Race and Ethnicity and Primary Language in Emergency Department Triage

Joseph, Joshua W.; Kennedy, Maura; Landry, Alden M.; Marsh, Regan H.; Baymon, Da’Marcus E.; Im, Dana E.; Chen, Paul C.; Samuels-Kalow, Margaret E.; Nentwich, Lauren M.; Elhadad, Noémie; Sánchez, León D.

doi:10.1001/jamanetworkopen.2023.37557

Cited by 10 publications

(2 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the limited presence of biologically plausible mechanisms linking race and ethnicity to the relationship between ICD codes and the low acuity composite outcomes, and because of the potential for perpetuating race‐based health inequities, 35 we excluded race/ethnicity as a covariate in our primary models. The exclusion was driven by concerns that Black or Hispanic individuals may be systematically assigned less acute triage scores, 36 thereby increasing the likelihood of categorizing their visits as low acuity. In such cases, inclusion of the race/ethnicity variable could inadvertently raise the threshold for allocating clinical resources to these patients.…”

Section: Methodsmentioning

confidence: 99%

Identifying low acuity Emergency Department visits with a machine learning approach: The low acuity visit algorithms (LAVA)

Chen,

Kuzma,

Friedman

2024

Health Services Research

View full text Add to dashboard Cite

ObjectiveTo improve the performance of International Classification of Disease (ICD) code rule‐based algorithms for identifying low acuity Emergency Department (ED) visits by using machine learning methods and additional covariates.Data SourcesWe used secondary data on ED visits from the National Hospital Ambulatory Medical Survey (NHAMCS), from 2016 to 2020.Study DesignWe established baseline performance metrics with seven published algorithms consisting of International Classification of Disease, Tenth Revision codes used to identify low acuity ED visits. We then trained logistic regression, random forest, and gradient boosting (XGBoost) models to predict low acuity ED visits. Each model was trained on five different covariate sets of demographic and clinical data. Model performance was compared using a separate validation dataset. The primary performance metric was the probability that a visit identified by an algorithm as low acuity did not experience significant testing, treatment, or disposition (positive predictive value, PPV). Subgroup analyses assessed model performance across age, sex, and race/ethnicity.Data CollectionWe used 2016–2019 NHAMCS data as the training set and 2020 NHAMCS data for validation.Principal FindingsThe training and validation data consisted of 53,074 and 9542 observations, respectively. Among seven rule‐based algorithms, the highest‐performing had a PPV of 0.35 (95% CI [0.33, 0.36]). All model‐based algorithms outperformed existing algorithms, with the least effective—random forest using only age and sex—improving PPV by 26% (up to 0.44; 95% CI [0.40, 0.48]). Logistic regression and XGBoost trained on all variables improved PPV by 83% (to 0.64; 95% CI [0.62, 0.66]). Multivariable models also demonstrated higher PPV across all three demographic subgroups.ConclusionsMachine learning models substantially outperform existing algorithms based on ICD codes in predicting low acuity ED visits. Variations in model performance across demographic groups highlight the need for further research to ensure their applicability and fairness across diverse populations.

show abstract

Section: Methodsmentioning

confidence: 99%

Identifying low acuity Emergency Department visits with a machine learning approach: The low acuity visit algorithms (LAVA)

Chen,

Kuzma,

Friedman

2024

Health Services Research

View full text Add to dashboard Cite

show abstract

“…Those who display potential acute coronary syndrome received different care depending on their sex 13 or if they were Caucasian or African American 14,15 . In addition, disparities have been shown to impact triage score assignment 16,17,18,19 as well as rooming prioritization 20,21 , with African-American and Hispanic patients receiving less acute scores and being less likely to be prioritized for rooming.…”

Section: Introductionmentioning

confidence: 99%

Identifying Patient Subpopulations with Significant Race-Sex Differences in Emergency Department Disposition Decisions

Lin,

Argon,

Cheng

et al. 2024

Preprint

View full text Add to dashboard Cite

Background/Objectives The race-sex differences in emergency department (ED) disposition decisions have been reported widely. Our objective is to identify demographic and clinical subgroups for which this disparity is most pronounced, which will facilitate future targeted research and potential interventions. Methods We performed a retrospective analysis of 93,987 Caucasian and African-American adults assigned an Emergency Severity Index of 3 at three large EDs from January 2019 to February 2020. Using random forests, we identified the Elixhauser comorbidity score, age, and insurance status as important variables to divide data into subpopulations. Logistic regression models were then fitted to test race-sex disparities within each subpopulation while controlling for other patient characteristics and ED conditions. Results In each subpopulation, African-American women were less likely to be admitted than Caucasian men with odds ratios as low as 0.304 (95% confidence interval (CI): [0.229, 0.404]). African-American men had smaller admission odds compared to Caucasian men in subpopulations of 41+ years of age or with very low/high Elixhauser scores, odds ratios being as low as 0.652 (CI: [0.590, 0.747]). Caucasian women were less likely to be admitted than Caucasian men in subpopulations of 18-40 or 41-64 years of age, with low Elixhauser scores, or with Self-Pay or Medicaid insurance status with odds ratios as low as 0.574 (CI: [0.421, 0.784]). Conclusions African-American women faced disparities in all subgroups while disparities were lessened by younger age for African-American men, and by older age, higher Elixhauser score, and Medicare or Commercial insurance for Caucasian women. In general, patients of age 64 years or younger, with low comorbidity scores, or with Medicaid or no insurance appeared most prone to disparities in admissions.

show abstract

Exploration of Electronic Health Record Patterns of Emergency Physicians—Charting the Digital Burden

Rotenstein,

Molina

2024

JAMA Netw Open

View full text Add to dashboard Cite

Race and Ethnicity and Primary Language in Emergency Department Triage

Cited by 10 publications

References 44 publications

Identifying low acuity Emergency Department visits with a machine learning approach: The low acuity visit algorithms (LAVA)

Identifying low acuity Emergency Department visits with a machine learning approach: The low acuity visit algorithms (LAVA)

Identifying Patient Subpopulations with Significant Race-Sex Differences in Emergency Department Disposition Decisions

Exploration of Electronic Health Record Patterns of Emergency Physicians—Charting the Digital Burden

Contact Info

Product

Resources

About