Probabilistic forecasting of hourly emergency department arrivals

An accurate forecast of Emergency Department (ED) arrivals by an hour of the day is critical to meet patients' demand. It enables planners to match ED staff to the number of arrivals, redeploy staff, and reconfigure units. In this study, we develop a model based on Generalised Additive Models a...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Health systems 2024, Vol.ahead-of-print (ahead-of-print), p.1-17
Hauptverfasser: Rostami-Tabar, Bahman, Browell, Jethro, Svetunkov, Ivan
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 17
container_issue ahead-of-print
container_start_page 1
container_title Health systems
container_volume ahead-of-print
creator Rostami-Tabar, Bahman
Browell, Jethro
Svetunkov, Ivan
description An accurate forecast of Emergency Department (ED) arrivals by an hour of the day is critical to meet patients' demand. It enables planners to match ED staff to the number of arrivals, redeploy staff, and reconfigure units. In this study, we develop a model based on Generalised Additive Models and an advanced dynamic model based on exponential smoothing to generate an hourly probabilistic forecast of ED arrivals for a prediction window of 48 hours. We compare the forecast accuracy of these models against appropriate benchmarks, including TBATS, Poisson Regression, Prophet, and simple empirical distribution. We use Root Mean Squared Error to examine the point forecast accuracy and assess the forecast distribution accuracy using Quantile Bias, PinBall Score and Pinball Skill Score. Our results indicate that the proposed models outperform their benchmarks. Our developed models can also be generalised to other services, such as hospitals, ambulances or clinical desk services.
doi_str_mv 10.1080/20476965.2023.2200526
format Article
fullrecord <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmed_primary_38800601</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3060746935</sourcerecordid><originalsourceid>FETCH-LOGICAL-c413t-e8da5ce19e9c4bc48c8382f40eb0a73920e10af018958f08f1cd0ca2966a526e3</originalsourceid><addsrcrecordid>eNp9kE1PwzAMhiMEYtPYTwD1yGXDSdo0vTFNfEmT4ADnKE2dUdQ2I-lA_fdk2scRX2xZr_3aDyHXFOYUJNwxSHNRiGzOgPE5YwAZE2dkvOvPRJHz81MtshGZhvAFMWTGmKCXZMSlBBBAx2Tx5l2py7qpQ1-bxDqPRseyWyfOJp9u65shwRb9GjszJBVutO9b7PpEe1__6CZckQsbE04PeUI-Hh_el8-z1evTy3KxmpmU8n6GstKZQVpgYdLSpNJILplNAUvQOS8YIAVtgcoikxakpaYCo1khhI7PIZ-Q2_3ejXffWwy9autgsGl0h24bFI8P5akoeBal2V5qvAvBo1UbX7faD4qC2gFUR4BqB1AdAMa5m4PFtmyxOk0dcUXB_V5Qd5FUq3-dbyrV66Fx3nrdmTre8b_HHzaTf2Y</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3060746935</pqid></control><display><type>article</type><title>Probabilistic forecasting of hourly emergency department arrivals</title><source>Alma/SFX Local Collection</source><creator>Rostami-Tabar, Bahman ; Browell, Jethro ; Svetunkov, Ivan</creator><creatorcontrib>Rostami-Tabar, Bahman ; Browell, Jethro ; Svetunkov, Ivan</creatorcontrib><description>An accurate forecast of Emergency Department (ED) arrivals by an hour of the day is critical to meet patients' demand. It enables planners to match ED staff to the number of arrivals, redeploy staff, and reconfigure units. In this study, we develop a model based on Generalised Additive Models and an advanced dynamic model based on exponential smoothing to generate an hourly probabilistic forecast of ED arrivals for a prediction window of 48 hours. We compare the forecast accuracy of these models against appropriate benchmarks, including TBATS, Poisson Regression, Prophet, and simple empirical distribution. We use Root Mean Squared Error to examine the point forecast accuracy and assess the forecast distribution accuracy using Quantile Bias, PinBall Score and Pinball Skill Score. Our results indicate that the proposed models outperform their benchmarks. Our developed models can also be generalised to other services, such as hospitals, ambulances or clinical desk services.</description><identifier>ISSN: 2047-6965</identifier><identifier>EISSN: 2047-6973</identifier><identifier>DOI: 10.1080/20476965.2023.2200526</identifier><identifier>PMID: 38800601</identifier><language>eng</language><publisher>England: Taylor &amp; Francis</publisher><subject>Emergency department ; generalised additive models ; intermittent exponential smoothing ; Poisson regression ; probabilistic forecasting</subject><ispartof>Health systems, 2024, Vol.ahead-of-print (ahead-of-print), p.1-17</ispartof><rights>2023 The Operational Research Society 2023</rights><rights>2023 The Operational Research Society.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c413t-e8da5ce19e9c4bc48c8382f40eb0a73920e10af018958f08f1cd0ca2966a526e3</citedby><cites>FETCH-LOGICAL-c413t-e8da5ce19e9c4bc48c8382f40eb0a73920e10af018958f08f1cd0ca2966a526e3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,4024,27923,27924,27925</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/38800601$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Rostami-Tabar, Bahman</creatorcontrib><creatorcontrib>Browell, Jethro</creatorcontrib><creatorcontrib>Svetunkov, Ivan</creatorcontrib><title>Probabilistic forecasting of hourly emergency department arrivals</title><title>Health systems</title><addtitle>Health Syst (Basingstoke)</addtitle><description>An accurate forecast of Emergency Department (ED) arrivals by an hour of the day is critical to meet