Disparities Associated With Electronic Behavioral Alerts for Safety and Violence Concerns in the Emergency Department.

STUDY OBJECTIVE: Although electronic behavioral alerts are placed as an alert flag in the electronic health record to notify staff of previous behavioral and/or violent incidents in emergency departments (EDs), they have the potential to reinforce negative perceptions of patients and contribute to bias. We provide characterization of ED electronic behavioral alerts using electronic health record data across a large, regional health care system. METHODS: We conducted a retrospective cross-sectional study of adult patients presenting to 10 adult EDs within a Northeastern United States health care system from 2013 to 2022. Electronic behavioral alerts were manually screened for safety concerns and then categorized by the type of concern. In our patient-level analyses, we included patient data at the time of the first ED visit where an electronic behavioral alert was triggered or, if a patient had no electronic behavioral alerts, the earliest visit in the study period. We performed a mixed-effects regression analysis to identify patient-level risk factors associated with safety-related electronic behavioral alert deployment. RESULTS: Of the 2,932,870 ED visits, 6,775 (0.2%) had associated electronic behavioral alerts across 789 unique patients and 1,364 unique electronic behavioral alerts. Of the encounters with electronic behavioral alerts, 5,945 (88%) were adjudicated as having a safety concern involving 653 patients. In our patient-level analysis, the median age for patients with safety-related electronic behavioral alerts was 44 years (interquartile range 33 to 55 years), 66% were men, and 37% were Black. Visits with safety-related electronic behavioral alerts had higher rates of discontinuance of care (7.8% vs 1.5% with no alert; P<.001) as defined by the patient-directed discharge, left-without-being-seen, or elopement-type dispositions. The most common topics in the electronic behavioral alerts were physical (41%) or verbal (36%) incidents with staff or other patients. In the mixed-effects logistic analysis, Black non-Hispanic patients (vs White non-Hispanic patients: adjusted odds ratio 2.60; 95% confidence interval [CI] 2.13 to 3.17), aged younger than 45 (vs aged 45-64 years: adjusted odds ratio 1.41; 95% CI 1.17 to 1.70), male (vs female: adjusted odds ratio 2.09; 95% CI 1.76 to 2.49), and publicly insured patients (Medicaid: adjusted odds ratio 6.18; 95% CI 4.58 to 8.36; Medicare: adjusted odds ratio 5.63; 95% CI 3.96 to 8.00 vs commercial) were associated with a higher risk of a patient having at least 1 safety-related electronic behavioral alert deployment during the study period. CONCLUSION: In our analysis, younger, Black non-Hispanic, publicly insured, and male patients were at a higher risk of having an ED electronic behavioral alert. Although our study is not designed to reflect causality, electronic behavioral alerts may disproportionately affect care delivery and medical decisions for historically marginalized populations presenting to the ED, contribute to structural racism, and perpetuate systemic inequities.

Characterizing Acute Pulmonary Embolism Cases Diagnosed at an Emergency Department Revisit Using a Statewide Clinical Registry.

STUDY OBJECTIVE: To assess the rate and characteristics of acute pulmonary embolism (PE) cases diagnosed in the emergency department (ED) following an ED discharge visit within 10 days. METHODS: This is a retrospective analysis of 40 EDs in a statewide clinical registry from 2017 to 2022. We identified adult patients with acute PEs diagnosed in the ED. We assessed PE cases wherein a prior ED visit for the same patient resulting in discharge had taken place within 10 days without interval hospitalization. We then characterized the overall rate of revisit PE cases per overall acute PE cases and per 10,000 ED discharges. We also reported on subgroups of revisit cases where the preceding visit resulted in diagnosis of COVID-19, other cardiopulmonary conditions, and cardiopulmonary symptom codes (eg, chest pain, unspecified). RESULTS: Of 24,525 acute PEs, 1,202 (4.9%, 95% confidence interval [CI] 4.6% to 5.2%) had an ED discharge within the preceding 10 days (2.0 per 10,000 ED discharges, 95% CI 1.9 to 2.1). Two hundred thirty-three (19.4%) were originally discharged with a COVID-19 diagnosis, 107 (8.9%) were originally discharged with another cardiopulmonary condition, and 201 (16.7%) were cases discharged with a nonspecific cardiopulmonary symptom code. Discharges with diagnoses of COVID-19, pneumonia, and pleural effusion had higher rates of revisits with acute PE. CONCLUSION: In this retrospective analysis, about 1 in 20 acute PEs and 2 in 10,000 ED discharges were associated with an ED revisit for acute PE. Some cases may represent potential diagnostic opportunities, whereas others may be progression of disease, risk factors for PE, or unrelated.

