Early Prediction of Mortality for Septic Patients Visiting Emergency Room Based on Explainable Machine Learning: A Real-World Multicenter Study

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.

Clear cell odontogenic carcinoma mimicking a cystic lesion: a case of misdiagnosis

Clear cell odontogenic carcinoma (CCOC) is a rare jaw tumor that was classified as a malignant tumor of odontogenic origin in 2005 by the World Health Organization because of its aggressive and destructive growth capacity and metastasis to the lungs and lymph nodes. We report a case of a 66-year-old female who had swelling, incision and drainage history and a well-defined unicystic radiolucent lesion that was comparable to a cystic lesion. At first, the patient received decompression, and the lesion size decreased. Three months after decompression, cyst enucleation was performed. The pathologic result indicated that the lesion was CCOC. In this report we emphasize that patients with painful cystic lesions in addition to jaw enlargement and loosening teeth should be considered for the possibility of malignancy.

Skin and Soft Tissue Infection Caused by Mycobacterium abscessus Developed after Intramuscular Injection: A Case Report / 감염과화학요법

Mycobacterium abscessus is a rapidly-growing bacterium which spreads everywhere in the natural world. Lung infection is the most common infection that it causes, but skin and soft tissue infections can occur after injections, operations, or other trauma. We report a case of subcutaneous infection caused by M. abscessus followed by an intramuscular injection.

Analysis of Risk Factors for Nonunion after Intramedullary Nailing of Femoral Shaft Fracture in Adult

PURPOSE: To evaluate the union time and nonunion rate after intramedullary nailing of femoral shaft fracture in adult, we would like to analysis the operation techniques, comminution, contact surface and displacement. MATERIALS AND METHODS: We reviewed retrospectively 53 patients undergoing femoral intramedullary nailing at least 2 years postoperatively and analysised the union time and nonunion rate by operation techniques, comminution, contact surface and displacement. Patients were operated by either antegrade or retrograde intramedullary nailing. RESULTS: There were no differences in nonunion rate, the duration of bony union between antegrade and retrograde intramedullary nail groups. Significant differences were found in the duration of bony union between the Winquist and Hansen type I, II and the type III, IV (p<0.05). There were significant differences in the duration of bony union among simple, comminuted, and segmental fracture groups (p<0.05). CONCLUSION: The union time is affected by not operation techniques and fracture displacement, but Winquist-Hansen classification and number of fracture fragments in intramedullary nailing of adult femoral shaft fracture.