchymal, diffuse axonal, intraventricular and epidural hemorrhages. Intraparenchymal contusions carry the highest risk for progression. Contusion expansion is one of the most important drivers of death and disability after TBI. Over the past decade, there has been increasing evidence of the role of the sulfonylurea-receptor 1-transient receptor potential melastatin 4 (SUR1-TRPM4) channel in secondary injury after TBI, including progression of both cerebral edema and intraparenchymal hemorrhage. Inhibition of SUR1-TRPM4 with glibenclamide has shown promising results in preclinical models of contusional TBI with benefits against cerebral edema, secondary hemorrhage progression of the contusion, and improved functional outcome. Early-stage human research supports the key role of this pathway in contusion expansion and suggests a benefit with glibenclamide inhibition. ASTRAL is an ongoing international multi-center double blind multidose placebo-controlled phase-II clinical trial evaluating the safety and efficacy of an intravenous formulation of glibenclamide (BIIB093). ASTRAL is a unique and innovative study that addresses TBI heterogeneity by limiting enrollment to patients with the TBI pathoanatomic endotype of brain contusion and using contusion-expansion (a mechanistically linked secondary injury) as its primary outcome. Both criteria are consistent with the strong supporting preclinical and molecular data. In this narrative review, we contextualize the development and design of ASTRAL, including the need to address TBI heterogeneity, the scientific rationale underlying the focus on brain contusions and contusion-expansion, and the preclinical and clinical data supporting benefit of SUR1-TRPM4 inhibition in this specific endotype. Within this framework, we summarize the current study design of ASTRAL which is sponsored by Biogen and actively enrolling with a goal of 160 participants.

Predictors of radiological contusion progression in traumatic brain injury

BACKGROUND

Traumatic brain injury, mainly caused by the unintentional falls and motor vehicle accidents, is a serious condition encompassing a spectrum of pathological features from axonal to hemorrhagic injuries. Among these, cerebral contusions significantly contribute to death and disability following the injury and occur in up to 35% of cases. This study aimed to investigate the predictors of radiological contusion progression in traumatic brain injury.

METHODS

We performed a retrospective cross-sectional study using the files of the patients with mild traumatic brain injury who had cerebral contusions from 21 March 2021 to 20 March 2022. The severity of brain injury was determined using the Glasgow Coma Score. Furthermore, we used a cut-off value of a 30% increase in contusion size in the secondary CT scans (up to 72 hours) compared to the first one to define the significant progression of the contusions. For the patients with multiple contusions, we measured the biggest contusion.

RESULTS

705 patients with traumatic brain injury were found, the severity of the injury was mild in 498 of them, and 218 had cerebral contusions. 131 (60.1%) patients were injured in vehicle accidents. 111 (50.9%) had significant contusion progression. Most patients were conservatively managed, but 21 out of them (10%) required delayed surgical intervention.

CONCLUSION

We found that the presence of subdural hematoma, subarachnoid hemorrhage, and epidural hematoma were predictors of radiological contusion progression, and the patients with a subdural hematoma and epidural hematoma were more likely to undergo surgery. In addition to providing prognostic information, predicting risk factors for the progression of the contusions is crucial for identifying patients who might benefit from surgical and critical care therapies.

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.

Prediction of Intraparenchymal Hemorrhage Progression and Neurologic Outcome in Traumatic Brain Injury Patients Using Radiomics Score and Clinical Parameters

(1) Background: Radiomics analysis of spontaneous intracerebral hemorrhages on computed tomography (CT) images has been proven effective in predicting hematoma expansion and poor neurologic outcome. In contrast, there is limited evidence on its predictive abilities for traumatic intraparenchymal hemorrhage (IPH). (2) Methods: A retrospective analysis of 107 traumatic IPH patients was conducted. Among them, 45 patients (42.1%) showed hemorrhagic progression of contusion (HPC) and 51 patients (47.7%) had poor neurological outcome. The IPH on the initial CT was manually segmented for radiomics analysis. After feature extraction, selection and repeatability evaluation, several machine learning algorithms were used to derive radiomics scores (R-scores) for the prediction of HPC and poor neurologic outcome. (3) Results: The AUCs for R-scores alone to predict HPC and poor neurologic outcome were 0.76 and 0.81, respectively. Clinical parameters were used to build comparison models. For HPC prediction, variables including age, multiple IPH, subdural hemorrhage, Injury Severity Score (ISS), international normalized ratio (INR) and IPH volume taken together yielded an AUC of 0.74, which was significantly (p = 0.022) increased to 0.83 after incorporation of the R-score in a combined model. For poor neurologic outcome prediction, clinical variables of age, Glasgow Coma Scale, ISS, INR and IPH volume showed high predictability with an AUC of 0.92, and further incorporation of the R-score did not improve the AUC. (4) Conclusion: The results suggest that radiomics analysis of IPH lesions on initial CT images has the potential to predict HPC and poor neurologic outcome in traumatic IPH patients. The clinical and R-score combined model further improves the performance of HPC prediction.

