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

被引:8
作者
Wu, Lijuan [1 ,2 ]
Chen, Xuanhui [3 ]
Khalemsky, Anna [4 ]
Li, Deyang [1 ]
Zoubeidi, Taoufik [5 ]
Lauque, Dominique [6 ,7 ]
Alsabri, Mohammed [6 ,8 ]
Boudi, Zoubir [9 ,10 ]
Kumar, Vijaya Arun [11 ]
Paxton, James [11 ]
Tsilimingras, Dionyssios [12 ]
Kurland, Lisa [13 ]
Schwartz, David [14 ]
Hachimi-Idrissi, Said [10 ,15 ]
Camargo Jr, Carlos A. [16 ]
Liu, Shan W. [16 ]
Savioli, Gabriele [17 ]
Intas, Geroge [18 ]
Soni, Kapil Dev [19 ]
Junhasavasdikul, Detajin [20 ]
Cabello, Jose Javier Trujillano [21 ]
Rathlev, Niels K. [22 ]
Tazarourte, Karim [23 ,24 ]
Slagman, Anna [25 ]
Christ, Michael [26 ]
Singer, Adam J. [27 ]
Lang, Eddy [28 ]
Ricevuti, Giovanni [29 ]
Li, Xin [30 ]
Liang, Huiying [3 ]
Grossman, Shamai A. [6 ]
Bellou, Abdelouahab [1 ,6 ,10 ,11 ,30 ]
机构
[1] Southern Med Univ, Inst Sci Emergency Med, Guangdong Prov Peoples Hosp, Dept Emergency Med,Guangdong Acad Med Sci, Guangzhou 510080, Peoples R China
[2] Southern Med Univ, Med Res Inst, Guangdong Prov Peoples Hosp, Guangdong Acad Med Sci, Guangzhou 510080, Peoples R China
[3] Southern Med Univ, Guangdong Prov Peoples Hosp, Med Big Data Ctr, Guangdong Acad Med Sci, Guangzhou 510080, Peoples R China
[4] Hadassah Acad Coll, Dept Management, IL-91010 Jerusalem, Israel
[5] UAE Univ, Dept Stat, Coll Business & Econ, Al Ain 1555, U Arab Emirates
[6] Harvard Med Sch, Dept Emergency Med, Beth Israel Deaconess Med Ctr, Teaching Hosp, Boston, MA 02115 USA
[7] Purpan Hosp, Toulouse III Univ, Dept Emergency Med, F-31300 Toulouse, France
[8] Brookdale Univ Hosp & Med Ctr, Dept Pediat, 1 Brookdale Pl, Brooklyn, NY 11212 USA
[9] Dr Sulaiman Alhabib Hosp, Dept Emergency Med, Dubai 2542, U Arab Emirates
[10] Global Network Emergency Med, Brookline, MA 02446 USA
[11] Wayne State Univ, Dept Emergency Med, Sch Med, Detroit, MI 48201 USA
[12] Wayne State Univ, Dept Family Med Publ Hlth Sci, Sch Med, Detroit, MI 48201 USA
[13] Orebro Univ, Dept Med Sci, S-70182 Orebro, Sweden
[14] Bar Ilan Univ, Grad Sch Business Adm, Informat Syst Dept, IL-529002 Ramat Gan, Israel
[15] Ghent Univ Hosp, Dept Emergency Med, B-9000 Ghent, Belgium
[16] Harvard Med Sch, Massachusetts Gen Hosp, Dept Emergency Med, Boston, MA 02114 USA
[17] IRCCS Fdn Policlin San Matteo, Emergency Dept, I-27100 Pavia, Italy
[18] Gen Hosp Nikaia Agios Panteleimon, Dept Crit Care, Athens 18454, Greece
[19] Jai Prakash Narayan Apex Trauma Ctr, Ring Rd, New Delhi 110029, India
[20] Mahidol Univ, Fac Med Ramathibodi Hosp, Dept Med, Bangkok 10400, Thailand
[21] Hosp Arnau Vilanova, Intens Care Unit, Lleida 25198, Spain
[22] Univ Massachusetts, Dept Emergency Med, Med Sch, Springfield, MA 01199 USA
[23] Univ Hosp, Hosp Civils, Dept Hlth Qual, F-69002 Lyon, France
[24] Univ Hosp, Hosp Civils, Dept Emergency Med, F-69002 Lyon, France
[25] Charite, Div Emergency & Acute Med, Campus Virchow Klinikum & Charite Campus Mitte, D-10117 Berlin, Germany
[26] Dept Emergency Med, CH-6000 Luzern, Switzerland
[27] SUNY Stony Brook, Dept Emergency Med, Renaissance Scholl Med, Stony Brook, NY 11794 USA
[28] Univ Calgary, Emergency Med Cumming Sch Med, Dept Emergency Med, Alberta Hlth Serv, Calgary, AB T2N 1N4, Canada
[29] Univ Pavia, Sch Pharm, Emergency Med, I-27100 Pavia, Italy
[30] Southern Med Univ, Guangdong Prov Peoples Hosp, Dept Emergency Med, Guangdong Acad Med Sci, Guangzhou 510080, Peoples R China
基金
中国国家自然科学基金;
关键词
emergency department; in-hospital mortality; length of stay; boarding time; machine learning; older adults; OUTCOMES; TIME;
D O I
10.3390/jcm12144750
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
The association between emergency department (ED) length of stay (EDLOS) with inhospital 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.
