•  
  •  
 

Authors

Nere Larrea Aguirre, Research Unit, Galdakao-Usansolo University Hospital, Vizcaya, Spain. Kronikgune Institute for Health Services Research, Barakaldo, Spain.
Susana García Gutiérrez, Research Unit, Galdakao-Usansolo University Hospital, Vizcaya, Spain. Kronikgune Institute for Health Services Research, Barakaldo, Spain.
Oscar Miro, Emergency Department, Hospital Clínic, IDIBAPS, Universitat de Barcelona, Barcelona, Spain.
Javier Jacob, Emergency Department, Hospital Universitari de Bellvitge, l’Hospitalet de Llobregat, Barcelona, Spain.
Pere Llorens, Emergency Department, Hospital Doctor Balmis de Alicante, Instituto de Investigación Sanitaria y Biomédica de Alicante (ISABIAL), Universidad Miguel Hernández, Alicante, Spain
Guillermo Burillo-Putze, 6Emergency Department, Hospital Universitario de Canarias. Facultad de Ciencias de la Salud, Universidad Europea de Canarias, Tenerife, Spain.
Cesáreo Fernández, 7Emergency Department, Hospital Clínico San Carlos, IdISSC, Madrid, Spain
Aitor Alquezar-Arbé, Emergency Department, Hospital de la Santa Creu i Sant Pau, Barcelona, Spain.
Sira Aguiló, Emergency Department, Hospital Clínic, IDIBAPS, Universitat de Barcelona, Barcelona, Spain.
Francisco Javier Montero Pérez, Emergency Department, Hospital Universitario Reina Sofía, Córdoba, Spain.
José J. Noceda Bermejo, Emergency Department, Hospital Clinico Universitario de Valencia, Spain.
María Teresa Maza Vera, 12Emergency Department, Complejo Hospitalario de Vigo, Spain.
Ángel García García, Emergency Department, Hospital Universitario de Salamanca, Spain.
Patxi Ezponda, Emergency Department, Hospital de Eibar, Spain.
Juan González del Castillo, Emergency Department, Hospital Clínico San Carlos, IdISSC, Madrid, SpainFollow

Abstract

Background: The ageing population poses a significant challenge for health and social care systems. Emergency Departments (EDs) frequently experience overcrowding due to the high volume of patients and the limited availability of hospital beds. From the perspective of bed management planners, knowing the likelihood of a patient's admission at the earliest stage of care can be highly beneficial for effective resource planning. The goal of our study was to develop a prediction model to identify patients with a high probability of being admitted to the hospital.

Methods: We included all patients aged 65 or older who were treated over the course of one week in 52 Spanish Emergency Departments. The data collected included socio-demographic characteristics, baseline functional status, comorbidities, vital signs, chronic treatments, and laboratory test results. The primary outcome variable was hospital admission. We applied several mathematical strategies to develop the most accurate model for identifying high-risk patients likely to require hospitalisation.

Results: The most effective model was developed using a random forest algorithm, incorporating various variables available during patient care in the ED. The probability of admission was categorised into four risk groups: 2.19%, 15.65%, 25.09%, and 57.08%. The resulting model had a sensitivity of 0.88.

Conclusion: We developed a high-sensitivity score for hospital admission in older patients treated in the ED to enhance the management of patient flow by bed planners. This score will help prevent ED overcrowding, which compromises patient safety and disrupts the healthcare system.

Keywords: Emergency medicine, Health care system, Hospital prediction, Overcrowd


References

[1] King AII, Boyd ML, Raphael DL, Jull A. The effect of a gerontology nurse specialist for high needs older people in the community on healthcare utilisation: a controlled beforeafter study. BMC Geriatr 2018;18(1):22. https://doi.org/10.1186/s12877-018-0717-3.

[2] Puig-Campmany M, Ris-Romeu J. Frail older patients in the emergency department: main challenges. Emergencias 2022; 34(6):415e7.

[3] Aguilo Mir S. Identifying the frail patient in the emergency department: an urgent and necessary effort. Emergencias 2023 Jun;35(3):165e6. English, Spanish. https://doi.org/10.55633/s3me/E058.2023.

