Background: Early recognition and prevention of in-hospital cardiac arrest (IHCA) have played an increasingly important role in the chain of survival. However, clinical tools for predicting IHCA are scarce, particularly in the emergency department (ED). We sought to estimate the incidence of ED-based IHCA and to develop and validate a novel triage tool, the Emergency Department In-hospital Cardiac Arrest Score (EDICAS), for predicting ED-based IHCA.

Methods: In this retrospective cohort study we used electronic clinical warehouse data from a tertiary medical center with approximately 100,000 ED visits per year. We extracted data from 733,398 ED visits over a seven-year period. We selected one ED visit per person and excluded out-of-hospital cardiac arrest or children. Patient demographics and computerized triage information were included as potential predictors.

Results: A total of 325,502 adult ED patients were included. Of these patients, 623 (0.2%) developed ED-based IHCA. The EDICAS, which includes age and arrival mode and categorizes vital signs with simple cut-offs, showed excellent discrimination (area under the receiver operating characteristic [AUROC] curve, 0.87) and maintained its discriminatory ability (AUROC, 0.86) in cross-validation. Previously developed early warning scores showed lower AUROC (0.77 for the Modified Early Warning Score and 0.83 for the National Early Warning Score) when applied to our ED population.

Conclusion: In-hospital cardiac arrest in the ED is relatively uncommon. We developed and internally validated a novel tool for predicting imminent IHCA in the ED. Future studies are warranted to determine whether this tool could gain lead time to identify high-risk patients and potentially reduce ED-based IHCA.

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.

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.

Introduction: Bacteremia, a common disease but difficult to diagnose early, may result in significant morbidity and mortality without prompt treatment. We aimed to develop machine-learning (ML) algorithms to predict patients with bacteremia from febrile patients presenting to the emergency department (ED) using data that is readily available at the triage.

Methods: We included all adult patients (≥18 years of age) who presented to the emergency department (ED) of National Taiwan University Hospital (NTUH), a tertiary teaching hospital in Taiwan, with the chief complaint of fever or measured body temperature more than 38°C, and who received at least one blood culture during the ED encounter. We extracted data from the Integrated Medical Database of NTUH from 2009–2018.The dataset included patient demographics, triage details, symptoms, and medical history. The positive blood culture result of at least one potential pathogen was defined as bacteremia and used as the binary classification label. We split the dataset into training/validation and testing sets (60-to-40 ratio) and trained five supervised ML models using K-fold cross-validation. The model performance was evaluated using the area under the receiver operating characteristic curve (AUC) in the testing set.

Results: We included 80,201 cases in this study. Of them, 48120 cases were assigned to the training/validation set and 32,081 to the testing set. Bacteremia was identified in 5,831 (12.1%) and 3,824 (11.9%) cases of the training/validation set and test set, respectively. All ML models performed well, with CatBoost achieving the highest AUC (.844, 95% confidence interval [CI] .837-.850), followed by extreme gradient boosting (.843, 95% CI .836-.849), gradient boosting (.842, 95% CI .836-.849), light gradient boosting machine (.841, 95% CI .834-.847), and random forest (.828, 95% CI .821-.834).

Conclusion: Our machine-learning model has shown excellent discriminatory performance to predict bacteremia based only on clinical features at ED triage. It has the potential to improve care quality and save more lives if successfully implemented in the ED. 

Introduction: Diverse coronavirus disease 2019 (COVID-19) mortalities have been reported but focused on identifying susceptible patients at risk of more severe disease or death. This study aims to investigate the mortality variations of COVID-19 from different hospital settings during different pandemic phases.

Methods: We retrospectively included adult (≥18 years) patients who visited emergency departments (ED) of five hospitals in the state of Texas and who were diagnosed with COVID-19 between March–November 2020. The included hospitals were dichotomized into urban and suburban based on their geographic location. The primary outcome was mortality that occurred either during hospital admission or within 30 days after the index ED visit. We used multivariable logistic regression to investigate the associations between independent variables and outcome. Generalized additive models were employed to explore the mortality variation during different pandemic phases.

Results: A total of 1,788 adult patients who tested positive for COVID-19 were included in the study. The median patient age was 54.6 years, and 897 (50%) patients were male. Urban hospitals saw approximately 59.5% of the total patients. A total of 197 patients died after the index ED visit. The analysis indicated visits to the urban hospitals (odds ratio [OR] 2.14, 95% confidence interval [CI], 1.41, 3.23), from March to April (OR 2.04, 95% CI, 1.08, 3.86), and from August to November (OR 2.15, 95% CI, 1.37, 3.38) were positively associated with mortality.

Conclusion: Visits to the urban hospitals were associated with a higher risk of mortality in patients with COVID-19 when compared to visits to the suburban hospitals. The mortality risk rebounded and showed significant difference between urban and suburban hospitals since August 2020. Optimal allocation of medical resources may be necessary to bridge this gap in the foreseeable future.

Introduction: Within a few months coronavirus disease 2019 (COVID-19) evolved into a pandemic causing millions of cases worldwide, but it remains challenging to diagnose the disease in a timely fashion in the emergency department (ED). In this study we aimed to construct machine-learning (ML) models to predict severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) infection based on the clinical features of patients visiting an ED during the early COVID-19 pandemic.

