Objective:To explore the correlation of serum albumin level at admission with clinical prognoses in patients with acute traumatic brain injury (TBI).Methods:One hundred and fifty-four patients with acute moderate-extreme severe TBI (Glasgow Coma Scale [GCS] scores of 3-12 at admission) in Department of Neurosurgery, General Hospital of Western Theater Command from January 1, 2019 to December 31, 2020 were chosen. The comprehensive clinical data of these patients were collected, including age, gender, GCS scores, serum albumin level (hypoalbuminemia defined as<35 g/L), hemoglobin level, comorbidities, treatment measures, and prognoses 6 months after discharge (poor prognosis defined as Glasgow outcome Scale [GOS] scores of 1-2, and good prognosis defined as GOS scores of 3-5). Univariate and multivariate Logistic regressions were used to identify the independent factors for clinical prognoses of these patients, and differences in poor prognosis rate, length of ICU stay, and total hospital cost were compared between different groups.Results:Among the 154 patients, 43 had poor prognosis and 111 had good prognosis. Serum albumin level at admission ( OR=0.916, 95% CI: 0.843-0.996, P=0.001) and GCS scores at admission ( OR=0.701, 95% CI: 0.594-0.828, P<0.001) were independent factors for prognosis. Patients with hypoalbuminemia ( n=70) displayed significantly higher poor prognosis rate, longer ICU stays, and increased total hospitalization cost compared with those without hypoalbuminemia ( n=84, P<0.05); specifically, in patients with GCS scores of 9-12 at admission ( n=58), those with hypoalbuminemia ( n=27) exhibited significantly higher poor prognosis rate, longer ICU stays, and higher total hospitalization cost than their non-hypoalbuminemia counterparts ( n=31, P<0.05); similarly, in patients with GCS scores of 3-8 at admission ( n=96), those with hypoalbuminemia ( n=74) had significantly higher poor prognosis rate than their non-hypoalbuminemia counterparts ( n=22, P<0.05). In patients with good prognosis, those with hypoalbuminemia ( n=56) showed significantly longer total hospital stays, prolonged ICU stays, and increased total hospitalization cost compared with those without hypoalbuminemia ( n=55, P<0.05). Conclusion:Low serum albumin level at admission is likely to lead to poor prognosis, prolonged ICU stays and increased total hospitalization cost in patients with acute TBI.

Objective To explore the value of machine learning(ML)models based on non-contrast CT(NCCT)radiomics features for predicting the severity of acute phase traumatic brain injury(TBI).Methods Totally 600 TBI patients were retrospectively collected as observation group,other 65 TBI patients were taken as external validation set,while 50 TBI patients were prospectively enrolled as prospective validation set.Patients in observation group were divided into high-risk subgroup(n=240)and low-risk subgroup(n=360)according to Glasgow outcome scale(GOS)at discharge.The severity of acute phase TBI in observation group was assessed by doctor A and B with the same criteria,then an artificial model was established based on clinical and NCCT data at the time of first diagnosis using logistic regression(LR)method for predicting the severity of acute phase TBI.Patients in observation group were divided into training set(n=420,including 168 in high-risk subgroup and 252 in low-risk subgroup)and test set(n=180,including 72 in high-risk subgroup and 108 in low-risk subgroup)at the ratio of 7∶3.Based on NCCT of training set,radiomics features were extracted and selected,and LR,support vector machine(SVM),random forest(RF)and K-nearest neighbor(KNN)were used to establish 4 ML models.The efficacies of the above models were validated in test set,external validation set(including 34 cases of high-risk and 31 cases of low-risk TBI)and prospective validation set(including 21 cases of high-risk and 29 cases of low-risk TBI),respectively.Results The area under the curve(AUC)of doctor A and B for evaluating the severity of acute phase TBI in observation group was 0.606 and 0.771,respectively,of artificial model was 0.824.Based on NCCT in training set,6 optimal radiomics features were selected to construct LR,SVM,RF and KNN ML models,with AUC of 0.983,0.971,0.970 and 0.984 in test set,respectively,while the AUC of artificial model was 0.708.The AUC of LR,SVM,RF,KNN ML models and artificial model in external validation set was 0.879,0.881,0.984,0.863 and 0.733,while in prospective validation set was 0.984,0.873,0.982,0.897 and 0.704,respectively.Conclusion ML models based on CT radiomics could effectively predict the severity of acute phase TBI.