Applications of Artificial Intelligence in Helicopter Emergency Medical Services: A Scoping Review.

OBJECTIVE: Recent systematic reviews of acute care medicine applications of artificial intelligence (AI) have focused on hospital and general prehospital uses. The purpose of this scoping review was to identify and describe the literature on AI use with a focus on applications in helicopter emergency medical services (HEMS). METHODS: A literature search was performed with specific inclusion and exclusion criteria. Articles were grouped by characteristics such as publication year and general subject matter with categoric and temporal trend analyses. RESULTS: We identified 21 records focused on the use of AI in HEMS. These applications included both clinical and triage uses and nonclinical uses. The earliest study appeared in 2006, but over one third of the identified studies have been published in 2021 or later. The passage of time has seen an increased likelihood of HEMS AI studies focusing on nonclinical issues; for each year, the likelihood of a nonclinical focus had an odds ratio of 1.3. CONCLUSION: This scoping review provides overview and hypothesis-generating information regarding AI applications specific to HEMS. HEMS AI may be ultimately deployed in nonclinical arenas as much as or more than for clinical decision support. Future studies will inform future decisions as to how AI may improve HEMS systems design, asset deployment, and clinical care.

Development of a Novel Emergency Department Quality Measure to Reduce Very Low-Risk Syncope Hospitalizations.

STUDY OBJECTIVE: Emergency department (ED) evaluations for syncope are common, representing 1.3 million annual US visits and $2 billion in related hospitalizations. Despite evidence supporting risk stratification and outpatient management, variation in syncope hospitalization rates persist. We sought to develop a new quality measure for very low-risk adult ED patients with syncope that could be applied to administrative data. METHODS: We developed this quality measure in 2 phases. First, we used an existing prospective, observational ED patient data set to identify a very low-risk cohort with unexplained syncope using 2 variables: age less than 50 years and no history of heart disease. We then applied this to the 2019 Nationwide Emergency Department Sample (NEDS) to assess its potential effect, assessing for hospital-level factors associated with hospitalization variation. RESULTS: Of the 8,647 adult patients in the prospective cohort, 3,292 (38%) patients fulfilled these 2 criteria: age less than 50 years and no history of heart disease. Of these, 15 (0.46%) suffered serious adverse events within 30 days. In the NEDS, there were an estimated 566,031 patients meeting these 2 criteria, of whom 15,507 (2.7%; 95% confidence interval [CI] 2.48% to 3.00%) were hospitalized. We found substantial variation in the hospitalization rates for this very low-risk cohort, with a median rate of 1.7% (range 0% to 100%; interquartile range 0% to 3.9%). Factors associated with increased hospitalization rates included a yearly ED volume of more than 80,000 (odds ratio [OR] 3.14; 95% CI 2.02 to 4.89) and metropolitan teaching status (OR 1.5; 95% CI 1.24 to 1.81). CONCLUSION: In summary, our novel syncope quality measure can assess variation in low-value hospitalizations for unexplained syncope. The application of this measure could improve the value of syncope care.

Establishment of SEP-1 national practice guidelines does not impact fluid administration for septic shock patients.