Evaluation of Traumatic Subdural Hematoma Volume by Using Image Segmentation Assessment Based on Deep Learning

Rapid and accurate evaluations of hematoma volume can guide the treatment of traumatic subdural hematoma. We aim to explore the consistency between the measurement results of traumatic subdural hematoma (TSDH) using a deep learn-based image segmentation algorithm. A retrospective study was conducted on 90 CT images of patients diagnosed with TSDH in our hospital from January 2019 to January 2022. All image data were measured by manual segmentation, convolutional neural networks (CNN) algorithm segmentation, and ABC/2 volume formula. With manual segmentation as the “golden standard,” a consistency test was carried out with CNN algorithm segmentation and ABC/2 volume formula, respectively. The percentage error of CNN algorithm segmentation is less than ABC/2 volume formula. There is no significant difference between CNN algorithm segmentation and manual segmentation (P > 0.05). The area under curve of the ABC/2 volume formula, manual segmentation, and CNN algorithm segmentation is 0.811 (95% CI: 0.717~0.905), 0.840 (95% CI: 0.753~0.928), and 0.832 (95% CI: 0.742~0.922), respectively. From our results, the algorithm based on CNN has a good efficiency in segmentation and accurate calculation of TSDH hematoma volume.

Radiomics Features on Computed Tomography Combined With Clinical-Radiological Factors Predicting Progressive Hemorrhage of Cerebral Contusion

Background

Traumatic brain injury (TBI) is the main cause of death and severe disability in young adults worldwide. Progressive hemorrhage (PH) worsens the disease and can cause a poor neurological prognosis. Radiomics analysis has been used for hematoma expansion of hypertensive intracerebral hemorrhage. This study attempts to develop an optimal radiomics model based on non-contrast CT to predict PH by machine learning (ML) methods and compare its prediction performance with clinical-radiological models.

Methods

We retrospectively analyzed 165 TBI patients, including 89 patients with PH and 76 patients without PH, whose data were randomized into a training set and a testing set at a ratio of 7:3. A total of 10 different machine learning methods were used to predict PH. Univariate and multivariable logistic regression analyses were implemented to screen clinical-radiological factors and to establish a clinical-radiological model. Then, a combined model combining clinical-radiological factors with the radiomics score was constructed. The area under the receiver operating characteristic curve (AUC), accuracy and F1 score, sensitivity, and specificity were used to evaluate the models.

Results

Among the 10 various ML algorithms, the support vector machine (SVM) had the best prediction performance based on 12 radiomics features, including the AUC (training set: 0.918; testing set: 0.879) and accuracy (training set: 0.872; test set: 0.834). Among the clinical and radiological factors, the onset-to-baseline CT time, the scalp hematoma, and fibrinogen were associated with PH. The radiomics model's prediction performance was better than the clinical-radiological model, while the predictive nomogram combining the radiomics features with clinical-radiological characteristics performed best.

Conclusions

The radiomics model outperformed the traditional clinical-radiological model in predicting PH. The nomogram model of the combined radiomics features and clinical-radiological factors is a helpful tool for PH.

A Clinical Predictive Nomogram for Traumatic Brain Parenchyma Hematoma Progression

INTRODUCTION

Acute traumatic intraparenchymal hematoma (tICH) expansion is a major cause of clinical deterioration after brain contusion. Here, an accurate prediction tool for acute tICH expansion is proposed.

METHODS

A multicenter hospital-based study for multivariable prediction model was conducted among patients (889 patients in a development dataset and 264 individuals in an external validation dataset) with initial and follow-up computed tomography (CT) imaging for tICH volume evaluation. Semi-automated software was employed to assess tICH expansion. Two multivariate predictive models for acute tICH expansion were developed and externally validated.

