Researchers modelled mortality after emergency department presentation using 593,673 de-identified records from a tertiary hospital in the Waikato region of New Zealand between 2016 and 2024, combining generalised linear models with regularised logistic regression. Age, clinical complexity and longer stays in the department were associated with worse outcomes, while longer waiting times were associated with better ones, which the authors attribute to the sickest patients being seen first. The resulting score reached an area under the curve of 0.95 for death in the department and 0.90 at 28 days.
Why it is interesting: It shows plainly why raw waiting-time and mortality correlations in emergency care invert once triage order is in the data.
Abstract — the authors' own words, CC BY
Adverse patient outcomes in Emergency Departments (ED) are shaped by a complex interplay of clinical, demographic, and operational factors, yet existing approaches often fail to account for these dimensions in an integrated and actionable manner. This study introduces the Integrated Model for Patient Acuity, Care, and Triage Efficiency (IMPACT), a comprehensive framework developed to identify key predictors of mortality and generate individual adverse outcome risk scores across multiple clinical timeframes using a retrospective analytical approach. A retrospective analysis was conducted using 593,673 de-identified ED presentations from a tertiary hospital in the Waikato region in New Zealand, between 2016 and 2024. The modelling strategy involved a two-step approach, starting with Generalised Linear Models (GLM) for inferential analysis, followed by multiple regularised logistic regressions to enhance predictive accuracy and mitigate multicollinearity. The results indicated that advanced age, greater clinical complexity, and longer ED stays were associated with increased adverse outcomes, while longer waiting times were inversely associated with adverse outcomes, a finding consistent with triage-induced prioritisation effects whereby the most acutely unwell patients are seen first and also face the highest mortality risk, an associational pattern rather than a causal relationship. Based on the final model, an adverse outcome scoring system was derived, translating patient-level data into individual probability scores. The IMPACT model demonstrated high discriminative performance, with AUROC values of 0.9532 for ED mortality, 0.9183 for 10-days mortality, and 0.8999 for 28-days mortality. By combining robust statistical inference with a clinically interpretable scoring system, IMPACT provides a scalable and practical tool for retrospective risk stratification, service evaluation, and equitable decision-making in emergency care settings.
Cite this item
BibTeX
Free sign-up. A digest of the new papers twice a week, grouped by domain.