BACKGROUND: The Centers for Medicare and Medicaid Services introduced the Early Management Bundle, Severe Sepsis/Septic Shock (SEP-1) as a national quality measure in October 2015. The purpose of SEP-1 is to facilitate the efficient, effective, and timely delivery of high-quality care to patients presenting along the spectrum of sepsis severity. OBJECTIVES: The primary aim of this study was to investigate whether provider practice surrounding emergency department (ED) fluid management of suspected septic shock patients was impacted by SEP-1. METHODS: The study was a retrospective observational analysis of 470,558 patient encounters at an urban academic center over a five-year period. The sample of suspected septic shock patients was defined by the following: blood cultures collected, antibiotics administered, and vasopressors initiated. Participants were divided into two cohorts based on date of presentation (Pre-SEP-1: May 1, 2013, - August 30, 2015, and Post-SEP-1: November 1, 2015, - February 28, 2018). The primary outcome was classified as a dichotomous variable based on whether the total volume of fluids administered equaled or exceeded the calculated weight-based (≥30 cc/kg) goal. Segmented logistic regression analyses were used to assess the immediate impact of SEP-1 as well as to compare the long-term trend of fluid volume administered between Pre-SEP-1 and Post-SEP-1 cohorts. RESULTS: A total of 413 and 482 septic shock patients were included in the Pre-SEP-1 and Post-SEP-1 cohorts, respectively. There was no statistically significant change in weight-based fluid management between the cohorts. The odds of compliance with the weight-based goal decreased 22% immediately following dissemination of SEP-1, however, this was not statistically significant (log-odds = -0.25, p = 0.41). A positive trend in compliance was observed during both the Pre-SEP-1 and Post-SEP-1 periods with odds ratios increasing 0.005 and 0.018 each month, respectively, however, these findings were not statistically significant (log-odds = 0.005, p = 0.736, and log-odds = 0.018, p = 0.10, respectively). CONCLUSIONS: Overall, there were no clinically or statistically meaningful changes in fluid volume resuscitation strategies for suspected septic shock patients following SEP-1. Broad mandates may not be effective tools for promoting practice change in the ED setting. Further research investigating barrier to changes in practice patterns surrounding fluid administration and other SEP-1 bundle elements is warranted.

Genomes by design.

Next-generation DNA sequencing has revealed the complete genome sequences of numerous organisms, establishing a fundamental and growing understanding of genetic variation and phenotypic diversity. Engineering at the gene, network and whole-genome scale aims to introduce targeted genetic changes both to explore emergent phenotypes and to introduce new functionalities. Expansion of these approaches into massively parallel platforms establishes the ability to generate targeted genome modifications, elucidating causal links between genotype and phenotype, as well as the ability to design and reprogramme organisms. In this Review, we explore techniques and applications in genome engineering, outlining key advances and defining challenges.

Recoded organisms engineered to depend on synthetic amino acids.

Genetically modified organisms (GMOs) are increasingly used in research and industrial systems to produce high-value pharmaceuticals, fuels and chemicals. Genetic isolation and intrinsic biocontainment would provide essential biosafety measures to secure these closed systems and enable safe applications of GMOs in open systems, which include bioremediation and probiotics. Although safeguards have been designed to control cell growth by essential gene regulation, inducible toxin switches and engineered auxotrophies, these approaches are compromised by cross-feeding of essential metabolites, leaked expression of essential genes, or genetic mutations. Here we describe the construction of a series of genomically recoded organisms (GROs) whose growth is restricted by the expression of multiple essential genes that depend on exogenously supplied synthetic amino acids (sAAs). We introduced a Methanocaldococcus jannaschii tRNA:aminoacyl-tRNA synthetase pair into the chromosome of a GRO derived from Escherichia coli that lacks all TAG codons and release factor 1, endowing this organism with the orthogonal translational components to convert TAG into a dedicated sense codon for sAAs. Using multiplex automated genome engineering, we introduced in-frame TAG codons into 22 essential genes, linking their expression to the incorporation of synthetic phenylalanine-derived amino acids. Of the 60 sAA-dependent variants isolated, a notable strain harbouring three TAG codons in conserved functional residues of MurG, DnaA and SerS and containing targeted tRNA deletions maintained robust growth and exhibited undetectable escape frequencies upon culturing ∼10(11) cells on solid media for 7 days or in liquid media for 20 days. This is a significant improvement over existing biocontainment approaches. We constructed synthetic auxotrophs dependent on sAAs that were not rescued by cross-feeding in environmental growth assays. These auxotrophic GROs possess alternative genetic codes that impart genetic isolation by impeding horizontal gene transfer and now depend on the use of synthetic biochemical building blocks, advancing orthogonal barriers between engineered organisms and the environment.

Sepsis Fluid Metric Compliance and its Impact on Outcomes of Patients with Congestive Heart Failure, End-Stage Renal Disease or Obesity.

