KUTS: A Foundational Triage System for Improving Accuracy in Mid-Level Emergency Classifications

KUTS: A Foundational Triage System for Improving Accuracy in Mid-Level Emergency Classifications | 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 KUTS: A Foundational Triage System for Improving Accuracy in Mid-Level Emergency Classifications Tao Yu, Tuo Liu, Yang Gu, Hongyi Chen, Yan Zhang, Leqi Zheng, and 16 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4580303/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 31 Jul, 2025 Read the published version in Communications Medicine → Version 1 posted You are reading this latest preprint version Abstract Triage is of great importance in the procedure of the emergency diagnosis, which needs artificial intelligence to assist due to the scarcity of medical resources. However, AI models for aiding triage have difficulty in identifying levels that are difficult or ambiguous for human clinicians to distinguish. Here, to address this challenge and improve the performance of triage models, we propose KUTS, a foundational classification model for emergency triage, which leverages a knowledge prompt-tuning encoder and an uncertainty-based classifier. KUTS takes tabular data and chief complaints as input, and then generates the recommended triage level for human clinicians. On the most difficult level for human to distinguish (Level 3), our KUTS significantly outperformed the previous shallow single-modal methods, deep single-modal methods and deep multi-modal methods by an average of 14.85%, 28.38% and 11.14%, respectively. Besides, on all the triage levels, our KUTS also outperformed the previous shallow single-modal methods, deep single-modal methods and deep multi-modal methods by an average of 9.02%, 9.45% and 4.18%, respectively. KUTS provides a foundational framework and paradigm for the study of emergency triage, and can be extended to scenarios that require pre-hospital emergency treatment such as disasters and accidents. Health sciences/Health care/Diagnosis/Physical examination Health sciences/Risk factors Triage Pretrained Language Model Knowledge Prompt Learning Uncertainty Learning Full Text Additional Declarations There is NO Competing Interest. Cite Share Download PDF Status: Published Journal Publication published 31 Jul, 2025 Read the published version in Communications Medicine → Version 1 posted 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-4580303","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":314654371,"identity":"4962673b-b469-4693-82a7-bf8964726589","order_by":0,"name":"Tao Yu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA1UlEQVRIiWNgGAWjYHACxgcMDBIycF4DYR3MzAZALTwkaWGTAJIkaDG4kX+s6kaNBQ8D/xnjzzwMNrIbDjA/e4BfSzLb7ZxjQIdJ5JhJ8zCkGW84wGZuQFgLG0gLjxkzD8PhxA0HeMBOxaulOOefBMxh/4nTwpzbBgqxHAOgww4Q1iJ55rGxdG6fBFBZWpnkHINk45mH2czwauE7nvjwc863Ojl+/sObP7ypsJPtO978DK8WhQNQBhsDBzCcQEHFjE89EMg3wJnsDwioHQWjYBSMgpEKALQdPuQtFPk6AAAAAElFTkSuQmCC","orcid":"","institution":"Department of Urology, Department of Radiology, Department of Emergency Medicine, Department of respiratory medicine, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University","correspondingAuthor":true,"prefix":"","firstName":"Tao","middleName":"","lastName":"Yu","suffix":""},{"id":314654372,"identity":"7066f8ae-cb8e-4324-9826-a237c30da5d1","order_by":1,"name":"Tuo Liu","email":"","orcid":"","institution":"Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Tuo","middleName":"","lastName":"Liu","suffix":""},{"id":314654373,"identity":"5a393062-29f4-4dca-9210-ec69a99c6428","order_by":2,"name":"Yang Gu","email":"","orcid":"","institution":"Sun Yat-sen Memorial Hospital, Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Yang","middleName":"","lastName":"Gu","suffix":""},{"id":314654374,"identity":"b58e2340-43e3-4373-b9f6-3dc5a2bbb9e3","order_by":3,"name":"Hongyi Chen","email":"","orcid":"","institution":"Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Hongyi","middleName":"","lastName":"Chen","suffix":""},{"id":314654375,"identity":"b57b14c6-587e-48e9-abcf-b326f404adeb","order_by":4,"name":"Yan Zhang","email":"","orcid":"","institution":"Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Yan","middleName":"","lastName":"Zhang","suffix":""},{"id":314654376,"identity":"acbb9afa-c64b-4278-8eb1-2a94253b9101","order_by":5,"name":"Leqi