RESULTS

A total of 198 (22.27%) individuals had remarkable acute tICH expansion. The novel Traumatic Parenchymatous Hematoma Expansion Aid (TPHEA) model retained several variables, including age, coagulopathy, baseline tICH volume, time to baseline CT time, subdural hemorrhage, a novel imaging marker of multihematoma fuzzy sign, and an inflammatory index of monocyte-to-lymphocyte ratio. Compared with multihematoma fuzzy sign, monocyte-to-lymphocyte ratio, and the basic model, the TPHEA model exhibited optimal discrimination, calibration, and clinical net benefits for patients with acute tICH expansion. A TPHEA nomogram was subsequently introduced from this model to facilitate clinical application. In an external dataset, this device showed good predicting performance for acute tICH expansion.

CONCLUSIONS

The main predictive factors in the TPHEA nomogram are the monocyte-to-lymphocyte ratio, baseline tICH volume, and multihematoma fuzzy sign. This user-friendly tool can estimate acute tICH expansion and optimize personalized treatments for individuals with brain contusion.

Usage of image registration and three-dimensional visualization tools on serial computed tomography for the analysis of patients with traumatic intraparenchymal hemorrhages

The aim of this study was to apply registration and three-dimensional (3D) display tools to assess the evolution of intraparenchymal hemorrhage (IPH) in patients with traumatic brain injury (TBI). We identified 109 TBI patients who had two computed tomography (CT) scans within 4 days retrospectively. The IPH was manually outlined. The registration was performed in 39 lesions from 29 patients with lesion volume < 1.5 cm on both baseline and follow-up CT. The center of mass (COM) of each lesion was calculated, and the distance between baseline and follow-up CT was used to evaluate the registration effect. The mean distances of COM before registration in the XYZ, XY, and YZ coordinates were 20.5 ± 10.2 mm, 17.8 ± 9.4 mm, and 15.9 ± 9.4 mm, respectively, which decreased significantly (p < 0.001) to 7.9 ± 4.9, 7.8 ± 5.0, and 6.1 ± 4.1 mm after registration. A 3D short video displaying the rendering view of all lesions in 34 randomly selected patients from baseline and follow-up scans were presented side-by-side for comparison. The detection rate of new IPH lesions increased in 3D videos (100%) as compared with axial CT slices (78.6-92.9%). A very high interrater agreement (k = 0.856) on perceiving IPH lesion progression upon viewing 3D video was noted, and the absolute volume increase was significantly higher (p < 0.001) for progressive lesions (median 7.36 cc) over non-progressive lesions (median 0.01 cc). Compared to patients with spontaneous hemorrhagic stroke, evaluation of multiple small traumatic hemorrhages in TBI is more challenging. The applied image analysis and visualization methods may provide helpful tools for comparing changes between serial CT scans.

Association between serum calcium level and hemorrhagic progression in patients with traumatic intraparenchymal hemorrhage: Investigating the mediation and interaction effects of coagulopathy

In this study, we investigate the association of serum calcium with coagulopathy and hemorrhagic progression contusion (HPC) in patients with traumatic intraparenchymal hemorrhage (tIPH), and further explored the interaction and mediation effect between serum calcium as well as coagulopathy on HPC. Retrospective analyses of patients with tIPH admitted to the First Affiliated Hospital of Wenzhou Medical University between January 2016 to December 2019. The clinical data, coagulation parameters, and serum calcium levels were collected for further analysis. Multivariate logistic regression analysis was applied to identify the association of serum calcium level with coagulopathy and HPC. Causal mediation analysis (CMA) and additive interaction model were used to estimate the interaction and mediation effect between serum calcium as well as coagulopathy on HPC. Additionally, we repeated the analysis using corrected calcium. A total of 473 patients were included in this study. Of these, 54 (11.4%) patients had hypocalcemia at admission, 105 (22.2%) presented with coagulopathy, and 187 (39.5%) experienced HPC. Admission serum calcium level in patients presented with coagulopathy and HPC were 8.84 [IQR: 8.44-9.40] and 8.92 [IQR: 8.48-9.40] mg/dL respectively, which were significantly lower than that of patients without (9.10 [IQR: 8.68-9.88] and 9.12 [IQR: 8.72-9.89] mg/dL; all p < 0.001). Multivariate logistic regression analysis identified that hypocalcemia emerged as an independent risk factor for coagulopathy and HPC. However, no significant interaction was detected between hypocalcemia and coagulopathy. CMA showed that the mediator coagulopathy explained 24.4% (95% CI: 4.7-65.0%; p = 0.006) of the association between hypocalcemia and HPC. Moreover, comparable results were held using corrected calcium as well. Admission serum calcium level is associated with the HPC for patients with tIPH and this relationship is partially mediated by coagulopathy, but no significant interaction is detected. Further studies are needed to validate the findings and explore its mechanisms.