BACKGROUND: Emergency physicians express concern administering a 30-cc/kg fluid bolus to septic shock patients with pre-existing congestive heart failure (CHF), end-stage renal disease (ESRD), or obesity, due to the perceived risk of precipitating a fluid overload state. OBJECTIVE: Our aim was to determine whether there is a difference in fluid administration to septic shock patients with these pre-existing conditions in the emergency department (ED). Secondary objectives focused on whether compliance impacts mortality, need for intubation, and length of stay. METHODS: We conducted a retrospective chart review of 470,558 ED patient encounters at a single urban academic center during a 5-year period. RESULTS: Of 847 patients with septic shock, 308 (36.36%) had no pre-existing condition and 199 (23.49%), 17 (2.01%), and 154 (18.18%) had the single pre-existing condition of CHF, ESRD, and obesity, respectively, and 169 (19.95%) had multiple pre-existing conditions. Weight-based fluid compliance was achieved in 460 patients (54.31%). There was a lower likelihood of compliance among patients with CHF (adjusted odds ratio [aOR] 0.35; 95% confidence interval [CI] 0.24-0.52; p < 0.001), ESRD (aOR 0.11, 95% CI 0.04-0.32; p < 0.001), and obesity (aOR 0.29, 95% CI 0.19-0.44; p < 0.001) compared with patients with no pre-existing conditions. Compliance decreased further in patients with multiple pre-existing conditions (aOR 0.49, 95% CI 0.33-0.72; p < 0.001). Compliance was not associated with mortality in patients with CHF and ESRD, but was protective in patients with obesity and those with no pre-existing conditions. CONCLUSIONS: Septic shock patients with pre-existing CHF, ESRD, or obesity are less likely to achieve compliance with a 30-cc/kg weight-based fluid goal compared with those without these pre-existing conditions.

Development and Validation of the Quick COVID-19 Severity Index: A Prognostic Tool for Early Clinical Decompensation.

STUDY OBJECTIVE: The goal of this study is to create a predictive, interpretable model of early hospital respiratory failure among emergency department (ED) patients admitted with coronavirus disease 2019 (COVID-19). METHODS: This was an observational, retrospective, cohort study from a 9-ED health system of admitted adult patients with severe acute respiratory syndrome coronavirus 2 (COVID-19) and an oxygen requirement less than or equal to 6 L/min. We sought to predict respiratory failure within 24 hours of admission as defined by oxygen requirement of greater than 10 L/min by low-flow device, high-flow device, noninvasive or invasive ventilation, or death. Predictive models were compared with the Elixhauser Comorbidity Index, quick Sequential [Sepsis-related] Organ Failure Assessment, and the CURB-65 pneumonia severity score. RESULTS: During the study period, from March 1 to April 27, 2020, 1,792 patients were admitted with COVID-19, 620 (35%) of whom had respiratory failure in the ED. Of the remaining 1,172 admitted patients, 144 (12.3%) met the composite endpoint within the first 24 hours of hospitalization. On the independent test cohort, both a novel bedside scoring system, the quick COVID-19 Severity Index (area under receiver operating characteristic curve mean 0.81 [95% confidence interval {CI} 0.73 to 0.89]), and a machine-learning model, the COVID-19 Severity Index (mean 0.76 [95% CI 0.65 to 0.86]), outperformed the Elixhauser mortality index (mean 0.61 [95% CI 0.51 to 0.70]), CURB-65 (0.50 [95% CI 0.40 to 0.60]), and quick Sequential [Sepsis-related] Organ Failure Assessment (0.59 [95% CI 0.50 to 0.68]). A low quick COVID-19 Severity Index score was associated with a less than 5% risk of respiratory decompensation in the validation cohort. CONCLUSION: A significant proportion of admitted COVID-19 patients progress to respiratory failure within 24 hours of admission. These events are accurately predicted with bedside respiratory examination findings within a simple scoring system.

US-Pro: An Application Enabling Efficient, High-Throughput Ultrasound Video Processing.

We describe a new graphical user interface-based application, US-Pro, designed to enable customized, high-throughput ultrasound video anonymization and dynamic cropping before output to video or high-efficiency disk storage. This application is distributed in a Docker container environment, which supports facile software installation on the most commonly used operating systems, as well as local processing of data sets, precluding the external transfer of electronic protected health information. The US-Pro application will facilitate the reproducible production of large-scale ultrasound video data sets for varied applications, including machine-learning analysis, educational distribution, and quality assurance review.

Differential regulation of mesodermal gene expression by Drosophila cell type-specific Forkhead transcription factors.

