Search

Objective: Neurotrauma is a significant cause of morbidity and mortality in Nigeria. We conducted this systematic review to generate nationally generalizable reference data for the country., Methods: Four research databases and gray literature sources were electronically searched. Risk of bias was assessed using the Risk of Bias in Non-Randomized Studies of Interventions and Cochrane's risk of bias tools. Descriptive analysis, narrative synthesis, and statistical analysis (via paired t-tests and χ 2 independence tests) were performed on relevant article metrics (α = 0.05)., Results: We identified a cohort of 45,763 patients from 254 articles. The overall risk of bias was moderate to high. Most articles employed retrospective cohort study designs (37.4%) and were published during the last 2 decades (81.89%). The cohort's average age was 32.5 years (standard deviation, 20.2) with a gender split of ∼3 males per female. Almost 90% of subjects were diagnosed with traumatic brain injury, with road traffic accidents (68.6%) being the greatest cause. Altered consciousness (48.4%) was the most commonly reported clinical feature. Computed tomography (53.5%) was the most commonly used imaging modality, with skull (25.7%) and vertebral fracture (14.1%) being the most common radiological findings for traumatic brain injury and traumatic spinal injury, respectively. Two-thirds of patients were treated nonoperatively. Outcomes were favorable in 63.7% of traumatic brain injury patients, but in only 20.9% of traumatic spinal injury patients. Pressure sores, infection, and motor deficits were the most commonly reported complications in the latter., Conclusions: This systematic review and pooled analysis demonstrate the significant burden of neurotrauma across Nigeria., (Copyright © 2023 Elsevier Inc. All rights reserved.)

Objective: Traumatic brain injury (TBI) carries a major global burden of disease; however, it is well established that patients in low- and middle-income countries, such as those in Africa, have higher mortality rates. Pediatric TBI, specifically, is a documented cause for concern as injuries to the developing brain have been shown to lead to cognitive, psychosocial, and motor problems in adulthood. The purpose of this study was to investigate the reported demographics, causes, management, and outcomes of pediatric TBI in Africa., Methods: A literature search was conducted using PubMed, Global Index Medicus, Embase, Scopus, Google Scholar, African Journals Online, and Web of Science. Various combinations of "traumatic brain injury," "head injury," "p(a)ediatric," "Africa," and country names were used. Relevant primary data published in the English language were included and subjected to a risk of bias analysis. Variables included age, sex, TBI severity, TBI cause, imaging findings, treatment, complications, and outcome., Results: After screening, 45 articles comprising 11,635 patients were included. The mean patient age was 6.48 ± 2.13 years, and 66.3% of patients were male. Of patients with reported data, mild, moderate, and severe TBIs were reported in 57.6%, 14.5%, and 27.9% of patients, respectively. Road traffic accidents were the most reported cause of pediatric TBI (50.53%) followed by falls (25.18%). Skull fractures and intracerebral contusions were the most reported imaging findings (28.32% and 16.77%, respectively). The most reported symptoms included loss of consciousness (24.4%) and motor deficits (17.1%). Surgical management was reported in 28.66% of patients, with craniotomy being the most commonly reported procedure (15.04%). Good recovery (Glasgow Outcome Scale score 5, Glasgow Outcome Scale-Extended score 7-8) was reported in 47.17% of patients. Examination of the period post-2015 demonstrated increased spread in the literature regarding pediatric TBI in Africa., Conclusions: This study provides a comprehensive overview of the literature regarding pediatric TBI in Africa and how it has evolved alongside global neurosurgical efforts. Although there has been increased involvement from various African countries in the neurosurgical literature, there remains a relative paucity of data on this subject. Standardized reporting protocols for patient care may aid in future studies seeking to synthesize data. Finally, further studies should seek to correlate the trends seen in this study, with primary epidemiological data to gain deeper insight into the disease burden of pediatric TBI in Africa.

Objective: Traumatic brain injury (TBI) disproportionately affects low- and middle-income countries (LMICs). In these settings, accurate patient prognostication is both difficult and essential for high-quality patient care. With the ultimate goal of enhancing TBI triage in LMICs, we aim to develop the first deep learning model to predict outcomes after TBI and compare its performance with that of less complex algorithms., Methods: TBI patients' data were prospectively collected in Kampala, Uganda, from 2016 to 2020. To predict good versus poor outcome at hospital discharge, we created deep neural network, shallow neural network, and elastic-net regularized logistic regression models. Predictors included 13 easily acquirable clinical variables. We assessed model performance with 5-fold cross-validation to calculate areas under both the receiver operating characteristic curve and precision-recall curve (AUPRC), in addition to standardized partial AUPRC to focus on comparisons at clinically relevant operating points., Results: We included 2164 patients for model training, of which 12% had poor outcomes. The deep neural network performed best as measured by the area under the receiver operating characteristic curve (0.941) and standardized partial AUPRC in region maximizing recall (0.291), whereas the shallow neural network was best by the area under the precision-recall curve (0.770). In several other comparisons, the elastic-net regularized logistic regression was noninferior to the neural networks., Conclusions: We present the first use of deep learning for TBI prognostication, with an emphasis on LMICs, where there is great need for decision support to allocate limited resources. Optimal algorithm selection depends on the specific clinical setting; deep learning is not a panacea, though it may have a role in these efforts., (Copyright © 2022 Elsevier Inc. All rights reserved.)

Background: Current traumatic brain injury (TBI) prognostic calculators are commonly used to predict the mortality and Glasgow Outcome Scale, but these outcomes are most relevant for severe TBI. Because mild and moderate TBI rarely reaches severe outcomes, there is a need for novel prognostic endpoints., Objective: To generate machine learning (ML) models with a strong predictive capacity for trichotomized discharge disposition, an outcome not previously used in TBI prognostic models. The outcome can serve as a proxy for patients' functional status, even in mild and moderate patients with TBI., Methods: Using a large data set (n = 5292) of patients with TBI from a quaternary care center and 84 predictors, including vitals, demographics, mechanism of injury, initial Glasgow Coma Scale, and comorbidities, we trained 6 different ML algorithms using a nested-stratified-cross-validation protocol. After optimizing hyperparameters and performing model selection, isotonic regression was applied to calibrate models., Results: When maximizing the microaveraged area under the receiver operating characteristic curve during hyperparameter optimization, a random forest model exhibited top performance. A random forest model was also selected when maximizing the microaveraged area under the precision-recall curve. For both models, the weighted average area under the receiver operating characteristic curves was 0.84 (95% CI 0.81-0.87) and the weighted average area under the precision-recall curves was 0.85 (95% CI 0.82-0.88)., Conclusion: Our group presents high-performing ML models to predict trichotomized discharge disposition. These models can assist in optimization of patient triage and treatment, especially in cases of mild and moderate TBI., (Copyright © Congress of Neurological Surgeons 2022. All rights reserved.)

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., (Copyright © Congress of Neurological Surgeons 2022. All rights reserved.)