EDSim: An Agentic Simulator for Emergency Department Operations

preprint OA: closed
Full text JSON View at publisher

Abstract

Abstract Emergency departments (EDs) face chronic crowding and complex patient flow challenges that traditional simulations struggle to capture. Conventional discrete-event or agent-based simulation can match high-level metrics, such as wait time distributions and throughput. However, they cannot reproduce the fine-grained behaviors, communications, and dynamic decision-making of real clinicians and patients. These micro-level interactions are often key to showing ED performance. We propose EDSim, an agentic ED flow simulator that uses large language model (LLM) agents to drive realistic, environment-aware interactions among artificial intelligence agents. EDSim offers a modularized patient journey from triage through treatment and discharge that supports customization, with virtual patients and healthcare providers who converse and make decisions in natural language based on dynamic conditions in the ED. The LLM agents are constrained by clinical rules and global EDstates, enabling both macro-level fidelity and micro-level insight. We have parameterized EDSim with aggregate historical data to reproduce daily arrival patterns and acuity mixes. Results show that EDSim’s baseline outputs align with historical wait time distributions stratified by triage acuity. Moreover, EDSim generates convincing individual conversations and behavior under potentially new workflows. This illustrates a new paradigm for healthcare operations research, combining data-driven agent-based modeling with LLM-generated behavior to provide a realistic, versatile testbed for improving ED operations. We demonstrate how analysts and hospital managers can use our tool to conduct what-if experiments in minutes, such as reallocating beds or staff to uncover bottlenecks and evaluate interventions. Our simulator can be used by both researchers and practitioners to explore ways to improve emergency care delivery.
Full text 18,195 characters · extracted from preprint-html · click to expand
EDSim: An Agentic Simulator for Emergency Department Operations | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Article EDSim: An Agentic Simulator for Emergency Department Operations Jiajun Wu, Hutton Ledingham, Zirui Wang, Braden Teitge, Alexander Burn, and 13 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8960989/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 10 You are reading this latest preprint version Abstract Emergency departments (EDs) face chronic crowding and complex patient flow challenges that traditional simulations struggle to capture. Conventional discrete-event or agent-based simulation can match high-level metrics, such as wait time distributions and throughput. However, they cannot reproduce the fine-grained behaviors, communications, and dynamic decision-making of real clinicians and patients. These micro-level interactions are often key to showing ED performance. We propose EDSim, an agentic ED flow simulator that uses large language model (LLM) agents to drive realistic, environment-aware interactions among artificial intelligence agents. EDSim offers a modularized patient journey from triage through treatment and discharge that supports customization, with virtual patients and healthcare providers who converse and make decisions in natural language based on dynamic conditions in the ED. The LLM agents are constrained by clinical rules and global EDstates, enabling both macro-level fidelity and micro-level insight. We have parameterized EDSim with aggregate historical data to reproduce daily arrival patterns and acuity mixes. Results show that EDSim’s baseline outputs align with historical wait time distributions stratified by triage acuity. Moreover, EDSim generates convincing individual conversations and behavior under potentially new workflows. This illustrates a new paradigm for healthcare operations research, combining data-driven agent-based modeling with LLM-generated behavior to provide a realistic, versatile testbed for improving ED operations. We demonstrate how analysts and hospital managers can use our tool to conduct what-if experiments in minutes, such as reallocating beds or staff to uncover bottlenecks and evaluate interventions. Our simulator can be used