ABSTRACT
Background@#Worldwide, sepsis is the leading cause of death in hospitals. If mortality rates in patients with sepsis can be predicted early, medical resources can be allocated efficiently. We constructed machine learning (ML) models to predict the mortality of patients with sepsis in a hospital emergency department. @*Methods@#This study prospectively collected nationwide data from an ongoing multicenter cohort of patients with sepsis identified in the emergency department. Patients were enrolled from 19 hospitals between September 2019 and December 2020. For acquired data from 3,657 survivors and 1,455 deaths, six ML models (logistic regression, support vector machine, random forest, extreme gradient boosting [XGBoost], light gradient boosting machine, and categorical boosting [CatBoost]) were constructed using fivefold cross-validation to predict mortality. Through these models, 44 clinical variables measured on the day of admission were compared with six sequential organ failure assessment (SOFA) components (PaO 2 /FIO 2 [PF], platelets (PLT), bilirubin, cardiovascular, Glasgow Coma Scale score, and creatinine).The confidence interval (CI) was obtained by performing 10,000 repeated measurements via random sampling of the test dataset. All results were explained and interpreted using Shapley’s additive explanations (SHAP). @*Results@#Of the 5,112 participants, CatBoost exhibited the highest area under the curve (AUC) of 0.800 (95% CI, 0.756–0.840) using clinical variables. Using the SOFA components for the same patient, XGBoost exhibited the highest AUC of 0.678 (95% CI, 0.626–0.730). As interpreted by SHAP, albumin, lactate, blood urea nitrogen, and international normalization ratio were determined to significantly affect the results. Additionally, PF and PLTs in the SOFA component significantly influenced the prediction results. @*Conclusion@#Newly established ML-based models achieved good prediction of mortality in patients with sepsis. Using several clinical variables acquired at the baseline can provide more accurate results for early predictions than using SOFA components. Additionally, the impact of each variable was identified.
ABSTRACT
Purpose@#Electric scooters have recently entered into wide use in South Korea because of their eco-friendliness and convenience. Associated accidents resulting in friction burns are also increasing, due to a lack of recognition of the regulations regarding drivable roads and speed limits. We present the clinical characteristics of friction burns induced by electric scooters.M ethods: We retrospectively evaluated the clinical records of 48 patients who visited our institution after accidents involving electric scooters from January 2018 to February 2022. Demographic data, including age, sex, time of the accident, the type and location of the friction burn, and associated injuries, were reviewed. @*Results@#The age of the patients ranged from 15 to 51 years. The most common injuries were superficial partial-thickness dermal burns, while 14 cases involved deep partial-thickness dermal burns. Multifocal injuries were present in a single patient in most cases. The face was the most commonly affected region, followed by the knees. The average treatment period was 13.0 days, but the follow-up period was longer in patients with facial bone fractures or other comorbidities. @*Conclusion@#Friction burns from electric scooters are increasing, but their clinical presentation and related statistics have not been reported yet. Since most patients were not injured or had only mild epidermal burns in regions with enough clothing, appropriate safety equipment can prevent burns from electric scooters. However, once accidents occur, patients often present with multiple other injuries in the extremities, so proper injury evaluation and management should be emphasized for shorter hospitalization and optimal outcomes.