Predicting Neurological Deterioration after Moderate Traumatic Brain Injury: Development and Validation of a Prediction Model Based on Data Collected on Admission

Moderate traumatic brain injury (mTBI) is a heterogeneous entity that poorly defined in the literature. mTBI patients suffer from a high rate of neurological deterioration (ND), which is usually accompanied with poor prognosis and no definitive methods to predict. The purpose of this study is to develop and validate a prediction model that estimates the ND risk in mTBI patients using data collected on admission. Retrospectively collected 479 mTBI patients' data in our department were analyzed by logistic regression models. Bivariable logistic regression identified variables with a p-value<0.05. Multivariable logistic regression modeling with backward stepwise elimination was used to determine reduced parameters and establish a prediction model. The discrimination efficacy, calibration efficacy, and clinical utility of the prediction model were evaluated. The prediction model was validated using 176 patients' data collected from another hospital. Eight independent prognostic factors were identified: hypertension, Marshall's scale (types III and IV), subdural hemorrhage (SDH), location of contusion (LOC) (frontal and temporal contusions), Injury Severity Score (ISS) >13, D-dimer level >11.4 mg/L, Glasgow Coma Scale (GCS) score ≤10, and platelet (PLT) count ≤152×109/L. A prediction model was established and was shown as a nomogram. Using bootstrapping, internal validation showed that the C-statistic of the prediction model was 0.881 (95% confidence interval (CI): 0.849-0.909). The results of external validation showed that the nomogram could predict ND with an area under the curve (AUC) of 0.827 (95% CI: 0763.-0.880). The present model, based on simple parameters collected on admission, can predict the risk of ND in mTBI patients accurately. The high discriminative ability indicates the potential of this model for classifying mTBI patients according to ND risk.

Contusion Progression Following Traumatic Brain Injury: A Review of Clinical and Radiological Predictors, and Influence on Outcome

Secondary injuries remain an important cause of the morbidity and mortality associated with traumatic brain injury (TBI). Progression of cerebral contusions occurs in up to 75% of patients with TBI, and this contributes to subsequent clinical deterioration and requirement for surgical intervention. Despite this, the role of early clinical and radiological factors in predicting contusion progression remains relatively poorly defined due to studies investigating progression of all types of hemorrhagic injuries as a combined cohort. In this review, we summarize data from recent studies on factors which predict contusion progression, and the effect of contusion progression on clinical outcomes.

The Use of Rotterdam CT Score for Prediction of Outcomes in Pediatric Traumatic Brain Injury Patients Admitted to Emergency Service

INTRODUCTION

Rotterdam CT score for prediction of outcome in traumatic brain injury is widely used for patient evaluation. The data on the assessment of pediatric traumatic brain injury patients with the Rotterdam scale in our country are still limited. In this study, we aimed to evaluate the use of the Rotterdam scale on pediatric trauma patients in our country and assess its relationship with lesion type, location and severity, trauma type, and need for surgery.

METHODS

A total of 229 pediatric patients admitted to the emergency service due to head trauma were included in our study. Patients were evaluated in terms of age, gender, Glasgow Coma Scale (GCS), initial and follow-up Rotterdam scale scores, length of stay, presence of other traumas, seizures, antiepileptic drug use, need for surgical necessity, and final outcome.

RESULTS

A total of 229 patients were included in the study, and the mean age of the patients was 95.8 months. Of the patients, 87 (38%) were girls and 142 (62%) were boys. Regarding GCS at the time of admission, 59% (n = 135) of the patients had mild (GCS = 13-15), 30.6% (n = 70) had moderate (GCS = 9-12), and 10.5% (n = 24) had severe (GCS < 9) head trauma. The mean Rotterdam scale score was calculated as 1.51 (ranging from 1 to 3) for mild, 2.22 (ranging from 1 to 4) for moderate, and 4.33 (ranging from 2 to 6) for severe head trauma patients. Rotterdam scale score increases significantly as the degree of head injury increases (p < 0.001).

DISCUSSION

With the adequate use of GCS and cerebral computed tomography imaging, pediatric patients with a higher risk of mortality and need for surgery can be predicted. We recommend the follow-up of pediatric traumatic brain injury patients with repeated CT scans to observe alterations in Rotterdam CT scores, which may be predictive for the need for surgery and intensive care.