by both researchers and practitioners to explore ways to improve emergency care delivery. Biological sciences/Computational biology and bioinformatics Physical sciences/Engineering Health sciences/Health care Physical sciences/Mathematics and computing Emergency departments simulation large language model agentic AI Full Text Additional Declarations No competing interests reported. Supplementary Files edsimfeb24supplementary.pdf Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 01 Apr, 2026 Reviews received at journal 18 Mar, 2026 Reviews received at journal 17 Mar, 2026 Reviewers agreed at journal 05 Mar, 2026 Reviewers agreed at journal 05 Mar, 2026 Reviewers agreed at journal 28 Feb, 2026 Reviewers invited by journal 25 Feb, 2026 Editor assigned by journal 25 Feb, 2026 Submission checks completed at journal 25 Feb, 2026 First submitted to journal 24 Feb, 2026 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-8960989","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":598699620,"identity":"fb754807-ec55-4647-b5ee-89dfd19ec806","order_by":0,"name":"Jiajun Wu","email":"","orcid":"","institution":"University of Calgary","correspondingAuthor":false,"prefix":"","firstName":"Jiajun","middleName":"","lastName":"Wu","suffix":""},{"id":598699621,"identity":"46ef00d8-1777-42fa-925b-931efec58607","order_by":1,"name":"Hutton Ledingham","email":"","orcid":"","institution":"University of Calgary","correspondingAuthor":false,"prefix":"","firstName":"Hutton","middleName":"","lastName":"Ledingham","suffix":""},{"id":598699622,"identity":"5eb22004-1bb0-40f2-86d9-e332b70cded8","order_by":2,"name":"Zirui Wang","email":"","orcid":"","institution":"University of Calgary","correspondingAuthor":false,"prefix":"","firstName":"Zirui","middleName":"","lastName":"Wang","suffix":""},{"id":598699623,"identity":"9e2d8ad9-a7ce-4d53-ad99-4f07d0164e52","order_by":3,"name":"Braden Teitge","email":"","orcid":"","institution":"University of Calgary","correspondingAuthor":false,"prefix":"","firstName":"Braden","middleName":"","lastName":"Teitge","suffix":""},{"id":598699624,"identity":"02e45a4b-cb9b-4a08-bdab-850de5650bfb","order_by":4,"name":"Alexander Burn","email":"","orcid":"","institution":"University of Calgary","correspondingAuthor":false,"prefix":"","firstName":"Alexander","middleName":"","lastName":"Burn","suffix":""},{"id":598699625,"identity":"5336c7d6-9b5a-4b20-9d80-65dd136c56e4","order_by":5,"name":"Oussama Ouadihi","email":"","orcid":"","institution":"University of Calgary","correspondingAuthor":false,"prefix":"","firstName":"Oussama","middleName":"","lastName":"Ouadihi","suffix":""},{"id":598699626,"identity":"778c3ca7-4432-428b-9794-baf4e50f214d","order_by":6,"name":"Mohamad Ghattas","email":"","orcid":"","institution":"University of Calgary","correspondingAuthor":false,"prefix":"","firstName":"Mohamad","middleName":"","lastName":"Ghattas","suffix":""},{"id":598699627,"identity":"9d14fa71-9cf3-4e0d-818f-ef63f9c5fe2a","order_by":7,"name":"Darin Vicaldo","email":"","orcid":"","institution":"University of Calgary","correspondingAuthor":false,"prefix":"","firstName":"Darin","middleName":"","lastName":"Vicaldo","suffix":""},{"id":598699628,"identity":"3d10c644-ded8-4385-88ee-3594567cd37a","order_by":8,"name":"Sergiu Cociuba","email":"","orcid":"","institution":"University of Calgary","correspondingAuthor":false,"prefix":"","firstName":"Sergiu","middleName":"","lastName":"Cociuba","suffix":""},{"id":598699630,"identity":"9c52b873-0f73-4930-8edb-16bfb8c5a8d0","order_by":9,"name":"Megan Harmon","email":"","orcid":"","institution":"University of Calgary","correspondingAuthor":false,"prefix":"","firstName":"Megan","middleName":"","lastName":"Harmon","suffix":""},{"id":598699631,"identity":"b5ca64b9-3b53-4632-a588-b9a6140abb95","order_by":10,"name":"Tanvir Chowdhury","email":"","orcid":"","institution":"University of Calgary","correspondingAuthor":false,"prefix":"","firstName":"Tanvir","middleName":"","lastName":"Chowdhury","suffix":""},{"id":598699633,"identity":"edf38d71-e98a-4d64-8d45-a8da3d41b6e9","order_by":11,"name":"Zack Marshall","email":"","orcid":"","institution":"University of Calgary","correspondingAuthor":false,"prefix":"","firstName":"Zack","middleName":"","lastName":"Marshall","suffix":""},{"id":598699634,"identity":"c1198303-2076-4310-ad13-497c7710defe","order_by":12,"name":"Tyler