[4] Fernandez Alonso C, Del Arco Galan C, Torres Garate R, Madrigal Valdes JF, Romero Pareja R, Bibiano Guillen C, et al. Performance of 3 frailty scales for predicting adverse outcomes at 30 days in older patients discharged from emergency departments. Emergencias. Emergencias. 2023 Jun;35(3):196e204. English, 10.55633/s3me/E062.2023.

[5] Urbina A, Juve-Udina ME, Romero-García M, DelgadoHito P, Gonzalez-Samartino M, Adamuz J. Care complexity factors associated with revisits to an emergency department. Emergencias 2023 Aug;35(4):245e51. English, Spanish. https://doi.org/10.55633/s3me/E039.2023.

[6] Karamercan MA, Dündar DZ, Slagman A, Ergin M, Janssens KAC, Fabbri A, et al. Epidemiology of geriatric patients presenting to emergency departments in Europe: EGERS study. Eur J Emerg Med 2023;30(2):117e24. https://doi.org/10.1097/MEJ.0000000000000974.

[7] Jimenez-Fabrega X, Jacob J. Pre- and postpandemic emergency services: similarities and differences. Emergencias 2023 Apr;35(2):142e5. English, Spanish. https://doi.org/10.55633/s3me/E083.2023.

[8] Savioli G, Ceresa IF, Gri N, Bavestrello Piccini G, Longhitano Y, Zanza C, et al. Emergency department overcrowding: understanding the factors to find corresponding solutions. J Pers Med 2022 Feb 14;12(2):279. https://doi.org/10.3390/jpm12020279.

[9] Estella A. Learning from the pandemic: the key to the fight against emergency service overcrowding. Emergencias 2022; 34(2):141e3.

[10] Maninchedda M, Proia AS, Bianco L, Aromatario M, Orsi GB, Napoli C. Main features and control strategies to reduce overcrowding in emergency departments: a systematic review of the literature. Risk Manag Healthc Policy 2023 Feb 21;16:255e66. https://doi.org/10.2147/RMHP.S399045.

[11] King Z, Farrington J, Utley M, Kung E, Elkhodair S, Harris S, et al. Machine learning for real-time aggregated prediction of hospital admission for emergency patients. NPJ Digit Med 2022 Jul 26;5(1):104. https://doi.org/10.1038/s41746-022-00649-y.

[12] Stylianou N, Fackrell R, Vasilakis C. Are medical outliers associated with worse patient outcomes? A retrospective study within a regional NHS hospital using routine data. BMJ Open 2017 May 9;7(5):e015676. https://doi.org/10.1136/bmjopen-2016-015676.

[13] McKenna P, Heslin SM, Viccellio P, Mallon WK, Hernandez C, Morley EJ. Emergency department and hospital crowding: causes, consequences, and cures. Clin Exp Emerg Med 2019 Sep;6(3):189e95. https://doi.org/10.15441/ceem.18.022.

[14] PatryC,PerozzielloA,PardineilleC,AubertC,deMalglaiveP, Choquet C, et al. Older medical outliers on surgical wards: impact on 6-month outcomes. Emerg Med J 2022;39(3):181e5. https://doi.org/10.1136/emermed-2020-210457.

[15] Briganti G, Le Moine O. Artificial intelligence in medicine: today and tomorrow. Front Med (Lausanne) 2020 Feb 5;7:27. https://doi.org/10.3389/fmed.2020.00027.

[16] Miro O, Gonzalez Del Castillo J. Colaboracion entre servicios de urgencias espa~noles para fomentar la investigacion: a proposito de la creacion de la red SIESTA (Spanish Investigators on Emergengy Situations TeAm y de la coordinacion del macroproyecto UMC-19) Unusual Manifestations of C. Emergencias 2020;32(4):269e77. Ago.

[17] Miro O, Gonzalez Del Castillo J. SIESTA- the Spanish Investigators in Emergency Situations TeAm- during the COVID-19 pandemic: a summary of results of the network's first challenge. Emergencias 2022 Jun;34(3):225e7.

[18] Hanley JA, McNeil BJ. The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology 1982 Apr;143(1):29e36. https://doi.org/10.1148/radiology.143.1.7063747.

