The long-term treatment trends of splenic injuries can provide guidance when treating trauma patients. The nonoperative management (NOM) of splenic injuries was introduced in early 1989. After decades of development, it has proven to be safe and is now the primary treatment choice worldwide. However, there remains a lack of nationwide registry data to support the feasibility and efficiency of NOM. We used the Taiwan National Health Insurance Research Database to conduct a whole population-based cohort study. Patients admitted with blunt splenic injuries from 2002 to 2013 were identified. Demographic data, management methods, associated injuries, comorbidities and outcome parameters were collected. Patients were divided into 2 groups by the type of admitting institution: a tertiary center or a non-center hospital. We also used 4 years as an interval to analyze the changes in epidemiological data and treatment trends. Comparisons of the results of NOM and surgical management were also performed. A total of 12,455 patients were admitted with blunt splenic injuries between 2002 and 2013. Among the 11,551 patients treated in a single hospital after admission, patients underwent NOM more frequently at tertiary centers than at non-center hospitals (64.6% vs 50.3%). During the 12-year study period, the NOM rate increased from 56 to 73% in tertiary centers, while in noncenter hospitals, the rate only increased from 43 to 58%. The mortality rate decreased in tertiary centers from 8.9 to 7.2%, with no apparent change in noncenter hospitals. Complications occurred more frequently in the surgical management group. There is a trend toward the use of NOM for blunt splenic injury treatments, and the outcomes from the NOM groups were not inferior to those of the operation group. In addition, tertiary centers performed more NOM than did non-center hospitals and better met the international consensus.

Objective: To identify the feasibility and efficiency of deep convolutional neural networks (DCNNs) in the detection of ankle fractures and to explore ensemble strategies that applied multiple projections of radiographs. Ankle radiographs (AXRs) are the primary tool used to diagnose ankle fractures. Applying DCNN algorithms on AXRs can potentially improve the diagnostic accuracy and efficiency of detecting ankle fractures. Methods: A DCNN was trained using a trauma image registry, including 3102 AXRs. We separately trained the DCNN on anteroposterior (AP) and lateral (Lat) AXRs. Different ensemble methods, such as “sum-up,” “severance-OR,” and “severance-Both,” were evaluated to incorporate the results of the model using different projections of view. Results: The AP/Lat model’s individual sensitivity, specificity, positive-predictive value, accuracy, and F1 score were 79%/84%, 90%/86%, 88%/86%, 83%/85%, and 0.816/0.850, respectively. Furthermore, the area under the receiver operating characteristic curve (AUROC) of the AP/Lat model was 0.890/0.894 (95% CI: 0.826–0.954/0.831–0.953). The sum-up method generated balanced results by applying both models and obtained an AUROC of 0.917 (95% CI: 0.863–0.972) with 87% accuracy. The severance-OR method resulted in a better sensitivity of 90%, and the severance-Both method obtained a high specificity of 94%. Conclusion: Ankle fracture in the AXR could be identified by the trained DCNN algorithm. The selection of ensemble methods can depend on the clinical situation which might help clinicians detect ankle fractures efficiently without interrupting the current clinical pathway. Advances in knowledge: This study demonstrated different ensemble strategies of AI algorithms on multiple view AXRs to optimize the performance in various clinical needs.

This study aimed to assess current evidence regarding the effect of selenium (Se) supplementation on the prognosis in patients sustaining trauma. MEDLINE, Embase, and Web of Science databases were searched with the following terms: “trace element”, “selenium”, “copper”, “zinc”, “injury”, and “trauma”. Seven studies were included in the meta-analysis. The pooled results showed that Se supplementation was associated with a lower mortality rate (OR 0.733, 95% CI: 0.586, 0.918, p = 0.007; heterogeneity, I² = 0%). Regarding the incidence of infectious complications, there was no statistically significant benefit after analyzing the four studies (OR 0.942, 95% CI: 0.695, 1.277, p = 0.702; heterogeneity, I² = 14.343%). The patients with Se supplementation had a reduced ICU length of stay (standard difference in means (SMD): −0.324, 95% CI: −0.382, −0.265, p < 0.001; heterogeneity, I² = 0%) and lesser hospital length of stay (SMD: −0.243, 95% CI: −0.474, −0.012, p < 0.001; heterogeneity, I² = 45.496%). Se supplementation after trauma confers positive effects in decreasing the mortality and length of ICU and hospital stay.

Uncontrolled post-traumatic hemorrhage is an important cause of traumatic mortality that can be avoided. This study intends to use machine learning (ML) to build an algorithm based on data collected from an electronic health record (EHR) system to predict the risk of delayed bleeding in trauma patients in the ICU. We enrolled patients with torso trauma in the surgical ICU. Demographic features, clinical presentations, and laboratory data were collected from EHR. The algorithm was designed to predict hemoglobin dropping 6 h before it happened and evaluated the performance with 10-fold cross-validation. We collected 2218 cases from 2008 to 2018 in a trauma center. There were 1036 (46.7%) patients with positive hemorrhage events during their ICU stay. Two machine learning algorithms were used to predict ongoing hemorrhage events. The logistic model tree (LMT) and the random forest algorithm achieved an area under the curve (AUC) of 0.816 and 0.809, respectively. In this study, we presented the ML model using demographics, vital signs, and lab data, promising results in predicting delayed bleeding risk in torso trauma patients. Our study also showed the possibility of an early warning system alerting ICU staff that trauma patients need re-evaluation or further survey.