Williamson","email":"","orcid":"","institution":"University of Calgary","correspondingAuthor":false,"prefix":"","firstName":"Tyler","middleName":"","lastName":"Williamson","suffix":""},{"id":598699635,"identity":"e5de6aab-3aa1-430d-ba16-b825097a95f8","order_by":13,"name":"Tracie Risling","email":"","orcid":"","institution":"University of Calgary","correspondingAuthor":false,"prefix":"","firstName":"Tracie","middleName":"","lastName":"Risling","suffix":""},{"id":598699636,"identity":"31a2c146-0323-466d-8df0-630f12ed1eab","order_by":14,"name":"Eddy Lang","email":"","orcid":"","institution":"University of Calgary","correspondingAuthor":false,"prefix":"","firstName":"Eddy","middleName":"","lastName":"Lang","suffix":""},{"id":598699638,"identity":"b916e30b-b345-4163-a394-86f69e2929b9","order_by":15,"name":"Jiayu Zhou","email":"","orcid":"","institution":"University of Michigan","correspondingAuthor":false,"prefix":"","firstName":"Jiayu","middleName":"","lastName":"Zhou","suffix":""},{"id":598699639,"identity":"86a5456c-c458-4ab0-8d67-90cfa2939466","order_by":16,"name":"Jessalyn Holodinsky","email":"","orcid":"","institution":"University of Calgary","correspondingAuthor":false,"prefix":"","firstName":"Jessalyn","middleName":"","lastName":"Holodinsky","suffix":""},{"id":598699640,"identity":"64b19c59-a0b4-49bc-a760-925fb2b8fcf2","order_by":17,"name":"Steve Drew","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA/UlEQVRIiWNgGAWjYPACZhA+ACQsiFDMBtfClgAkJEjSwmNAnBb5+c3HJD4wWOfzS+R8k/hRI2HXP/uMAcOPGtxaDI6xpUnOYEi3nDkjd5tkzzGJ5BnncgwYe47h0cLGY2zMw3DYwOB27jZpBjaJZIYzPAbMUPdid1gb/2fjP0At9rdznkkz/JNIlgdr+YfHM8d4GB8zgGyRzmGTZmyTsDMAaWFsw+eXNMOHPQbpBhL3nxlb9vZJJBieYSs42NuHx2HNhx8c+FFhbcDfc/jhjR/fbOzlzjBvfPDjGx6HQexCMBMbGDgMDhDSgALsGRjYH5CkYxSMglEwCoY9AAB1wUlddZfEgwAAAABJRU5ErkJggg==","orcid":"","institution":"University of Calgary","correspondingAuthor":true,"prefix":"","firstName":"Steve","middleName":"","lastName":"Drew","suffix":""}],"badges":[],"createdAt":"2026-02-24 20:53:19","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8960989/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8960989/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":103859031,"identity":"c87cb147-aea6-49ee-9b9b-b835735110b3","added_by":"auto","created_at":"2026-03-03 19:21:43","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2080480,"visible":true,"origin":"","legend":"","description":"","filename":"edsimfeb24mainv2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8960989/v1_covered_acbf103c-5ac1-40ae-b5c3-a50cfa032ab7.pdf"},{"id":103859029,"identity":"1e83e0d6-ecad-41e7-8752-d568eac86f60","added_by":"auto","created_at":"2026-03-03 19:21:28","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":230314,"visible":true,"origin":"","legend":"","description":"","filename":"edsimfeb24supplementary.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8960989/v1/df1f87e4735926016371cd6e.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"EDSim: An Agentic Simulator for Emergency Department Operations","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"npj-digital-medicine","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"npjdigitalmed","sideBox":"Learn more about [npj Digital Medicine](http://www.nature.com/npjdigitalmed/)","snPcode":"41746","submissionUrl":"https://submission.springernature.com/new-submission/41746/3","title":"npj Digital Medicine","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"NPJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Emergency departments, simulation, large language model, agentic AI","lastPublishedDoi":"10.21203/rs.3.rs-8960989/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8960989/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Emergency departments (EDs) face chronic crowding and complex patient flow challenges that traditional simulations struggle to capture. Conventional discrete-event or agent-based simulation can match high-level metrics, such as wait time distributions and throughput. However, they cannot reproduce the fine-grained behaviors, communications, and dynamic decision-making of real clinicians and patients. These micro-level interactions are often key to showing ED performance. We propose EDSim, an agentic ED flow simulator that uses large language model (LLM) agents to drive realistic, environment-aware interactions among artificial