A Practical Triage and Risk Scoring for Prediction of Early Mortality in Polytrauma Patients: GAS-TRS
Abstract Background Accurate evaluation of mortality risk in polytrauma patients is crucial for guiding the precision treatment strategy. There are few scales designed to provide an early assessment of mortality risk. However, the complexity of available scoring systems limits their application in pre-hospital care. Here, we established a GAS-TRS system to estimate the risk of early death for individual polytrauma patients and assess the early mortality risk in the individual patient.Methods We performed a secondary analysis from public Database. RCS and Multivariate Logistic regression analyses were used to screen potential prognostic factors for nomogram model. The VIF method examined multicollinearity, and VIF ≥ 5 suggested multicollinearity in this model. CMA was used to characterize the causality relationship in nomogram model. A four-layer back-propagation artificial neural network (BP-ANN) model was built by neuralnet package on R software. AUC of ROC analysis or F1 score were used to analyze the quality of predictive performance of GAS-TRS system. DCA and precision-recall curves were used to make up for the limitations of ROC curves.Results A total of 2406 patients were included in this analysis. Logistic regression analysis predicted four independent risk factors for nomogram model, including age (OR=1.03, 95%CI:1.02~1.03), GCS (OR=0.83, 95%CI:0.79~0.86), BE (OR=0.95, 95%CI:0.91~0.99) and serum lactic acid (OR=1.30, 95%CI:1.20~1.41) with an AUC of 0.88. Causal mediation analysis performed the mediation effect that lactate, age and BE accounted for 1.7%,0.7% and 3.0% indirect effect.The calibration curve showed model has good highly consistent with actual condition after bootstrapping. DCA showed the net benefit probability was between 2% and 85% and could bring more benefits for predicting early mortality.Then the input neurons were selected step by step in BP-ANN model. An optimal BP-ANN with an AUC of 0.91and AUPRC of 0.79 was established.Conclusion We established a GAS-TRS predictive system which includes a quick prognostic nomogram model and a precise BP-ANN model to evaluate early mortality within 72 hours for polytrauma patients. This scoring system might be practical and more efficient in identifying high-risk polytrauma patients. Moreover, this system may also guide triaging and precise initial individual treatment strategy for pre-hospital medical personnel.