patients' demand. It enables planners to match ED staff to the number of arrivals, redeploy staff, and reconfigure units. In this study, we develop a model based on Generalised Additive Models and an advanced dynamic model based on exponential smoothing to generate an hourly probabilistic forecast of ED arrivals for a prediction window of 48 hours. We compare the forecast accuracy of these models against appropriate benchmarks, including TBATS, Poisson Regression, Prophet, and simple empirical distribution. We use Root Mean Squared Error to examine the point forecast accuracy and assess the forecast distribution accuracy using Quantile Bias, PinBall Score and Pinball Skill Score. Our results indicate that the proposed models outperform their benchmarks. Our developed models can also be generalised to other services, such as hospitals, ambulances or clinical desk services.</description><subject>Emergency department</subject><subject>generalised additive models</subject><subject>intermittent exponential smoothing</subject><subject>Poisson regression</subject><subject>probabilistic forecasting</subject><issn>2047-6965</issn><issn>2047-6973</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNp9kE1PwzAMhiMEYtPYTwD1yGXDSdo0vTFNfEmT4ADnKE2dUdQ2I-lA_fdk2scRX2xZr_3aDyHXFOYUJNwxSHNRiGzOgPE5YwAZE2dkvOvPRJHz81MtshGZhvAFMWTGmKCXZMSlBBBAx2Tx5l2py7qpQ1-bxDqPRseyWyfOJp9u65shwRb9GjszJBVutO9b7PpEe1__6CZckQsbE04PeUI-Hh_el8-z1evTy3KxmpmU8n6GstKZQVpgYdLSpNJILplNAUvQOS8YIAVtgcoikxakpaYCo1khhI7PIZ-Q2_3ejXffWwy9autgsGl0h24bFI8P5akoeBal2V5qvAvBo1UbX7faD4qC2gFUR4BqB1AdAMa5m4PFtmyxOk0dcUXB_V5Qd5FUq3-dbyrV66Fx3nrdmTre8b_HHzaTf2Y</recordid><startdate>2024</startdate><enddate>2024</enddate><creator>Rostami-Tabar, Bahman</creator><creator>Browell, Jethro</creator><creator>Svetunkov, Ivan</creator><general>Taylor &amp; Francis</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope></search><sort><creationdate>2024</creationdate><title>Probabilistic forecasting of hourly emergency department arrivals</title><author>Rostami-Tabar, Bahman ; Browell, Jethro ; Svetunkov, Ivan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c413t-e8da5ce19e9c4bc48c8382f40eb0a73920e10af018958f08f1cd0ca2966a526e3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Emergency department</topic><topic>generalised additive models</topic><topic>intermittent exponential smoothing</topic><topic>Poisson regression</topic><topic>probabilistic forecasting</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Rostami-Tabar, Bahman</creatorcontrib><creatorcontrib>Browell, Jethro</creatorcontrib><creatorcontrib>Svetunkov, Ivan</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><jtitle>Health systems</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Rostami-Tabar, Bahman</au><au>Browell, Jethro</au><au>Svetunkov, Ivan</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Probabilistic forecasting of hourly emergency department arrivals</atitle><jtitle>Health systems</jtitle><addtitle>Health Syst (Basingstoke)</addtitle><date>2024</date><risdate>2024</risdate><volume>ahead-of-print</volume><issue>ahead-of-print</issue><spage>1</spage><epage>17</epage><pages>1-17</pages><issn>2047-6965</issn><eissn>2047-6973</eissn><abstract>An accurate forecast of Emergency Department (ED) arrivals by an hour of the day is critical to meet patients' demand. It enables planners to match ED staff to the number of arrivals, redeploy staff, and reconfigure units. In this study, we develop a model based on Generalised Additive Models and an advanced dynamic model based on exponential smoothing to generate an hourly probabilistic forecast of ED arrivals for a prediction window of 48 hours. We compare the forecast accuracy of these models against appropriate benchmarks, including TBATS, Poisson Regression, Prophet, and simple empirical distribution. We use Root Mean Squared Error to examine the point forecast accuracy and assess the forecast distribution accuracy using Quantile Bias, PinBall Score and Pinball Skill Score. Our results indicate that the proposed models outperform their benchmarks. Our developed models can also be generalised to other services, such as hospitals, ambulances or clinical desk services.</abstract><cop>England</cop><pub>Taylor &amp; Francis</pub><pmid>38800601</pmid><doi>10.1080/20476965.2023.2200526</doi><tpages>17</tpages><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 2047-6965
ispartof Health systems, 2024, Vol.ahead-of-print (ahead-of-print), p.1-17
issn 2047-6965
2047-6973
language eng
recordid cdi_pubmed_primary_38800601
source Alma/SFX Local Collection
subjects Emergency department
generalised additive models
intermittent exponential smoothing
Poisson regression
probabilistic forecasting
title Probabilistic forecasting of hourly emergency department arrivals
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T18%3A00%3A38IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Probabilistic%20forecasting%20of%20hourly%20emergency%20department%20arrivals&rft.jtitle=Health%20systems&rft.au=Rostami-Tabar,%20Bahman&rft.date=2024&rft.volume=ahead-of-print&rft.issue=ahead-of-print&rft.spage=1&rft.epage=17&rft.pages=1-17&rft.issn=2047-6965&rft.eissn=2047-6973&rft_id=info:doi/10.1080/20476965.2023.2200526&rft_dat=%3Cproquest_pubme%3E3060746935%3C/proquest_pubme%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3060746935&rft_id=info:pmid/38800601&rfr_iscdi=true