This study was designed to develop machine-learning models to predict COVID-19 mortality and identify its key features based on clinical characteristics and laboratory tests. For this, deep-learning (DL) and machine-learning (ML) models were developed using receiver operating characteristic (ROC) area under the curve (AUC) and F1 score optimization of 87 parameters. Of the two, the DL model exhibited better performance (AUC 0.8721, accuracy 0.84, and F1 score 0.76). However, we also blended DL with ML, and the ensemble model performed the best (AUC 0.8811, accuracy 0.85, and F1 score 0.77). The DL model is generally unable to extract feature importance; however, we succeeded by using the Shapley Additive exPlanations method for each model. This study demonstrated both the applicability of DL and ML models for classifying COVID-19 mortality using hospital-structured data and that the ensemble model had the best predictive ability.

PurposeRecently many cases of appendectomy have been conducted by single-incision laparoscopic technique. The aim of this study is to figure out the benefits of transumbilical single-port laparoscopic appendectomy (TULA) compared with conventional three-port laparoscopic appendectomy (CTLA).MethodsFrom 2010 to 2012, 89 patients who were diagnosed as acute appendicitis and then underwent laparoscopic appendectomy a single surgeon were enrolled in this study and with their medical records were reviewed retrospectively. Cases of complicated appendicitis confirmed on imaging tools and patients over 3 points on the American Society of Anesthesia score were excluded.ResultsAmong the total of 89 patients, there were 51 patients in the TULA group and 38 patients in the CTLA group. The visual analogue scale (VAS) of postoperative day (POD) #1 was higher in the TULA group than in the CTLA group (P = 0.048). The operative time and other variables had no statistical significances (P > 0.05).ConclusionDespite the insufficiency of instruments and the difficulty of handling, TULA was not worse in operative time, VAS after POD #2, and the total operative cost than CTLA. And, if there are no disadvantages of TULA, TULA may be suitable in substituting three-port laparoscopic surgery and could be considered as one field of natural orifice transluminal endoscopic surgery with the improvement and development of the instruments and revised studies.

No abstract

Background An artificial-intelligence (AI) model for predicting the prognosis or mortality of coronavirus disease 2019 (COVID-19) patients will allow efficient allocation of limited medical resources. We developed an early mortality prediction ensemble model for COVID-19 using AI models with initial chest X-ray and electronic health record (EHR) data. Results We used convolutional neural network (CNN) models (Inception-ResNet-V2 and EfficientNet) for chest X-ray analysis and multilayer perceptron (MLP), Extreme Gradient Boosting (XGBoost), and random forest (RF) models for EHR data analysis. The Gradient-weighted Class Activation Mapping and Shapley Additive Explanations (SHAP) methods were used to determine the effects of these features on COVID-19. We developed an ensemble model (Area under the receiver operating characteristic curve of 0.8698) using a soft voting method with weight differences for CNN, XGBoost, MLP, and RF models. To resolve the data imbalance, we conducted F1-score optimization by adjusting the cutoff values to optimize the model performance (F1 score of 0.77). Conclusions Our study is meaningful in that we developed an early mortality prediction model using only the initial chest X-ray and EHR data of COVID-19 patients. Early prediction of the clinical courses of patients is helpful for not only treatment but also bed management. Our results confirmed the performance improvement of the ensemble model achieved by combining AI models. Through the SHAP method, laboratory tests that indicate the factors affecting COVID-19 mortality were discovered, highlighting the importance of these tests in managing COVID-19 patients.