A common theme in developmental biology is the repeated use of the same gene in diverse spatial and temporal domains, a process that generally involves transcriptional regulation mediated by multiple separate enhancers, each with its own arrangement of transcription factor (TF)-binding sites and associated activities. Here, by contrast, we show that the expression of the Drosophila Nidogen (Ndg) gene at different embryonic stages and in four mesodermal cell types is governed by the binding of multiple cell-specific Forkhead (Fkh) TFs - including Biniou (Bin), Checkpoint suppressor homologue (CHES-1-like) and Jumeau (Jumu) - to three functionally distinguishable Fkh-binding sites in the same enhancer. Whereas Bin activates the Ndg enhancer in the late visceral musculature, CHES-1-like cooperates with Jumu to repress this enhancer in the heart. CHES-1-like also represses the Ndg enhancer in a subset of somatic myoblasts prior to their fusion to form multinucleated myotubes. Moreover, different combinations of Fkh sites, corresponding to two different sequence specificities, mediate the particular functions of each TF. A genome-wide scan for the occurrence of both classes of Fkh domain recognition sites in association with binding sites for known cardiac TFs showed an enrichment of combinations containing the two Fkh motifs in putative enhancers found within the noncoding regions of genes having heart expression. Collectively, our results establish that different cell-specific members of a TF family regulate the activity of a single enhancer in distinct spatiotemporal domains, and demonstrate how individual binding motifs for a TF class can differentially influence gene expression.

Automating risk stratification for geriatric syndromes in the emergency department.

BACKGROUND: Geriatric emergency department (GED) guidelines endorse screening older patients for geriatric syndromes in the ED, but there have been significant barriers to widespread implementation. The majority of screening programs require engagement of a clinician, nurse, or social worker, adding to already significant workloads at a time of record-breaking ED patient volumes, staff shortages, and hospital boarding crises. Automated, electronic health record (EHR)-embedded risk stratification approaches may be an alternate solution for extending the reach of the GED mission by directing human actions to a smaller subset of higher risk patients. METHODS: We define the concept of automated risk stratification and screening using existing EHR data. We discuss progress made in three potential use cases in the ED: falls, cognitive impairment, and end-of-life and palliative care, emphasizing the importance of linking automated screening with systems of healthcare delivery. RESULTS: Research progress and operational deployment vary by use case, ranging from deployed solutions in falls screening to algorithmic validation in cognitive impairment and end-of-life care. CONCLUSIONS: Automated risk stratification offers a potential solution to one of the most pressing problems in geriatric emergency care: identifying high-risk populations of older adults most appropriate for specific GED care. Future work is needed to realize the promise of improved care with less provider burden by creating tools suitable for widespread deployment as well as best practices for their implementation and governance.

Geriatric End-of-Life Screening Tool Prediction of 6-Month Mortality in Older Patients.

Importance: Emergency department (ED) visits by older adults with life-limiting illnesses are a critical opportunity to establish patient care end-of-life preferences, but little is known about the optimal screening criteria for resource-constrained EDs. Objectives: To externally validate the Geriatric End-of-Life Screening Tool (GEST) in an independent population and compare it with commonly used serious illness diagnostic criteria. Design, Setting, and Participants: This prognostic study assessed a cohort of patients aged 65 years and older who were treated in a tertiary care ED in Boston, Massachusetts, from 2017 to 2021. Patients arriving in cardiac arrest or who died within 1 day of ED arrival were excluded. Data analysis was performed from August 1, 2023, to March 27, 2024. Exposure: GEST, a logistic regression algorithm that uses commonly available electronic health record (EHR) datapoints and was developed and validated across 9 EDs, was compared with serious illness diagnoses as documented in the EHR. Serious illnesses included stroke/transient ischemic attack, liver disease, cancer, lung disease, and age greater than 80 years, among others. Main Outcomes and Measures: The primary outcome was 6-month mortality following an ED encounter. Statistical analyses included area under the receiver operating characteristic curve, calibration analyses, Kaplan-Meier survival curves, and decision curves. Results: This external validation included 82 371 ED encounters by 40 505 unique individuals (mean [SD] age, 76.8 [8.4] years; 54.3% women, 13.8% 6-month mortality rate). GEST had an external validation area under the receiver operating characteristic curve of 0.79 (95% CI, 0.78-0.79) that was stable across years and demographic subgroups. Of included encounters, 53.4% had a serious illness, with a sensitivity of 77.4% (95% CI, 76.6%-78.2%) and specificity of 50.5% (95% CI, 50.1%-50.8%). Varying GEST cutoffs from 5% to 30% increased specificity (5%: 49.1% [95% CI, 48.7%-49.5%]; 30%: 92.2% [95% CI, 92.0%-92.4%]) at the cost of sensitivity (5%: 89.3% [95% CI, 88.8-89.9]; 30%: 36.2% [95% CI, 35.3-37.1]). In a decision curve analysis, GEST outperformed serious illness criteria across all tested thresholds. When comparing patients referred to intervention by GEST with serious illness criteria, GEST reclassified 45.1% of patients with serious illness as having low risk of mortality with an observed mortality rate 8.1% and 2.6% of patients without serious illness as having high mortality risk with an observed mortality rate of 34.3% for a total reclassification rate of 25.3%. Conclusions and Relevance: The findings of this study suggest that both serious illness criteria and GEST identified older ED patients at risk for 6-month mortality, but GEST offered more useful screening characteristics. Future trials of serious illness interventions for high mortality risk in older adults may consider transitioning from diagnosis code criteria to GEST, an automatable EHR-based algorithm.