Zheng","email":"","orcid":"","institution":"Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Leqi","middleName":"","lastName":"Zheng","suffix":""},{"id":314654377,"identity":"956e7bae-b5ff-41f3-b649-08779aa1fbde","order_by":6,"name":"Xuanqi Huang","email":"","orcid":"","institution":"Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Xuanqi","middleName":"","lastName":"Huang","suffix":""},{"id":314654378,"identity":"1c853cbc-5e56-4cd9-8c4a-aff777b984ad","order_by":7,"name":"Yanjun Xu","email":"","orcid":"","institution":"Sun Yat-sen Memorial Hospital, Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Yanjun","middleName":"","lastName":"Xu","suffix":""},{"id":314654379,"identity":"05f6b70f-9c46-4b07-a2e0-f91f688df685","order_by":8,"name":"Cai Wen","email":"","orcid":"","institution":"Sun Yat-sen Memorial Hospital, Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Cai","middleName":"","lastName":"Wen","suffix":""},{"id":314654380,"identity":"86ec1024-85c7-4459-b1f9-cfd588646869","order_by":9,"name":"Mansheng Chen","email":"","orcid":"","institution":"Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Mansheng","middleName":"","lastName":"Chen","suffix":""},{"id":314654381,"identity":"de74bfe4-b633-4a08-8740-890bdff0cc6a","order_by":10,"name":"Jiaqi Lin","email":"","orcid":"","institution":"Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Jiaqi","middleName":"","lastName":"Lin","suffix":""},{"id":314654382,"identity":"76c142b6-5162-403b-9775-4aef7fc9fb71","order_by":11,"name":"Dongguo Huang","email":"","orcid":"","institution":"Sun Yat-sen Memorial Hospital, Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Dongguo","middleName":"","lastName":"Huang","suffix":""},{"id":314654383,"identity":"de294c6d-d915-471c-ac53-5f4d4838b3a4","order_by":12,"name":"Feixia Chen","email":"","orcid":"","institution":"Sun Yat-sen Memorial Hospital, Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Feixia","middleName":"","lastName":"Chen","suffix":""},{"id":314654384,"identity":"6d5d8725-9e85-4d48-8416-3a4c4b25b218","order_by":13,"name":"Yulan Zhong","email":"","orcid":"","institution":"Sun Yat-sen Memorial Hospital, Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Yulan","middleName":"","lastName":"Zhong","suffix":""},{"id":314654385,"identity":"41012d9a-1cc2-4b57-b80f-2b1d2e783a10","order_by":14,"name":"Hui Chen","email":"","orcid":"","institution":"Sun Yat-sen Memorial Hospital, Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Hui","middleName":"","lastName":"Chen","suffix":""},{"id":314654386,"identity":"94b8dde3-6281-4518-97c8-ad9c762d6352","order_by":15,"name":"Yanfeng Guo","email":"","orcid":"","institution":"Guangdong Provincal Hospital of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Yanfeng","middleName":"","lastName":"Guo","suffix":""},{"id":314654387,"identity":"54fdeed1-eb74-4d35-89ac-f6b312082cda","order_by":16,"name":"Mei Lu","email":"","orcid":"","institution":"Guangdong Provincal Hospital of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Mei","middleName":"","lastName":"Lu","suffix":""},{"id":314654388,"identity":"a01f71a9-2aa7-4d80-9b2c-d195ba6c09a4","order_by":17,"name":"Guangwei Zhang","email":"","orcid":"","institution":"Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Guangwei","middleName":"","lastName":"Zhang","suffix":""},{"id":314654389,"identity":"21ce2415-1341-497d-be9a-1916169a5a7b","order_by":18,"name":"Hao Wu","email":"","orcid":"","institution":"Sun Yat-sen Memorial Hospital, Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Hao","middleName":"","lastName":"Wu","suffix":""},{"id":314654390,"identity":"7703a217-6a79-463c-8d4c-b21dfd3702f5","order_by":19,"name":"Changdong Wang","email":"","orcid":"","institution":"Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Changdong","middleName":"","lastName":"Wang","suffix":""},{"id":314654391,"identity":"00d03a5c-45f1-4b90-b944-71817be12689","order_by":20,"name":"Xiaotu Xi","email":"","orcid":"","institution":"Guangdong Provincial Hospital of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Xiaotu","middleName":"","lastName":"Xi","suffix":""},{"id":314654392,"identity":"e47a8c9f-d16f-41db-a7d0-26cedf1e8d7b","order_by":21,"name":"Li Li","email":"","orcid":"","institution":"Sun Yat-sen Memorial Hospital, Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Li","middleName":"","lastName":"Li","suffix":""}],"badges":[],"createdAt":"2024-06-14 07:35:33","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4580303/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4580303/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s43856-025-01052-w","type":"published","date":"2025-07-31T04:00:00+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":88076319,"identity":"ea4c1961-6c2f-4d79-9d67-842b21de55cb","added_by":"auto","created_at":"2025-08-01 07:09:00","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1448258,"visible":true,"origin":"","legend":"","description":"","filename":"ArticleFile.