Prognostic model for patients with traumatic brain injuries and abnormal computed tomography scans

Glasgow coma scale pupil score (GCS-P) and the hospital mortality in severe traumatic brain injury: analysis of 1,066 Brazilian patients

BACKGROUND

 Pupil reactivity and the Glasgow Coma Scale (GCS) score are the most clinically relevant information to predict the survival of traumatic brain injury (TBI) patients.

OBJECTIVE

 We evaluated the accuracy of the GCS-Pupil score (GCS-P) as a prognostic index to predict hospital mortality in Brazilian patients with severe TBI and compare it with a model combining GCS and pupil response with additional clinical and radiological prognostic factors.

METHODS

 Data from 1,066 patients with severe TBI from 5 prospective studies were analyzed. We determined the association between hospital mortality and the combination of GCS, pupil reactivity, age, glucose levels, cranial computed tomography (CT), or the GCS-P score by multivariate binary logistic regression.

RESULTS

 Eighty-five percent (n = 908) of patients were men. The mean age was 35 years old, and the overall hospital mortality was 32.8%. The area under the receiver operating characteristic curve (AUROC) was 0.73 (0.70-0.77) for the model using the GCS-P score and 0.80 (0.77-0.83) for the model including clinical and radiological variables. The GCS-P score showed similar accuracy in predicting the mortality reported for the patients with severe TBI derived from the International Mission for Prognosis and Clinical Trials in TBI (IMPACT) and the Corticosteroid Randomization After Significant Head Injury (CRASH) studies.

CONCLUSION

 Our results support the external validation of the GCS-P to predict hospital mortality following a severe TBI. The predictive value of the GCS-P for long-term mortality, functional, and neuropsychiatric outcomes in Brazilian patients with mild, moderate, and severe TBI deserves further investigation.

Traumatic Brain Injury in Select Low- and Middle-Income Countries: A Narrative Review of the Literature

Low- and middle-income countries (LMICs) experience the majority of traumatic brain injuries (TBIs), yet few studies have examined the epidemiology and management strategies of TBI in LMICs. The objective of this narrative review is to discuss the epidemiology of TBI within LMICs, describe the adherence to Brain Trauma Foundation (BTF) guidelines for the management of severe TBI in LMICs, and document TBI management strategies currently used in LMICs. Articles from January 1, 2009 to September 30, 2021 that included patients with TBI greater than 18 years of age in low-, low middle-, and high middle-income countries were queried in PubMed. Search results demonstrated that TBI in LMICs mostly impacts young males involved in road traffic accidents. Within LMICs there are a myriad of approaches to managing TBI with few randomized controlled trials performed within LMICs to evaluate those interventions. More studies are needed in LMICs to establish the effectiveness and appropriateness of BTF guidelines for managing TBI and to help identify methods for managing TBI that are appropriate in low-resource settings. The problem of limited pre- and post-hospital care is a bigger challenge that needs to be considered while addressing management of TBI in LMICs.

A hierarchical expert-guided machine learning framework for clinical decision support systems: an application to traumatic brain injury prognostication

Prognosis of the long-term functional outcome of traumatic brain injury is essential for personalized management of that injury. Nonetheless, accurate prediction remains unavailable. Although machine learning has shown promise in many fields, including medical diagnosis and prognosis, such models are rarely deployed in real-world settings due to a lack of transparency and trustworthiness. To address these drawbacks, we propose a machine learning-based framework that is explainable and aligns with clinical domain knowledge. To build such a framework, additional layers of statistical inference and human expert validation are added to the model, which ensures the predicted risk score’s trustworthiness. Using 831 patients with moderate or severe traumatic brain injury to build a model using the proposed framework, an area under the receiver operating characteristic curve (AUC) and accuracy of 0.8085 and 0.7488 were achieved, respectively, in determining which patients will experience poor functional outcomes. The performance of the machine learning classifier is not adversely affected by the imposition of statistical and domain knowledge “checks and balances”. Finally, through a case study, we demonstrate how the decision made by a model might be biased if it is not audited carefully.

Predictors of Hospital Mortality and the Related Burden of Disease in Severe Traumatic Brain Injury: A Prospective Multicentric Study in Brazil

Traumatic brain injury (TBI) is a worldwide social, economic, and health problem related to premature death and long-term disabilities. There were no prospective and multicentric studies analyzing the predictors of TBI related mortality and estimating the burden of TBI in Brazil. To address this gap, we investigated prospectively: (1) the hospital mortality and its determinants in patients admitted with severe TBI we analyzed in three reference centers; (2) the burden of TBI estimated by the years of life lost (YLLs) due to premature death based on the hospital mortality considering the hospital mortality. Between April 2014 and January 2016 (22 months), all the 266 patients admitted with Glasgow coma scale (GCS), ≤ 8 admitted in three TBI reference centers were included in the study. These centers cover a population of 1,527,378 population of the Santa Catarina state, Southern Brazil. Most patients were male (n = 230, 86.5%), with a mean (SD) age of 38 (17) years. Hospital mortality was 31.1% (n = 83) and independently associated with older age, worse cranial CT injury by the Marshall classification, the presence of subarachnoid hemorrhage in the CT, lower GCS scores and abnormal pupils at admission. The final multiple logistic regression model including these variables showed an overall accuracy for hospital mortality of 77.9% (specificity 88.6%, sensitivity 53.8%, PPV 67.7%, and NPV 81.1%). The estimated annual incidence of hospitalizations and mortality due to severe TBI were 9.5 cases and 5.43 per 100,000 inhabitants, respectively. The estimated YLLs in 22 months, in the 2 metropolitan areas were 2,841, corresponding to 1,550 YLLs per year and 101.5 YLLs per 100,000 people every year. The hospital mortality did not change significantly since the end of the 1990s and was similar to other centers in Brazil and Latin America. Significant predictors of hospital mortality were the same as those of studies worldwide, but their strength of association seemed to differ according to countries income. Present study results question the extrapolation of TBI hospital mortality models for high income to lower- and middle-income countries and therefore have implications for TBI multicentric trials including countries with different income levels.