intelligence agents. EDSim offers a modularized patient journey from triage through treatment and discharge that supports customization, with virtual patients and healthcare providers who converse and make decisions in natural language based on dynamic conditions in the ED. The LLM agents are constrained by clinical rules and global EDstates, enabling both macro-level fidelity and micro-level insight. We have parameterized EDSim with aggregate historical data to reproduce daily arrival patterns and acuity mixes. Results show that EDSim’s baseline outputs align with historical wait time distributions stratified by triage acuity. Moreover, EDSim generates convincing individual conversations and behavior under potentially new workflows. This illustrates a new paradigm for healthcare operations research, combining data-driven agent-based modeling with LLM-generated behavior to provide a realistic, versatile testbed for improving ED operations. We demonstrate how analysts and hospital managers can use our tool to conduct what-if experiments in minutes, such as reallocating beds or staff to uncover bottlenecks and evaluate interventions. Our simulator can be used by both researchers and practitioners to explore ways to improve emergency care delivery.","manuscriptTitle":"EDSim: An Agentic Simulator for Emergency Department Operations","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-03 19:21:23","doi":"10.21203/rs.3.rs-8960989/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-04-01T23:46:40+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-19T02:52:13+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-17T17:50:47+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"163222051568962140384691262756253548102","date":"2026-03-06T03:12:45+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"210153582155969307966154027477451754320","date":"2026-03-05T14:24:29+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"24028683031585071961793182650001042600","date":"2026-03-01T04:21:33+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-02-26T02:35:25+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-02-26T01:01:45+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-02-25T11:05:34+00:00","index":"","fulltext":""},{"type":"submitted","content":"npj Digital Medicine","date":"2026-02-24T20:41:53+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"npj-digital-medicine","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"npjdigitalmed","sideBox":"Learn more about [npj Digital Medicine](http://www.nature.com/npjdigitalmed/)","snPcode":"41746","submissionUrl":"https://submission.springernature.com/new-submission/41746/3","title":"npj Digital Medicine","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"NPJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"6f61a318-8210-4df7-a4fa-2fdfd273858e","owner":[],"postedDate":"March 3rd, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":63712064,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":63712065,"name":"Physical sciences/Engineering"},{"id":63712066,"name":"Health sciences/Health care"},{"id":63712067,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-04-28T02:23:32+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-03 19:21:23","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8960989","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8960989","identity":"rs-8960989","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}

Text is read by the "Ask this paper" AI Q&A widget below. Extraction quality varies by source — PMC NXML preserves structure cleanly, OA-HTML may include some navigation residue, and OA-PDF can have broken hyphenation. The publisher copy (via DOI) is the canonical version.

My notes (saved in your browser only)

Ask this paper AI returns verbatim quotes from the full text · source: preprint-html

Answers must be backed by verbatim quotes from this paper's full text. Hallucinated quotes are dropped automatically; if no verbatim passage answers the question, we say so. How this works

Citation neighborhood (no data yet)

We don't have any in-corpus citations linked to this paper yet. This is a recent paper (2026) — citers typically take a year or two to land, and the OpenAlex reference graph may still be filling in.

Source provenance

europepmc
last seen: 2026-05-20T01:45:00.602351+00:00