Deciphering the influence of demographic factors on the treatment of pediatric patients in the emergency department
🤖 AI Summary
This study investigates the systemic influence of demographic factors on clinical decision-making in pediatric emergency departments. Method: Leveraging 339,000 emergency department visits from a U.S. pediatric medical center (2019–2024), we employed propensity score matching, multivariable regression, and interpretable machine learning (e.g., SHAP) to isolate and quantify independent effects of race, insurance type, and socioeconomic status on triage acuity scoring and hospital admission decisions. Contribution/Results: Non-Hispanic Black children exhibited significantly lower odds of admission (OR = 0.77) and urgent triage (OR = 0.70) compared with non-Hispanic White children; these disparities intensified among patients with normal vital signs and those covered by public insurance. Model weight analysis uncovered latent structural bias embedded in algorithmic predictions. To our knowledge, this is the first real-world study to concurrently validate both clinician-driven decision bias and algorithmic bias in pediatric emergency care—providing empirical evidence to inform equity-oriented clinical interventions and fairness-aware AI design.
Application Category
📝 Abstract
Persistent demographic disparities have been identified in the treatment of patients seeking care in the emergency department (ED). These may be driven in part by subconscious biases, which providers themselves may struggle to identify. To better understand the operation of these biases, we performed a retrospective cross-sectional analysis using electronic health records describing 339,400 visits to the ED of a single US pediatric medical center between 2019-2024. Odds ratios were calculated using propensity-score matching. Analyses were adjusted for confounding variables, including chief complaint, insurance type, socio-economic deprivation, and patient comorbidities. We also trained a machine learning [ML] model on this dataset to identify predictors of admission. We found significant demographic disparities in admission (Non-Hispanic Black [NHB] relative to Non-Hispanic White [NHW]: OR 0.77, 95% CI 0.73-0.81; Hispanic relative to NHW: OR 0.80, 95% CI 0.76-0.83). We also identified disparities in individual decisions taken during the ED stay. For example, NHB patients were significantly less likely than NHW patients to be assigned an `emergent' triage acuity score of (OR 0.70, 95% CI 0.67-0.72), but emergent NHB patients were also significantly less likely to be admitted than NHW patients with the same triage acuity (OR 0.86, 95% CI 0.80-0.93). Demographic disparities were particularly acute wherever patients had normal vital signs, public insurance, moderate socio-economic deprivation, or a home address distant from the hospital. An ML model assigned higher importance to triage score for NHB than NHW patients when predicting admission, reflecting these disparities in assignment. We conclude that many visit characteristics, clinical and otherwise, may influence the operation of subconscious biases and affect ML-driven decision support tools.
Problem
Research questions and friction points this paper is trying to address.
Investigating demographic disparities in pediatric emergency department treatment
Analyzing subconscious bias influence on clinical decisions and admissions
Examining how demographic factors affect triage scoring and ML predictions
Innovation
Methods, ideas, or system contributions that make the work stand out.
Retrospective cross-sectional analysis of pediatric emergency visits
Propensity-score matching to calculate adjusted odds ratios
Machine learning model trained to identify admission predictors
🔎 Similar Papers
No similar papers found.
