Objective To develop a predictive model for guiding blood transfusion decisions in pediatric patients with traumatic brain injury(TBI)by identifying and analyzing key factors that influence blood transfusion requirements.Methods A retrospective analysis was conducted on the clinical data of 1,535 pediatric patients with TBI admitted to four medical institutions from January 1,2015,to December 31,2022.Patients were divided into two groups:those who received red blood cell transfusions during hospitalization and those who did not.Comparative analyses were performed on demographic,clinical,and laboratory data between these two groups.Logistic regression analysis was used to identify risk factors associated with in-hospital blood transfusion,and a predictive model was developed using a nomogram.The performance of this model was evaluated using a receiver operating characteristic(ROC)curve.Results Significant differences were observed between the blood transfusion and non-blood transfusion groups in terms of baseline demographics,clinical indicators,and laboratory test results(all P<0.05).Patients in the blood transfusion group exhibited significantly higher in-hospital mortality,compli-cation rates,use of mechanical ventilation,ICU admission rates,and length of stay compared to those in the non-blood transfusion group(all P<0.05).Multivariate logistic regression analysis identified heart rate,presence of other fractures,treatment methods,hemoglobin(Hb),platelet count(Plt),activated partial thromboplastin time(APTT),and D-dimer levels as independent risk factors for blood transfusion in TBI patients.The area under the ROC curve for the blood transfusion prediction model,based on these independent risk factors,was 0.95(95%CI:0.94～0.97),indicating excellent predictive accuracy.Calibration and decision curves further validated the robust-ness and reliability of the model's predictive capacity.Conclusions Heart rate,presence of other fractures,treatment methods,Hb,Plt count,APTT,and D-dimer levels serve as independent risk factors for blood transfusion in TBI patients.The prediction model developed based on these factors demonstrates excellent predictive performance,thereby guiding clinicians in making informed blood transfusion decisions and enhancing the success rate of patient outcomes.

Objective To develop a predictive model for guiding blood transfusion decisions in pediatric patients with traumatic brain injury(TBI)by identifying and analyzing key factors that influence blood transfusion requirements.Methods A retrospective analysis was conducted on the clinical data of 1,535 pediatric patients with TBI admitted to four medical institutions from January 1,2015,to December 31,2022.Patients were divided into two groups:those who received red blood cell transfusions during hospitalization and those who did not.Comparative analyses were performed on demographic,clinical,and laboratory data between these two groups.Logistic regression analysis was used to identify risk factors associated with in-hospital blood transfusion,and a predictive model was developed using a nomogram.The performance of this model was evaluated using a receiver operating characteristic(ROC)curve.Results Significant differences were observed between the blood transfusion and non-blood transfusion groups in terms of baseline demographics,clinical indicators,and laboratory test results(all P<0.05).Patients in the blood transfusion group exhibited significantly higher in-hospital mortality,compli-cation rates,use of mechanical ventilation,ICU admission rates,and length of stay compared to those in the non-blood transfusion group(all P<0.05).Multivariate logistic regression analysis identified heart rate,presence of other fractures,treatment methods,hemoglobin(Hb),platelet count(Plt),activated partial thromboplastin time(APTT),and D-dimer levels as independent risk factors for blood transfusion in TBI patients.The area under the ROC curve for the blood transfusion prediction model,based on these independent risk factors,was 0.95(95%CI:0.94～0.97),indicating excellent predictive accuracy.Calibration and decision curves further validated the robust-ness and reliability of the model's predictive capacity.Conclusions Heart rate,presence of other fractures,treatment methods,Hb,Plt count,APTT,and D-dimer levels serve as independent risk factors for blood transfusion in TBI patients.The prediction model developed based on these factors demonstrates excellent predictive performance,thereby guiding clinicians in making informed blood transfusion decisions and enhancing the success rate of patient outcomes.

[Abstract] [Objective] To explore the risk factors of blood transfusion in patients with isolated traumatic brain injury (iTBI) based on multiple machine learning methods, so as to establish a predictive model to provide reasonable guidance for blood transfusion in patients with iTBI. [Methods] A total of 2 273 patients with iTBI from the First Affiliated Hospital of Nanchang University from January 1, 2015 to June 30, 2021 were included to compare and analyze the differences in variables such as vital signs, clinical indicators and laboratory testing indicators between transfusion and non transfusion patients. Furthermore, six machine learning models were established to compare the performance of different models through cross validation, accuracy, specificity, recall, f1 value and area under the ROC curve. The SHAP plot was used to explain the influencing factors of blood transfusion in iTBI patients. [Results] This study included 2 273 iTBI patients, with a total of 301 patients receiving blood transfusions. There were significant differences (P<0.05) in gender, age, HR, clinical diagnosis, skull fracture, treatment methods, hemorrhagic shock, GCS, K, Ca, PT, APTT, INR, RBC, Hct, Hb and Plt between transfusion and non transfusion patients; Moreover, the LOS, incidence of complications, mechanical ventilation rate, ICU admission rate, readmission rate within 90 days and in-hospital mortality rate of transfusion patients were all higher than those of the non transfusion group (P<0.05). Six machine learning algorithms were used for model construction, and the validation results on the test set showed that the CatBoost model performed the best with an AUC of 0.911. Furthermore, the SHAP framework was used to explain and visualize the optimal model CatBoost, showing that surgical treatment, lower GCS, higher INR, lower Hct, lower K, lower Ca, age ≥60 years, skull fractures and hemorrhagic shock increase the risk of blood transfusion in patients. [Conclusion] This study established a machine learning model for predicting blood transfusion in iTBI patients, and the CatBoost model performed the best. This model may be useful and beneficial for identifying transfusion risks in this population, making clinical transfusion decisions and monitoring progress.