The Association between Emergency Department Length of Stay and In-Hospital Mortality in Older Patients Using Machine Learning: An Observational Cohort Study

The association between emergency department (ED) length of stay (EDLOS) with in-hospital mortality (IHM) in older patients remains unclear. This retrospective study aims to delineate the relationship between EDLOS and IHM in elderly patients. From the ED patients (n = 383,586) who visited an urban academic tertiary care medical center from January 2010 to December 2016, 78,478 older patients (age ≥60 years) were identified and stratified into three age subgroups: 60–74 (early elderly), 75–89 (late elderly), and ≥90 years (longevous elderly). We applied multiple machine learning approaches to identify the risk correlation trends between EDLOS and IHM, as well as boarding time (BT) and IHM. The incidence of IHM increased with age: 60–74 (2.7%), 75–89 (4.5%), and ≥90 years (6.3%). The best area under the receiver operating characteristic curve was obtained by Light Gradient Boosting Machine model for age groups 60–74, 75–89, and ≥90 years, which were 0.892 (95% CI, 0.870–0.916), 0.886 (95% CI, 0.861–0.911), and 0.838 (95% CI, 0.782–0.887), respectively. Our study showed that EDLOS and BT were statistically correlated with IHM (p < 0.001), and a significantly higher risk of IHM was found in low EDLOS and high BT. The flagged rate of quality assurance issues was higher in lower EDLOS ≤1 h (9.96%) vs. higher EDLOS 7 h <t≤ 8 h (1.84%). Special attention should be given to patients admitted after a short stay in the ED and a long BT, and new concepts of ED care processes including specific areas and teams dedicated to older patients care could be proposed to policymakers.

[1]  David G. Schwartz,et al.  Length-of-Stay in the Emergency Department and In-Hospital Mortality: A Systematic Review and Meta-Analysis , 2022, Journal of clinical medicine.

[2]  G. Ricevuti,et al.  Emergency Department Overcrowding: Understanding the Factors to Find Corresponding Solutions , 2022, Journal of personalized medicine.

[3]  A. Vishen,et al.  Increased Length of Stay of Critically Ill Patients in the Emergency Department Associated with Higher In-hospital Mortality , 2021, Indian journal of critical care medicine : peer-reviewed, official publication of Indian Society of Critical Care Medicine.

[4]  C. Youn,et al.  Prolonged Length of Stay in the Emergency Department and Mortality in Critically Ill Elderly Patients with Infections: A Retrospective Multicenter Study , 2021, Emergency medicine international.

[5]  F. Dutheil,et al.  Emergency Department and Overcrowding During COVID-19 Outbreak; a Letter to Editor , 2021, Archives of academic emergency medicine.

[6]  I. Ashkenazi,et al.  The 4-hour target in the emergency department, in-hospital mortality, and length of hospitalization: A single center-retrospective study. , 2021, The American journal of emergency medicine.

[7]  M. Knudson,et al.  Emergency Department Length of Stay and Mortality in Critically Injured Patients , 2021, Journal of intensive care medicine.

[8]  N. Mohr,et al.  Boarding of critically Ill patients in the emergency department , 2020, Journal of the American College of Emergency Physicians open.

[9]  C. Camargo,et al.  Analysis of Risk Factors for Patient Safety Events Occurring in the Emergency Department , 2020, Journal of patient safety.

[10]  A. Singer,et al.  Association between boarding in the emergency department and in-hospital mortality: A systematic review , 2020, PloS one.

[11]  Hugh Chen,et al.  From local explanations to global understanding with explainable AI for trees , 2020, Nature Machine Intelligence.

[12]  J. Bjørngaard,et al.  The effect of emergency department delays on 30-days mortality in Central Norway. , 2019, European journal of emergency medicine : official journal of the European Society for Emergency Medicine.

[13]  N. D. de Keizer,et al.  Emergency Department to ICU Time Is Associated With Hospital Mortality: A Registry Analysis of 14,788 Patients From Six University Hospitals in The Netherlands* , 2019, Critical care medicine.

[14]  T. Ala-Kokko,et al.  Factors related to delayed intensive care unit admission from emergency department—A retrospective cohort study , 2019, Acta anaesthesiologica Scandinavica.

[15]  Gabriel Erion,et al.  Explainable AI for Trees: From Local Explanations to Global Understanding , 2019, ArXiv.

[16]  K. Hillman,et al.  Impact of the four‐hour National Emergency Access Target on 30 day mortality, access block and chronic emergency department overcrowding in Australian emergency departments , 2018, Emergency medicine Australasia : EMA.

[17]  J. Considine,et al.  Longer time to transfer from the emergency department after bed request is associated with worse outcomes , 2018, Emergency medicine Australasia : EMA.

[18]  Scott M. Lundberg,et al.  Consistent Individualized Feature Attribution for Tree Ensembles , 2018, ArXiv.

[19]  Tie-Yan Liu,et al.  LightGBM: A Highly Efficient Gradient Boosting Decision Tree , 2017, NIPS.

[20]  H. Cryer,et al.  Emergency department length of stay in critical nonoperative trauma. , 2017, The Journal of surgical research.

[21]  Scott Lundberg,et al.  A Unified Approach to Interpreting Model Predictions , 2017, NIPS.

[22]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[23]  H. Yip,et al.  The impacts of prolonged emergency department length of stay on clinical outcomes of patients with ST-segment elevation myocardial infarction after reperfusion , 2016, Internal and Emergency Medicine.

[24]  C. Sarkisian,et al.  Emergency Department Crowding and Outcomes After Emergency Department Discharge. , 2015, Annals of emergency medicine.

[25]  T. Beasley,et al.  Prolonged Emergency Department Length of Stay as a Predictor of Adverse Outcomes in Patients with Intracranial Hemorrhage , 2015, Journal of critical care medicine.

[26]  Xu Sun,et al.  Fast Implementation of DeLong’s Algorithm for Comparing the Areas Under Correlated Receiver Operating Characteristic Curves , 2014, IEEE Signal Processing Letters.

[27]  D. Smit,et al.  The association between time to disposition plan in the emergency department and in‐hospital mortality of general medical patients , 2012, Internal medicine journal.

[28]  Jesse M Pines,et al.  The association between length of emergency department boarding and mortality. , 2011, Academic emergency medicine : official journal of the Society for Academic Emergency Medicine.

[29]  James H Holmes,et al.  Emergency department length of stay is an independent predictor of hospital mortality in trauma activation patients. , 2011, The Journal of trauma.

[30]  Tiemi Matsuo,et al.  Impact of delayed admission to intensive care units on mortality of critically ill patients: a cohort study , 2011, Critical care.

[31]  Elizabeth H Bradley,et al.  US emergency department performance on wait time and length of visit. , 2010, Annals of emergency medicine.

[32]  L. Breiman Random Forests , 2001, Encyclopedia of Machine Learning and Data Mining.

[33]  J SMITH,et al.  Intensive care unit. , 1962, Nursing times.

[34]  Hong-jie Yu,et al.  Access block and prolonged length of stay in the emergency department are associated with a higher patient mortality rate. , 2022, World journal of emergency medicine.

[35]  P. Brindley,et al.  Delayed intensive care unit admission from the emergency department: impact on patient outcomes. A retrospective study , 2021, Revista Brasileira de terapia intensiva.

[36]  H. P. Vinutha,et al.  Detection of Outliers Using Interquartile Range Technique from Intrusion Dataset , 2018 .

[37]  Acls Pals,et al.  DEPARTMENT OF EMERGENCY MEDICINE , 2009 .

[38]  Aditi Saxena,et al.  The Emergency Department , 2010 .