Introduction: Timely diagnosis of patients affected by an emerging infectious disease plays a crucial role in treating patients and avoiding disease spread. In prior research, we developed an approach by using machine learning (ML) algorithms to predict serious acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection based on clinical features of patients visiting an emergency department (ED) during the early coronavirus 2019 (COVID-19) pandemic. In this study, we aimed to externally validate this approach within a distinct ED population.

Methods: To create our training/validation cohort (model development) we collected data retrospectively from suspected COVID-19 patients at a US ED from February 23–May 12, 2020. Another dataset was collected as an external validation (testing) cohort from an ED in another country from May 12–June 15, 2021. Clinical features including patient demographics and triage information were used to train and test the models. The primary outcome was the confirmed diagnosis of COVID-19, defined as a positive reverse transcription polymerase chain reaction test result for SARS-CoV-2. We employed three different ML algorithms, including gradient boosting, random forest, and extra trees classifiers, to construct the predictive model. The predictive performances were evaluated with the area under the receiver operating characteristic curve (AUC) in the testing cohort.

Results: In total, 580 and 946 ED patients were included in the training and testing cohorts, respectively. Of them, 98 (16.9%) and 180 (19.0%) were diagnosed with COVID-19. All the constructed ML models showed acceptable discrimination, as indicated by the AUC. Among them, random forest (0.785, 95% confidence interval [CI] 0.747–0.822) performed better than gradient boosting (0.774, 95% CI 0.739–0.811) and extra trees classifier (0.72, 95% CI 0.677–0.762). There was no significant difference between the constructed models.

Conclusion: Our study validates the use of ML for predicting COVID-19 in the ED and demonstrates its potential for predicting emerging infectious diseases based on models built by clinical features with temporal and spatial heterogeneity. This approach holds promise for scenarios where effective diagnostic tools for an emerging infectious disease may be lacking in the future.

Background: Transesophageal echocardiography (TEE) has been introduced in resuscitative scenarios in recent decades, with a growing number of emergency physicians learning, performing, and studying resuscitative TEE.

Objective: Our goal was to characterize publishing trends regarding TEE use in emergency medicine (EM) and to investigate the increasing interest in potential applications of TEE in emergency departments (ED).

Methods: We retrieved published research associated with the use of TEE in EM from the Web of Science database from inception to December 31, 2023. We analyzed trends based on the number of articles published annually. To systematically map trends related to TEE in emergency medicine (EM), we extracted data on the number of unique EM TEE practitioners, institutions performing EM TEE, study topics, and other characteristics from research articles and case reports. To better reflect research trends, we exclusively conducted subgroup analysis on the research articles. We used linear regression analysis to analyze trends and conducted checkpoints on the timelines.

Results: Of the 964 titles and abstracts screened, we included 99 eligible published articles after careful review. Articles related to EM TEE increased from one article in 1991 to 20 articles in 2023, and the rate of publication has increased rapidly since 2018 (+12.4 publications per year, 95% confidence interval [CI] 9.8-15.0, P<0.001). The number of EM TEE practitioners and EM TEE-performing institutions underwent a rapid expansion with an inflection point between 2018–2020, with a rate of +91.7 practitioners per year and +36.5 institutions per year. Subgroup analysis revealed a similar trend in the published research articles. The most common indications for EM TEE were cardiac arrest (72.7%), shock (13.1%), and procedural guidance (11.1%). The United States published the majority of EM TEE-related articles (51.5%). 

Conclusion: The present study highlights that TEE-related articles in EM continue to accelerate. Among the indications for TEE, cardiac arrest remains the most frequently discussed. This scoping review provides insights into the expanding interest and applications of TEE in the field of EM.

Introduction: Regional anesthesia (RA) has become a prominent component of multimodal pain management in emergency medicine (EM), and its use has increased rapidly in recent decades. Nevertheless, there is a paucity of data on how RA practice has evolved in the specialty. In this study we sought to investigate how RA has been implemented in EM by analyzing trends of published articles and to describe the characteristics of the published research.

Methods: We retrieved RA-related publications from the SciVerse Scopus database from inception to January 13, 2022, focusing on studies associated with the use of RA in EM. The primary outcome was an analysis of trend based on the number of annual publications. Other outcomes included reports of technique diversity by year, trends in the use of individual techniques, and characteristics of published articles. We used linear regression analysis to analyze trends.

Results: In total, 133 eligible publications were included. We found that overall 23 techniques have been described and results published in the EM literature. Articles related to RA increased from one article in 1982 to 18 in 2021, and the rate of publication has increased more rapidly since 2016. Reports of lower extremity blocks (60.90%) were published most frequently in ranked-first aggregated citations. The use of thoracic nerve blocks, such as the erector spinae plane block, has increased exponentially in the past three years. The United States (41.35%) has published the most RA-related articles. Regional anesthesia administered by emergency physicians (52.63%) comprised the leading field in published articles related to RA. Most publications discussed single-shot (88.72%) and ultrasound-guided methods (55.64%).

Conclusion: This study highlights that the number of published articles related to regional anesthesia in EM has increased. Although RA research has primarily focused on lower extremity blocks, clinical researchers continue to broaden the field of study to encompass a wide spectrum of techniques and indications.