Discharge instruction comprehension by older adults in the emergency department: A systematic review and meta-analysis.

INTRODUCTION: Older adults are at high risk of adverse health outcomes in the post-emergency department (ED) discharge period. Prior work has shown that discharged older adults have variable understanding of their discharge instructions which may contribute to these outcomes. To identify discharge comprehension gaps amenable to future interventions, we utilize meta-analysis to determine patient comprehension across five domains of discharge instructions: diagnosis, medications, self-care, routine follow-up, and return precautions. METHODS: Using Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines, two reviewers sourced evidence from databases including Medline (PubMed), EMBASE, Web of Science, CINAHL, and Google Scholar (for gray literature). Publications or preprints appearing before April 2024 were included if they focused on geriatric ED discharge instructions and reported a proportion of patients with comprehension of at least one of five predefined discharge components. Meta-analysis of eligible studies for each component was executed using random-effects modeling to describe the proportion of geriatric ED cases understanding the discharge instructions; where appropriate we calculated pooled estimates, reported as percentages with 95% confidence interval (CI). RESULTS: Of initial records returned (N = 2898), exclusions based on title or abstract assessment left 51 studies for full-text review; of these, seven constituted the study set. Acceptable heterogeneity and absence of indication of publication bias supported pooled estimates for proportions comprehending instructions on medications (41%, 95% CI 31%-50%, I2 = 43%), self-care (81%, 95% CI 76%-85%, I2 = 43%), and routine follow-up (76%, 95% CI 72%-79%, I2 = 25%). Key findings included marked heterogeneity with respect to comprehending two discharge parameters: diagnosis (I2 = 73%) and return precautions (I2 = 95%). CONCLUSIONS: Older patients discharged from the ED had greater comprehension of self-care and follow-up instructions than about their medications. These findings suggest that medication instructions may be a priority domain for future interventions.

SOFA score performs worse than age for predicting mortality in patients with COVID-19.

The use of the Sequential Organ Failure Assessment (SOFA) score, originally developed to describe disease morbidity, is commonly used to predict in-hospital mortality. During the COVID-19 pandemic, many protocols for crisis standards of care used the SOFA score to select patients to be deprioritized due to a low likelihood of survival. A prior study found that age outperformed the SOFA score for mortality prediction in patients with COVID-19, but was limited to a small cohort of intensive care unit (ICU) patients and did not address whether their findings were unique to patients with COVID-19. Moreover, it is not known how well these measures perform across races. In this retrospective study, we compare the performance of age and SOFA score in predicting in-hospital mortality across two cohorts: a cohort of 2,648 consecutive adult patients diagnosed with COVID-19 who were admitted to a large academic health system in the northeastern United States over a 4-month period in 2020 and a cohort of 75,601 patients admitted to one of 335 ICUs in the eICU database between 2014 and 2015. We used age and the maximum SOFA score as predictor variables in separate univariate logistic regression models for in-hospital mortality and calculated area under the receiver operator characteristic curves (AU-ROCs) and area under precision-recall curves (AU-PRCs) for each predictor in both cohorts. Among the COVID-19 cohort, age (AU-ROC 0.795, 95% CI 0.762, 0.828) had a significantly better discrimination than SOFA score (AU-ROC 0.679, 95% CI 0.638, 0.721) for mortality prediction. Conversely, age (AU-ROC 0.628 95% CI 0.608, 0.628) underperformed compared to SOFA score (AU-ROC 0.735, 95% CI 0.726, 0.745) in non-COVID-19 ICU patients in the eICU database. There was no difference between Black and White COVID-19 patients in performance of either age or SOFA Score. Our findings bring into question the utility of SOFA score-based resource allocation in COVID-19 crisis standards of care.