引用
收藏
页数:15
相关论文
共 35 条
[1]   Factors related to delayed intensive care unit admission from emergency department-A retrospective cohort study [J].
Aitavaara-Anttila, Mia ;
Liisanantti, Janne H. ;
Raatiniemi, Lasse ;
Ohtonen, Pasi ;
Ala-Kokko, Tero .
ACTA ANAESTHESIOLOGICA SCANDINAVICA, 2019, 63 (07) :939-946
[2]  
Aletreby Waleed Tharwat, 2021, Rev. bras. ter. intensiva, V33, P125, DOI [10.5935/0103-507x.20210014, 10.5935/0103-507X.20210014]
[3]   Analysis of Risk Factors for Patient Safety Events Occurring in the Emergency Department [J].
Alsabri, Mohamed ;
Boudi, Zoubir ;
Zoubeidi, Taoufik ;
Alfaki, Ibrahim Abdalla ;
Levy, Phillip ;
Oneyji, Churchill ;
Shan, Liu ;
Camargo, Carlos A., Jr. ;
Michel, Philippe ;
Tazarourte, Karim ;
Hachimi-Idrissi, Said ;
Grossman, Shamai ;
Bellou, Abdelouahab .
JOURNAL OF PATIENT SAFETY, 2022, 18 (01) :E124-E135
[4]   The effect of emergency department delays on 30-day mortality in Central Norway [J].
Asheim, Andreas ;
Nilsen, Sara Marie ;
Carlsen, Fredrik ;
Naess-Pleym, Lars Eide ;
Uleberg, Oddvar ;
Dale, Jostein ;
Bjornsen, Lars P. Bache-Wiig ;
Bjorngaard, Johan Hakon .
EUROPEAN JOURNAL OF EMERGENCY MEDICINE, 2019, 26 (06) :446-452
[5]   The 4-hour target in the emergency department, in-hospital mortality, and length of hospitalization: A single center-retrospective study [J].
Ashkenazi, Itamar ;
Gefen, Lital ;
Hochman, Ohad ;
Tannous, Elias .
AMERICAN JOURNAL OF EMERGENCY MEDICINE, 2021, 47 :95-100
[6]  
Bansal Nisha, 2019, Explainable AI for trees: From local explanations to global understanding, DOI [10.1038/s42256-019-0138-9, DOI 10.1038/S42256-019-0138-9]
[7]   Association between boarding in the emergency department and in-hospital mortality: A systematic review [J].
Boudi, Zoubir ;
Lauque, Dominique ;
Alsabri, Mohamed ;
Ostlundh, Linda ;
Oneyji, Churchill ;
Khalemsky, Anna ;
Rial, Carlos Lojo ;
Liu, Shan W. ;
Camargo, Carlos A., Jr. ;
Aburawi, Elhadi ;
Moeckel, Martin ;
Slagman, Anna ;
Christ, Michael ;
Singer, Adam ;
Tazarourte, Karim ;
Rathlev, Niels K. ;
Grossman, Shamai A. ;
Bellou, Abdelouahab .
PLOS ONE, 2020, 15 (04)
[8]   Emergency Department and Overcrowding During COVID-19 Outbreak; a Letter to Editor [J].
Bouillon-Minois, Jean-Baptiste ;
Raconnat, Julien ;
Clinchamps, Maelys ;
Schmidt, Jeannot ;
Dutheil, Frederic .
ARCHIVES OF ACADEMIC EMERGENCY MEDICINE, 2021, 9 (01) :1-3
[9]   Random forests [J].
Breiman, L .
MACHINE LEARNING, 2001, 45 (01) :5-32
[10]   Impact of delayed admission to intensive care units on mortality of critically ill patients: a cohort study [J].
Cardoso, Lucienne T. Q. ;
Grion, Cintia M. C. ;
Matsuo, Tiemi ;
Anami, Elza H. T. ;
Kauss, Ivanil A. M. ;
Seko, Ludmila ;
Bonametti, Ana M. .
CRITICAL CARE, 2011, 15 (01)