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4580303/v1_covered_c17650d8-8f5c-4804-91eb-c9932c6656f4.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"KUTS: A Foundational Triage System for Improving Accuracy in Mid-Level Emergency Classifications","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"nature-portfolio","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"","title":"Nature Portfolio","twitterHandle":"","acdcEnabled":false,"dfaEnabled":false,"editorialSystem":"ejp","reportingPortfolio":"","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Triage, Pretrained Language Model, Knowledge Prompt Learning, Uncertainty Learning","lastPublishedDoi":"10.21203/rs.3.rs-4580303/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4580303/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Triage is of great importance in the procedure of the emergency diagnosis, which needs artificial intelligence to assist due to the scarcity of medical resources. However, AI models for aiding triage have difficulty in identifying levels that are difficult or ambiguous for human clinicians to distinguish. Here, to address this challenge and improve the performance of triage models, we propose KUTS, a foundational classification model for emergency triage, which leverages a knowledge prompt-tuning encoder and an uncertainty-based classifier. KUTS takes tabular data and chief complaints as input, and then generates the recommended triage level for human clinicians. On the most difficult level for human to distinguish (Level 3), our KUTS significantly outperformed the previous shallow single-modal methods, deep single-modal methods and deep multi-modal methods by an average of 14.85%, 28.38% and 11.14%, respectively. Besides, on all the triage levels, our KUTS also outperformed the previous shallow single-modal methods, deep single-modal methods and deep multi-modal methods by an average of 9.02%, 9.45% and 4.18%, respectively. KUTS provides a foundational framework and paradigm for the study of emergency triage, and can be extended to scenarios that require pre-hospital emergency treatment such as disasters and accidents.","manuscriptTitle":"KUTS: A Foundational Triage System for Improving Accuracy in Mid-Level Emergency Classifications","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-07-25 03:55:50","doi":"10.21203/rs.3.rs-4580303/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"communications-medicine","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"commsmed","sideBox":"Learn more about [Communications Medicine](http://www.nature.com/commsmed)","snPcode":"43856","submissionUrl":"https://mts-commsmed.nature.com/cgi-bin/main.plex","title":"Communications Medicine","twitterHandle":"@commsmedicine","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Communications Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"16ec86e1-e274-4e38-baa8-f89335a30062","owner":[],"postedDate":"July 25th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":33282670,"name":"Health sciences/Health care/Diagnosis/Physical examination"},{"id":33282671,"name":"Health sciences/Risk factors"}],"tags":[],"updatedAt":"2025-08-01T07:08:40+00:00","versionOfRecord":{"articleIdentity":"rs-4580303","link":"https://doi.org/10.1038/s43856-025-01052-w","journal":{"identity":"communications-medicine","isVorOnly":false,"title":"Communications Medicine"},"publishedOn":"2025-07-31 04:00:00","publishedOnDateReadable":"July 31st, 2025"},"versionCreatedAt":"2024-07-25 03:55:50","video":"","vorDoi":"10.1038/s43856-025-01052-w","vorDoiUrl":"https://doi.org/10.1038/s43856-025-01052-w","workflowStages":[]},"version":"v1","identity":"rs-4580303","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4580303","identity":"rs-4580303","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}