Mortality prediction in patients with isolated moderate and severe traumatic brain injury using machine learning models

BACKGROUND

The purpose of this study was to build a model of machine learning (ML) for the prediction of mortality in patients with isolated moderate and severe traumatic brain injury (TBI).

METHODS

Hospitalized adult patients registered in the Trauma Registry System between January 2009 and December 2015 were enrolled in this study. Only patients with an Abbreviated Injury Scale (AIS) score ≥ 3 points related to head injuries were included in this study. A total of 1734 (1564 survival and 170 non-survival) and 325 (293 survival and 32 non-survival) patients were included in the training and test sets, respectively.

RESULTS

Using demographics and injury characteristics, as well as patient laboratory data, predictive tools (e.g., logistic regression [LR], support vector machine [SVM], decision tree [DT], naive Bayes [NB], and artificial neural networks [ANN]) were used to determine the mortality of individual patients. The predictive performance was evaluated by accuracy, sensitivity, and specificity, as well as by area under the curve (AUC) measures of receiver operator characteristic curves. In the training set, all five ML models had a specificity of more than 90% and all ML models (except the NB) achieved an accuracy of more than 90%. Among them, the ANN had the highest sensitivity (80.59%) in mortality prediction. Regarding performance, the ANN had the highest AUC (0.968), followed by the LR (0.942), SVM (0.935), NB (0.908), and DT (0.872). In the test set, the ANN had the highest sensitivity (84.38%) in mortality prediction, followed by the SVM (65.63%), LR (59.38%), NB (59.38%), and DT (43.75%).

CONCLUSIONS

The ANN model provided the best prediction of mortality for patients with isolated moderate and severe TBI.

Therapeutic effect of intensive glycemic control therapy in patients with traumatic brain injury: A systematic review and meta-analysis of randomized controlled trials

BACKGROUND

Hyperglycemia is associated with dismal outcomes in patients with traumatic brain injury (TBI), which is frequently treated with insulin therapy. In this study, a systematic review and meta-analysis of the published randomized controlled trials (RCTs) was performed to assess the safety and efficacy of intensive glycemic control (IGC) versus conventional glycemic control (CGC) for patients following TBI.

METHODS

Databases, including PubMed, Embase, and the Cochran database, were retrieved up to January 2018. The outcomes evaluated in this study included mortality, neurological outcome, infection rate, hypoglycemia episode, and length of stay (LOS) in intensive care unit (ICU). The enrolled trials were analyzed using the Review Manager 5.3 software.

RESULTS

A total of 7 randomized controlled trials (RCTs) involving 1013 cases were enrolled in this study, and the results indicated no significant difference in 6-month mortality (risk ratio [RR], 0.92; 95% confidence interval [CI] 0.76-1.10; P = .34). Subsequently, IGC was associated with a better neurological outcome (RR, 1.22; 95% CI 1.05-1.43; P = .01), lower infection rate (RR, 0.65; 95% CI 0.51-0.82; P = .0003) and shorter LOS in ICU (mean difference [MD] = -1.37; 95%CI = -2.11, -0.63; P = .0003). In addition, IGC would also increase the risk of hypoglycemia episode (RR, 4.53; 95% CI 2.18-9.42; P < .001).

CONCLUSIONS

IGC plays a protective role in improving neurological outcome, decreasing infection rate and reducing the LOS in ICU. However, IGC therapy can also remarkably increase the risk of hypoglycemia, but it will not affect the mortality in TBI patients.

Lesions in deep gray nuclei after severe traumatic brain injury predict neurologic outcome

PURPOSE

This study evaluates the correlation between injuries to deep gray matter nuclei, as quantitated by lesions in these nuclei on MR T2 Fast Spin Echo (T2 FSE) images, with 6-month neurological outcome after severe traumatic brain injury (TBI).

MATERIALS AND METHODS

Ninety-five patients (80 males, mean age = 36.7y) with severe TBI were prospectively enrolled. All patients underwent a MR scan within the 45 days after the trauma that included a T2 FSE acquisition. A 3D deformable atlas of the deep gray matter was registered to this sequence; deep gray matter lesions (DGML) were evaluated using a semi-quantitative classification scheme. The 6-month outcome was dichotomized into unfavorable (death, vegetative or minimally conscious state) or favorable (minimal or no neurologic deficit) outcome.

RESULTS

Sixty-six percent of the patients (63/95) had both satisfactory registration of the 3D atlas on T2 FSE and available clinical follow-up. Patients without DGML had an 89% chance (P = 0.0016) of favorable outcome while those with bilateral DGML had an 80% risk of unfavorable outcome (P = 0.00008). Multivariate analysis based on DGML accurately classified patients with unfavorable neurological outcome in 90.5% of the cases.

CONCLUSION

Lesions in deep gray matter nuclei may predict long-term outcome after severe TBI with high sensitivity and specificity.