Mean corpuscular volume as a prognostic factor for 30-day mortality in major trauma patients: a retrospective cohort study.

We investigated the clinical implications of the mean corpuscular volume (MCV) in patients with major trauma. This single-center retrospective review included 2021 trauma patients admitted to the intensive care unit between January 2016 and June 2020. We included 1218 patients aged [Formula: see text] 18 years with an injury severity score [Formula: see text] 16 in the final analysis. The clinical and laboratory variables were compared between macrocytosis (defined as MCV [Formula: see text] 100 fL) and non-macrocytosis groups. Cox regression analysis was performed to calculate the hazard ratios (HRs) of variables for 30-day mortality, with adjustment for other potential confounding factors. The initial mean value of MCV was 102.7 fL in the macrocytosis group (n = 199) and 93.7 fL in the non-macrocytosis group (n = 1019). The macrocytosis group showed a significantly higher proportion of initial hypotension, transfusion within 4 and 24 h, and 30-day mortality than the non-macrocytosis group. Age ([Formula: see text] 65 years), hypotension (systolic blood pressure [Formula: see text] 90 mmHg), transfusion (within 4 h), anemia (Hb < 12 g/day in women, < 13 g/day in men), and macrocytosis were significantly associated with 30-day mortality (adjusted HR = 1.4; 95% confidence interval 1.01-1.94; p = 0.046) in major trauma patients. Thus, initial macrocytosis independently predicted 30-day mortality in patients with major trauma at a Level I trauma center.

Successful endovascular treatment of an obstruction following the surgical repair of a traumatic portal vein injury: a case report.

Traumatic portal vein injury is rare, but the associated mortality rate ranges from 50% to 70%. The management of this injury is difficult and remains controversial. In this case report, we describe the successful endovascular treatment of an obstruction that developed following the surgical repair of a traumatic portal vein injury. A man in his mid-40s who had been injured in a car accident presented to our trauma center with abdominal pain, abdominal distension, and open wounds over both knees. Emergency laparotomy revealed a longitudinal rupture from the upper border of the pancreas to the mid-portion of the portal vein; his hemorrhage was successfully controlled surgically. However, postoperative abdominal computed tomography imaging revealed portal vein obstruction. One week after admission to the intensive care unit, an endovascular stent was successfully inserted into the patient's portal vein via a percutaneous transhepatic approach. The associated injuries, including the distal common bile duct obstruction, were successfully managed by choledochojejunostomy. The patient's postoperative recovery was uneventful. Thus, endovascular stent placement is an effective and safe means of treating an obstruction following the surgical repair of a traumatic portal vein injury.

Comparing machine learning and logistic regression for acute kidney injury prediction in trauma patients: A retrospective observational study at a single tertiary medical center.

Acute kidney injury (AKI) is common in patients with trauma and is associated with poor outcomes. Therefore, early prediction of AKI in patients with trauma is important for risk stratification and the provision of optimal intensive care unit treatment. This study aimed to compare 2 models, machine learning (ML) techniques and logistic regression, in predicting AKI in patients with trauma. We retrospectively reviewed the charts of 400 patients who sustained torso injuries between January 2016 and June 2020. Patients were included if they were aged > 15 years, admitted to the intensive care unit, survived for > 48 hours, had thoracic and/or abdominal injuries, had no end-stage renal disease, and had no missing data. AKI was defined in accordance with the Kidney Disease Improving Global Outcomes definition and staging system. The patients were divided into 2 groups: AKI (n = 78) and non-AKI (n = 322). We divided the original dataset into a training (80%) and a test set (20%), and the logistic regression with stepwise selection and ML (decision tree with hyperparameter optimization using grid search and cross-validation) was used to build a model for predicting AKI. The models established using the training dataset were evaluated using a confusion matrix receiver operating characteristic curve with the test dataset. We included 400 patients with torso injury, of whom 78 (19.5%) progressed to AKI. Age, intestinal injury, cumulative fluid balance within 24 hours, and the use of vasopressors were independent risk factors for AKI in the logistic regression model. In the ML model, vasopressors were the most important feature, followed by cumulative fluid balance within 24 hours and packed red blood cell transfusion within 4 hours. The accuracy score showed no differences between the 2 groups; however, the recall and F1 score were significantly higher in the ML model (.94 vs 56 and.75 vs 64, respectively). The ML model performed better than the logistic regression model in predicting AKI in patients with trauma. ML techniques can aid in risk stratification and the provision of optimal care.