Development and External Validation of Clinical Features-based Machine Learning Models for Predicting COVID-19 in the Emergency Department.

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.

Point-of-Care Ultrasound in Airway Evaluation and Management: A Comprehensive Review.

Airway management is a common and critical procedure in acute settings, such as the Emergency Department (ED) or Intensive Care Unit (ICU) of hospitals. Many of the traditional physical examination methods have limitations in airway assessment. Point-of-care ultrasound (POCUS) has emerged as a promising tool for airway management due to its familiarity, accessibility, safety, and non-invasive nature. It can assist physicians in identifying relevant anatomy of the upper airway with objective measurements of airway parameters, and it can guide airway interventions with dynamic real-time images. To date, ultrasound has been considered highly accurate for assessment of the difficult airway, confirmation of proper endotracheal intubation, prediction of post-extubation laryngeal edema, and preparation for cricothyrotomy by identifying the cricothyroid membrane. This review aims to provide a comprehensive overview of the key evidence on the use of ultrasound in airway management. Databases including PubMed and Embase were systematically searched. A search strategy using a combination of the term "ultrasound" combined with several search terms, i.e., "probe", "anatomy", "difficult airway", "endotracheal intubation", "laryngeal edema", and "cricothyrotomy" was performed. In conclusion, POCUS is a valuable tool with multiple applications ranging from pre- and post-intubation management. Clinicians should consider using POCUS in conjunction with traditional exam techniques to manage the airway more efficiently in the acute setting.

End-tidal Carbon Dioxide + Return of Spontaneous Circulation After Cardiac Arrest (RACA) Score to Predict Outcomes After Out-of-hospital Cardiac Arrest.

INTRODUCTION: The return of spontaneous circulation after cardiac arrest (RACA) score is a well-validated model for estimating the probability of return of spontaneous circulation (ROSC) in patients with out-of-hospital cardiac arrest (OHCA) by incorporating several variables, including gender, age, arrest aetiology, witness status, arrest location, initial cardiac rhythms, bystander cardiopulmonary resuscitation (CPR), and emergency medical services (EMS) arrival time. The RACA score was initially designed for comparisons between different EMS systems by standardising ROSC rates. End-tidal carbon dioxide (EtCO2) is a quality indicator of CPR. We aimed to improve the performance of the RACA score by adding minimum EtCO2 measured during CPR to develop the EtCO2 + RACA score for OHCA patients transported to an emergency department (ED). METHODS: This was a retrospective analysis using prospectively collected data for OHCA patients resuscitated at an ED during 2015-2020. Adult patients with advanced airways inserted and available EtCO2 measurements were included. We used the EtCO2 values recorded in the ED for analysis. The primary outcome was ROSC. In the derivation cohort, we used multivariable logistic regression to develop the model. In the temporally split validation cohort, we assessed the discriminative performance of the EtCO2 + RACA score by the area under the receiver operating characteristic curve (AUC) and compared it with the RACA score using the DeLong test. RESULTS: There were 530 and 228 patients in the derivation and validation cohorts, respectively. The median measurements of EtCO2 were 8.0 times (interquartile range [IQR] 3.0-12.0 times), with the median minimum EtCO2 of 15.5 millimeters of mercury (mm Hg) (IQR 8.0-26.0 mm Hg). The median RACA score was 36.4% (IQR 28.9-48.0%), and a total of 393 patients (51.8%) achieved ROSC. The EtCO2 + RACA score was validated with good discriminative performance (AUC, 0.82, 95% CI 0.77-0.88), outperforming the RACA score (AUC, 0.71, 95% CI 0.65-0.78) (DeLong test: P < 0.001). CONCLUSION: The EtCO2 + RACA score may facilitate the decision-making process regarding allocations of medical resources in EDs for OHCA resuscitation.