Corticosteroid Randomization after Significant Head Injury and International Mission for Prognosis and Clinical Trialsin Traumatic Brain Injury Models Compared with a Machine Learning-Based Predictive Model from Tanzania

Comparative analysis of CRASH and IMPACT in predicting the outcome of 340 patients with traumatic brain injury

Background

Both the International Mission for Prognosis and Analysis of Clinical Trials (IMPACT) and the Corticosteroid randomization after significant head injury (CRASH) models are globally acknowledged prognostic algorithms for assessing traumatic brain injury (TBI) outcomes. The aim of this study is to externalize the validation process and juxtapose the prognostic accuracy of the CRASH and IMPACT models in moderate-to-severe TBI patients in the Chinese population.

Methods

We conducted a retrospective study encompassing a cohort of 340 adult TBI patients (aged > 18 years), presenting with Glasgow Coma Scale (GCS) scores ranging from 3 to 12. The data were accrued over 2 years (2020-2022). The primary endpoints were 14-day mortality rates and 6-month Glasgow Outcome Scale (GOS) scores. Analytical metrics, including the area under the receiver operating characteristic curve for discrimination and the Brier score for predictive precision were employed to quantitatively evaluate the model performance.

Results

Mortality rates at the 14-day and 6-month intervals, as well as the 6-month unfavorable GOS outcomes, were established to be 22.06, 40.29, and 65.59%, respectively. The IMPACT models had area under the curves (AUCs) of 0.873, 0.912, and 0.927 for the 6-month unfavorable GOS outcomes, with respective Brier scores of 0.14, 0.12, and 0.11. On the other hand, the AUCs associated with the six-month mortality were 0.883, 0.909, and 0.912, and the corresponding Brier scores were 0.15, 0.14, and 0.13, respectively. The CRASH models exhibited AUCs of 0.862 and 0.878 for the 6-month adverse outcomes, with uniform Brier scores of 0.18. The 14-day mortality rates had AUCs of 0.867 and 0.87, and corresponding Brier scores of 0.21 and 0.22, respectively.

Conclusion

Both the CRASH and IMPACT algorithms offer reliable prognostic estimations for patients suffering from craniocerebral injuries. However, compared to the CRASH model, the IMPACT model has superior predictive accuracy, albeit at the cost of increased computational intricacy.

Injury characteristics and their association with clinical complications among emergency care patients in Tanzania

•

Our patient sample from a national referral hospital serving upwards of 15 million people provides insight into patterns of injury morbidity and mortality in Northwestern Tanzania.

•

This study describes the characteristics, predictors and outcomes of adult acute injury patients presenting to a tertiary referral hospital in a low-income country in sub-Saharan Africa.

•

Although KCMC receives a large number of injury patients, risk factors for poor outcomes among all-cause injury patients who present to this hospital are not clear.

•

Information from this study is intended to aid the improvement of care received by injury patients in the Kilimanjaro region of Tanzania.

•

Our findings demonstrate that poor injury outcomes in the Kilimanjaro region may be dependent on injury, clinical, and sociodemographic characteristics.

Background

Over 5 million people annually die from injuries and millions more sustain non-fatal injuries requiring medical care. Ninety percent of injury deaths occur in low- and middle-income countries (LMICs). This study describes the characteristics, predictors and outcomes of adult acute injury patients presenting to a tertiary referral hospital in a low-income country in sub-Saharan Africa.

Methods

This secondary analysis uses an adult acute injury registry from Kilimanjaro Christian Medical Centre (KCMC) in Moshi, Tanzania. We describe this patient sample in terms of socio-demographics, clinical indicators, injury patterns, treatments, and outcomes at hospital discharge. Outcomes include mortality, length of hospital stay, and functional independence. Associations between patient characteristics and patient outcomes are quantified using Cox proportional hazards models, negative binomial regression, and multivariable logistic regression.

Results

Of all injury patients (n=1365), 39.0% were aged 30 to 49 years and 81.5% were men. Most patients had at least a primary school education (89.6%) and were employed (89.3%). A majority of injuries were road traffic (63.2%), fall (16.8%), or assault (14.0%) related. Self-reported comorbidities included hypertension (5.8%), HIV (3.1%), and diabetes (2.3%). Performed surgeries were classified as orthopedic (32.3%), general (4.1%), neurological (3.7%), or other (59.8%). Most patients reached the hospital at least four hours after injury occurred (53.9%). Mortality was 5.3%, median length of hospital stay was 6.1 days (IQR: 3.1, 15.0), self-care dependence was 54.2%, and locomotion dependence was 41.5%.

Conclusions

Our study sample included primarily young men suffering road traffic crashes with delayed hospital presentations and prolonged hospital stays. Being older, male, and requiring non-orthopedic surgeries or having HIV portends a worse prognosis. Prevention and treatment focused interventions to reduce the burden of injury mortality and morbidity at KCMC are needed to lower injury rates and improve injury outcomes.

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.

Non-Communicable Neurological Disorders and Neuroinflammation

Traumatic brain injury, stroke, and neurodegenerative diseases represent a major cause of morbidity and mortality in Africa, as in the rest of the world. Traumatic brain and spinal cord injuries specifically represent a leading cause of disability in the younger population. Stroke and neurodegenerative disorders predominantly target the elderly and are a major concern in Africa, since their rate of increase among the ageing is the fastest in the world. Neuroimmunology is usually not associated with non-communicable neurological disorders, as the role of neuroinflammation is not often considered when evaluating their cause and pathogenesis. However, substantial evidence indicates that neuroinflammation is extremely relevant in determining the consequences of non-communicable neurological disorders, both for its protective abilities as well as for its destructive capacity. We review here current knowledge on the contribution of neuroinflammation and neuroimmunology to the pathogenesis of traumatic injuries, stroke and neurodegenerative diseases, with a particular focus on problems that are already a major issue in Africa, like traumatic brain injury, and on emerging disorders such as dementias.

Machine Learning for Predicting In-Hospital Mortality After Traumatic Brain Injury in Both High-Income and Low- and Middle-Income Countries

BACKGROUND

Machine learning (ML) holds promise as a tool to guide clinical decision making by predicting in-hospital mortality for patients with traumatic brain injury (TBI). Previous models such as the international mission for prognosis and clinical trials in TBI (IMPACT) and the corticosteroid randomization after significant head injury (CRASH) prognosis calculators can potentially be improved with expanded clinical features and newer ML approaches.

OBJECTIVE

To develop ML models to predict in-hospital mortality for both the high-income country (HIC) and the low- and middle-income country (LMIC) settings.

METHODS

We used the Duke University Medical Center National Trauma Data Bank and Mulago National Referral Hospital (MNRH) registry to predict in-hospital mortality for the HIC and LMIC settings, respectively. Six ML models were built on each data set, and the best model was chosen through nested cross-validation. The CRASH and IMPACT models were externally validated on the MNRH database.

RESULTS

ML models built on National Trauma Data Bank (n = 5393, 84 predictors) demonstrated an area under the receiver operating curve (AUROC) of 0.91 (95% CI: 0.85-0.97) while models constructed on MNRH (n = 877, 31 predictors) demonstrated an AUROC of 0.89 (95% CI: 0.81-0.97). Direct comparison with CRASH and IMPACT models showed significant improvement of the proposed LMIC models regarding AUROC (P = .038).

CONCLUSION

We developed high-performing well-calibrated ML models for predicting in-hospital mortality for both the HIC and LMIC settings that have the potential to influence clinical management and traumatic brain injury patient trajectories.