This study aimed to develop a machine learning-based clinical decision support system for emergency departments based on the decision-making framework of physicians. We extracted 27 fixed and 93 observation features using data vital signs, mental status, laboratory results, electrocardiograms during department stay. Outcomes included intubation, admission intensive care unit, inotrope or vasopressor administration, in-hospital cardiac arrest. eXtreme gradient boosting algorithm was used...

Post contrast-acute kidney injury (PC-AKI) is defined as the deterioration of renal function after administration iodinated contrast media. HMGB1 known to play an important role in development acute injury. The purpose this study was investigate association between and PC-AKI protective effect glycyrrhizin, a direct inhibitor HMGB1, rats. Rats were divided into three groups: control, with glycyrrhizin. Oxidative stress measured MDA levels H

Intermittent manual measurement of vital signs may not rapidly predict sepsis development in febrile patients admitted to the emergency department (ED). We aimed evaluate predictive performance a wireless monitoring device that continuously measures heart rate (HR) and respiratory (RR) machine learning analysis but stable ED. analysed 468 (age, ≥18 years; training set, n = 277; validation 93; test 98) having fever (temperature >38 °C) isolation care unit The AUROC fragmented model with data...

In this retrospective observational study, we aimed to develop a machine-learning model using data obtained at the prehospital stage predict in-hospital cardiac arrest in emergency department (ED) of patients transferred via medical services. The dataset was constructed by attaching information from National Fire Agency and hospital factors Emergency Department Information System. Machine-learning models were developed patient variables, with without factors. We validated performance used...

Models for predicting acute myocardial infarction (AMI) at the prehospital stage were developed and their efficacy compared, based on variables identified from a nationwide systematic emergency medical service (EMS) registry using conventional statistical methods machine learning algorithms. Patients in EMS cardiovascular aged >15 years who transferred public to departments Korea January 2016 December 2018 enrolled. Two datasets constructed according hierarchical structure of registry. A...

Hemorrhagic shock (HS) is a life-threatening condition with high mortality rates despite current treatments. This study investigated whether targeted temperature management (TTM) could improve outcomes by modulating inflammation and protecting organs following HS. Using rat model of HS, TTM was applied at 33°C 36°C after fluid resuscitation. Surprisingly, increased mortality, while significantly improved survival rates. It also reduced histological damage in lung kidney tissues, lowered...

Introduction The coronavirus disease (COVID-19) pandemic has delayed the management of other serious medical conditions. This study presents an efficient method to prevent degradation quality diagnosis and treatment critical diseases during pandemic. Methods We performed a retrospective observational study. primary outcome was ED length stay (ED LOS). secondary outcomes were door-to-balloon time in patients with suspected ST-segment elevation myocardial infarction door-to-brain computed...

Considering the risk of coronavirus disease (COVID-19) transmission through infected droplets, emergency department (ED) operations in response to febrile patients should be planned. We investigated general and clinical characteristics visiting ED changes admission rates via during COVID-19 outbreak.We performed a retrospective analysis prospectively collected who visited 402 EDs Republic Korea with symptoms between January 27 May 31, 2020 compared them those enrolled before outbreak. The...

Upper gastrointestinal bleeding (UGIB) is a major cause of clinical deterioration worldwide. A large number patients with UGIB cannot be diagnosed through endoscopy, which normally the diagnostic method choice. Therefore, this study aimed to investigate value multi-detector computed tomography (MDCT) for suspected UGIB. In retrospective observational 386 patients, we compared contrast-enhanced abdominopelvic MDCT endoscopy analyze performance in identifying status, location origin, and...

In this study, we developed a model to predict culture test results for pulmonary tuberculosis (PTB) with customized multimodal approach and evaluated its performance in different clinical settings. Moreover, investigated potential improvements by combining deep learning-based automated detection algorithms (DLADs). This retrospective observational study enrolled patients over 18 years of age who consecutively visited the level 1 emergency department underwent chest radiograph sputum...

<sec> <title>BACKGROUND</title> Since acute myocardial infarction (AMI) is a leading cause of mortality worldwide, the accurate evaluation risk factors AMI at prehospital stage enables appropriate management and rapid transportation patients to most hospital for treatment. The prediction derived from national database may accelerate early recognition timely improve survival rate. </sec> <title>OBJECTIVE</title> This study was conducted develop compare efficacy models based on variables...

Introduction Febrile neutropenia (FN) is one of the major complications with high mortality rates in cancer patients undergoing chemotherapy. The Multinational Association for Supportive Care Cancer (MASCC) risk-index score has limited applicability routine use emergency department (ED). This study aimed to develop simplified new nomograms that can predict 28-day and development serious medical FN by using a combination complete blood count (CBC) parameters quick Sequential Organ Failure...

Abstract The array of complex and evolving patient data has limited clinical decision making in the emergency department (ED). This study introduces an advanced deep learning algorithm designed to enhance real-time prediction accuracy for integration into a novel Clinical Decision Support System (CDSS). A retrospective was conducted using from level 1 tertiary hospital. algorithm’s predictive performance evaluated based on in-hospital cardiac arrest, inotropic circulatory support, airway,...

The American Heart Association guidelines recommend switching chest compression providers at least every 2 min depending on their fatigue during cardiopulmonary resuscitation (CPR). Although the provider's heart rate is widely used as an objective indicator for detecting fatigue, accuracy of this measure debatable.This study was designed to determine whether real-time a in providers.A simulation-based prospective interventional including 110 participants.Participants performed compressions...