Methods: We retrospectively collected the data of all patients who received reverse transcriptase polymerase chain reaction (RT-PCR) testing for SARS-CoV-2 at the ED of Baylor Scott & White All Saints Medical Center, Fort Worth, from February 23–May 12, 2020. The variables collected included patient demographics, ED triage data, clinical symptoms, and past medical history. The primary outcome was the confirmed diagnosis of COVID-19 (or SARS-CoV-2 infection) by a positive RT-PCR test result for SARS-CoV-2, and was used as the label for ML tasks. We used univariate analyses for feature selection, and variables with P<0.1 were selected for model construction. Samples were split into training and testing cohorts on a 60:40 ratio chronologically. We tried various ML algorithms to construct the best predictive model, and we evaluated performances with the area under the receiver operating characteristic curve (AUC) in the testing cohort.

Results: A total of 580 ED patients were tested for SARS-CoV-2 during the study periods, and 98 (16.9%) were identified as having the SARS-CoV-2 infection based on the RT-PCR results. Univariate analyses selected 21 features for model construction. We assessed three ML methods for performance: of the three methods, random forest outperformed the others with the best AUC result (0.86), followed by gradient boosting (0.83) and extra trees classifier (0.82).

Conclusion: This study shows that it is feasible to use ML models as an initial screening tool for identifying patients with SARS-CoV-2 infection. Further validation will be necessary to determine how effectively this prediction model can be used prospectively in clinical practice.

Introduction: Healthcare professionals frequently experience work-related fatigue, which may jeopardize their health and put patient safety at risk. In this study, we applied a machine learning (ML) approach based on data collected from a smartwatch to construct prediction models of work-related fatigue for emergency clinicians.

Methods: We conducted this prospective study at the emergency department (ED) of a tertiary teaching hospital from March 10–June 20, 2021, where we recruited physicians, nurses, and nurse practitioners. All participants wore a commercially available smartwatch capable of measuring various physiological data during the experiment. Participants completed the Multidimensional Fatigue Inventory (MFI) web form before and after each of their work shifts. Wecalculated and labeled the before-and-after-shift score differences between each pair of scores. Using several tree-based algorithms, we constructed the prediction models based on features collected from the smartwatch. Records were split into training/validation and testing sets at a 70∶30 ratio, and we evaluated the performances using the area under the curve (AUC) measure of receiver operating characteristic on the test set.

Results: In total, 110 participants were included in this study, contributing to a set of 1,542 effective records. Of these records, 85 (5.5%) were labeled as having work-related fatigue when setting the MFI difference between two standard deviations as the threshold. The mean age of the participants was 29.6. Most of the records were collected from nurses (87.7%) and females (77.5%). We selected a union of 31 features to construct the models. For total participants, CatBoost classifier achieved the best performances of AUC (0.838, 95% confidence interval [CI] 0.742–0.918) to identify work-related fatigue. By focusing on a subgroup of nurses <35 years in age, XGBoost classifier obtained excellent performance of AUC (0.928, 95% CI 0.839–0.991) on the test set.

Conclusion: By using features derived from a smartwatch, we successfully built ML models capable of classifying the risk of work-related fatigue in the ED. By collecting more data to optimize the models, it should be possible to use smartwatch-based ML models in the future to predict work-related fatigue and adopt preventive measures for emergency clinicians.

Background: During cardiopulmonary resuscitation (CPR), end-tidal carbon dioxide (EtCO2) is primarily determined by pulmonary blood flow, thereby reflecting the blood flow generated by CPR. We aimed to develop an EtCO2 trajectory-based prediction model for prognostication at specific time points during CPR in patients with out-of-hospital cardiac arrest (OHCA).

Methods: We screened patients receiving CPR between 2015–2021 from a prospectively collected database of a tertiary-care medical center. The primary outcome was survival to hospital discharge. We used group-based trajectory modeling to identify the EtCO2 trajectories. Multivariable logistic regression analysis was used for model development and internally validated using bootstrapping. We assessed performance of the model using the area under the receiver operating characteristic curve (AUC).

Results: The primary analysis included 542 patients with a median age of 68.0 years. Three distinct EtCO2 trajectories were identified in patients resuscitated for 20 minutes (min): low (average EtCO2 10.0 millimeters of mercury [mm Hg]; intermediate (average EtCO2 26.5 mm Hg); and high (average EtCO2: 51.5 mm Hg). Twenty-min EtCO2 trajectory was fitted as an ordinal variable (low, intermediate, and high) and positively associated with survival (odds ratio 2.25, 95% confidence interval [CI] 1.07–4.74). When the 20-min EtCO2 trajectory was combined with other variables, including arrest location and arrest rhythms, the AUC of the 20-min prediction model for survival was 0.89 (95% CI 0.86–0.92). All predictors in the 20-min model remained statistically significant after bootstrapping.

Conclusion: Time-specific EtCO2 trajectory was a significant predictor of OHCA outcomes, which could be combined with other baseline variables for intra-arrest prognostication. For this purpose, the 20-min survival model achieved excellent discriminative performance in predicting survival to hospital discharge.