[19] Barrio I, Arostegui I, Rodríguez-Alvarez MX, Quintana JM. A new approach to categorising continuous variables in prediction models: proposal and validation. Stat Methods Med Res 2017;26(6):2586e602. https://doi.org/10.1177/0962280215601873.

[20] Vickers AJ, Elkin EB. Decision curve analysis: a novel methodfor evaluating prediction models. Med Decis Making 2006;26(6):565e74. https://doi.org/10.1177/0272989X06295361.

[21] Rodríguez-Perez R, Bajorath J. Interpretation of machine learning models using shapley values: application to compound potency and multi-target activity predictions. J Comput Aided Mol Des 2020;34(10):1013e26. https://doi.org/10.1007/s10822-020-00314-0.

[22] García-Perez D. The importance of holistic evaluation of older patients who fall. Emergencias 2022 Dec;34(6):413e4.

[23] Feral-Pierssens AL, Toury G, Sehimi F, Peschanski N, Laribi S, Carpentier A, et al. Emergency department outcome of elderly patients assisted by professional home services, the EPIGER study. BMC Geriatr 2020 Sep 21;20(1): 355. https://doi.org/10.1186/s12877-020-01742-1.

[24] Gomes JCP, Dias RD, de Barros JV, Velasco IT, Jacob Filho W. The growing impact of older patients in the emergency department: a 5-year retrospective analysis in Brazil. BMC Emerg Med 2020;20(1):47. https://doi.org/10.1186/s12873-020-00344-9.

[25] Lyon D, Lancaster GA, Taylor S, Dowrick C, Chellaswamy H. Predicting the likelihood of emergency admission to hospital of older people: development and validation of the Emergency Admission Risk Likelihood Index (EARLI). Fam Pract 2007;24(2):158e67. cmm004. https://doi.org/10.1093/fampra/

[26] Marcusson J, Nord M, Dong HJ, Lyth J. Clinically useful prediction of hospital admissions in an older population. BMC Geriatr 2020;20(1):95. https://doi.org/10.1186/s12877020-1475-6.

[27] Harper PR. A framework for operational modelling of hospital resources. Health Care Manag Sci. 2002;5(3):165e73. https://doi.org/10.1023/a:1019767900627.

[28] Larburu N, Azkue L, Kerexeta J. Predicting hospital ward admission from the emergency department: a systematic review. J Pers Med 2023;13(5):849. https://doi.org/10.3390/jpm13050849.

[29] Pianykh OS, Guitron S, Parke D, Zhang C. Improving healthcare operations management with machine learning. Nat Mach Intell 2020;2:266e73. https://doi.org/10.1038/s42256-020-0176-3.

[30] Raita Y, Goto T, Faridi MK, Brown DFM, Camargo CA Jr, Hasegawa K. Emergency department triage prediction of clinical outcomes using machine learning models. Crit Care 2019;23(1):64. https://doi.org/10.1186/s13054-019-2351-7.

[31] El-Bouri R, Eyre DW, Watkinson P, Zhu T, Clifton DA. Hospital admission location prediction via deep interpretable networks for the year-round improvement of emergency patient care. IEEE J Biomed Health Inform 2021 Jan; 25(1):289e300. https://doi.org/10.1109/JBHI.2020.2990309.

[32] Aguirre NL, Gutierrez SG, Miro O, Aguilo S, Jacob J, Alquezar-Arbe A, et al. Elderly patients in the Emergency Department: which patients should be selected for a different approach? Ann Geriatr Med Res 2023 Nov 15. https://doi.org/10.4235/agmr.23.0121.

[33] Hong WS, Haimovich AD, Taylor RA. Predicting hospital admission at emergency department triage using machine learning. PLoS One 2018 Jul 20;13(7):e0201016. https://doi.org/10.1371/journal.pone.0201016.

[34] Utley M, Gallivan S, Treasure T, Valencia O. Analytical methods for calculating the capacity required to operate an effective booked admissions policy for elective inpatient services. Health Care Manag Sci. 2003 May;6(2):97e104. https://doi.org/10.1023/a:1023333002675.

[35] Kohler K, Ercole A. Can network science reveal structure in a complex healthcare system? A network analysis using data from emergency surgical services. BMJ Open 2020 Feb 9; 10(2):e034265. https://doi.org/10.1136/bmjopen-2019-034265.

Share

COinS