Search

• A random forest model for early functional outcomes following acute care after traumatic brain injury (TBI) was developed and validated. • The BI score at admission, age, use of nonsurgical treatment, neurosurgery status, and mCCI score were the top 5 prognostic predictors. • The predictive model is generalisable by using hospital discharge abstract data. • The model can inform decision-making regarding TBI patient management and facilitate health care quality assessment and resource allocation. Few studies on early functional outcomes following acute care after traumatic brain injury (TBI) are available. The aim of this study was to develop and validate a predictive model for functional outcomes at discharge for TBI patients using machine learning methods. In this retrospective study, data from 5281 TBI patients admitted for acute care who were identified in the Beijing hospital discharge abstract database were analysed. Data from 4181 patients in 52 tertiary hospitals were used for model derivation and internal validation. Data from 1100 patients in 21 secondary hospitals were used for external validation. A poor outcome was defined as a Barthel Index (BI) score ≤ 60 at discharge. Logistic regression, XGBoost, random forest, decision tree, and back propagation neural network models were used to fit classification models. Performance was evaluated by the area under the receiver operating characteristic curve (AUC), the area under the precision-recall curve (AP), calibration plots, sensitivity/recall, specificity, positive predictive value (PPV)/precision, negative predictive value (NPV) and F1-score. Compared to the other models, the random forest model demonstrated superior performance in internal validation (AUC of 0.856, AP of 0.786, and F1-score of 0.724) and external validation (AUC of 0.779, AP of 0.630, and F1-score of 0.604). The sensitivity/recall, specificity, PPV/precision, and NPV of the model were 71.8%, 69.2%, 52.2%, and 84.0%, respectively, in external validation. The BI score at admission, age, use of nonsurgical treatment, neurosurgery status, and modified Charlson Comorbidity Index were identified as the top 5 predictors for functional outcome at discharge. We established a random forest model that performed well in predicting early functional outcomes following acute care after TBI. The model has utility for informing decision-making regarding patient management and discharge planning and for facilitating health care quality assessment and resource allocation for TBI treatment. [ABSTRACT FROM AUTHOR]

Introduction: Unintentional injuries (UIs) impose a significant burden on low- and middle-income countries (LMICs). However, available UI epidemiological data are limited for LMICs, including China. This article aimed to provide an overview of the UI hospitalization profile, identify risk factors for in-hospital mortality and provide diagnosis-specific survival risk ratios (SRRs) for reference by LMICs using hospital discharge abstract data (DAD) from Beijing, China.Patients and Methods: A cross-sectional study was conducted for patients sustaining UIs requiring admission. Information was retrieved from 138 hospitals in Beijing to describe the demographics, injury nature, mechanisms, severity and hospital outcomes. Multivariate logistic regression was performed to identify and evaluate risk factors for in-hospital mortality for UIs.Results: Falls (57.1%), transport accidents (19.9%) and exposure to inanimate mechanical forces (16.4%) were the leading causes of UI hospitalization. Falls and transport accidents were responsible for 94.2% of the in-hospital deaths caused by UIs. Injury mechanisms differed among sex (χ2 = 5322.1, P <  0.001) and age (χ2 = 24,143.3, P <  0.001) groups. Male sex (OR: 1.50, 95% confidence interval (CI): 1.23-1.79), age ≥ 85 years (OR: 16.39, 95% CI: 7.46-36.00), Barthel Index at admission ≤ 60 (OR: 25.78, 95% CI: 13.30-49.95), modified Charlson comorbidity index ≥ 6 (OR: 2.60, 95% CI: 1.91-3.55), International Classification of Diseases-based injury severity score (ICISS) < 0.85 (OR: 15.17, 95% CI: 12.57-18.30), sustaining injuries to the head/neck (OR: 23.20, 95% CI: 7.31-73.64), injuries caused by foreign body entering through natural orifice (OR: 34.00, 95%CI: 6.37-181.54) and injuries resulting from transport accidents (OR: 1.71, 95% CI: 1.41-2.07) were important risk factors for in-hospital mortality for UIs.Conclusions: Hospital DAD are an objective and cost-effective data source that allows for a hospital-based perspective of UI epidemiology. Sex, age, functional status at admission, comorbidities, injury nature, severity and mechanism are significantly associated with the in-hospital mortality of UIs in China. This study generates a reference dataset of diagnosis-specific SRRs from a large trauma population in China, which may be more applicable in injury severity estimation using ICISS in LMICs. [ABSTRACT FROM AUTHOR]