Selective classification with machine learning uncertainty estimates improves ACS prediction: A retrospective study in the prehospital setting.  

Selective classification with machine learning uncertainty estimates improves ACS prediction: A retrospective study in the prehospital setting. | 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 Selective classification with machine learning uncertainty estimates improves ACS prediction: A retrospective study in the prehospital setting. Juan Jose Garcia, Rebecca Kitzmiller, Ashok Krishnamurthy, Jessica K. Zègre-Hemsey This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4437265/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 08 Jan, 2026 Read the published version in Scientific Reports → Version 1 posted 13 You are reading this latest preprint version Abstract Accurate identification of acute coronary syndrome (ACS) in the prehospital setting is important for timely treatments that reduce damage to the compromised myocardium. Current machine learning approaches lack sufficient performance to safely rule-in or rule-out ACS. Our goal is to identify a method that bridges this gap. To do so, we retrospectively evaluate two promising approaches, an ensemble of gradient boosted decision trees (GBDT) and selective classification (SC) on consecutive patients transported by ambulance to the ED with chest pain and/or anginal equivalents. On the task of ACS classification with 23 prehospital covariates, we found the fusion of the two (GBDT+SC) improves the best reported sensitivity and specificity by 8% and 23% respectively. Accordingly, GBDT+SC is safer than current machine learning approaches to rule-in and rule-out of ACS in the prehospital setting. Health sciences/Cardiology Physical sciences/Mathematics and computing/Computer science Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 08 Jan, 2026 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 17 Jun, 2025 Reviews received at journal 13 Jun, 2025 Reviewers agreed at journal 02 Jun, 2025 Reviewers agreed at journal 27 Apr, 2025 Reviewers agreed at journal 22 Apr, 2025 Reviews received at journal 20 Mar, 2025 Reviewers agreed at journal 21 Feb, 2025 Reviewers agreed at journal 07 Oct, 2024 Reviewers invited by journal 07 Aug, 2024 Editor assigned by journal 30 Jul, 2024 Editor invited by journal 27 May, 2024 Submission checks completed at journal 23 May, 2024 First submitted to journal 17 May, 2024 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-4437265","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":309976622,"identity":"6aaecd60-3658-4822-90da-75bc0cb6c676","order_by":0,"name":"Juan Jose Garcia","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA0ElEQVRIiWNgGAWjYBACxoYDIEqCgR8hlkCkFskGYrXAgcEBYrUwNx6/+LmixkLe+PjxB8y8O+wY+NlzDAg47Eyx5JljEobbzuQYMPOeSWaQ7HlDUEuCZGODBOO2GzwMzLxtBxgMbhC2JfknUIv95hnsD8Ba7AlrOX4MZEviBgkGA4gtEoRtYbNsOCaRPAPol4Nz25J5JM48K8CrxXDG8cc3G2rqbPvbjz988LbNTo6/PXkDAS1nEM44AMQ8eJWDgDx/+wOCikbBKBgFo2CEAwBzoEiMTJnQvQAAAABJRU5ErkJggg==","orcid":"","institution":"University of North Carolina at Chapel Hill","correspondingAuthor":true,"prefix":"","firstName":"Juan","middleName":"Jose","lastName":"Garcia","suffix":""},{"id":309976623,"identity":"a0cc2a34-e8f8-479c-a73b-117033fcd1d4","order_by":1,"name":"Rebecca Kitzmiller","email":"","orcid":"","institution":"University of North Carolina at Chapel Hill","correspondingAuthor":false,"prefix":"","firstName":"Rebecca","middleName":"","lastName":"Kitzmiller","suffix":""},{"id":309976624,"identity":"f55d6b71-394f-48cd-9fdb-75ef1bd4e10a","order_by":2,"name":"Ashok Krishnamurthy","email":"","orcid":"","institution":"University of North Carolina at Chapel Hill","correspondingAuthor":false,"prefix":"","firstName":"Ashok","middleName":"","lastName":"Krishnamurthy","suffix":""},{"id":309976625,"identity":"6e3682a2-8041-4388-9ae5-3a6f9b4398f4","order_by":3,"name":"Jessica K. Zègre-Hemsey","email":"","orcid":"","institution":"University of North Carolina at Chapel Hill","correspondingAuthor":false,"prefix":"","firstName":"Jessica","middleName":"K.","lastName":"Zègre-Hemsey","suffix":""}],"badges":[],"createdAt":"2024-05-17 14:12:32","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4437265/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4437265/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-24340-w","type":"published","date":"2026-01-08T15:58:08+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":100070644,"identity":"f1e44f91-882d-4986-b207-325e17e40a5b","added_by":"auto","created_at":"2026-01-12 16:18:13","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":393697,"visible":true,"origin":"","legend":"","description":"","filename":"latexv6.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4437265/v1_covered_67993c3b-af08-4c74-a91d-87bbeb93b0ca.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Selective classification with machine learning uncertainty estimates improves ACS prediction: A retrospective study in the prehospital setting. ","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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-4437265/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4437265/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Accurate identification of acute coronary syndrome (ACS) in the prehospital setting is important for timely treatments that reduce damage to the compromised myocardium. Current machine learning approaches lack sufficient performance to safely rule-in or rule-out ACS. Our goal is to identify a method that bridges this gap. To do so, we retrospectively evaluate two promising approaches, an ensemble of gradient boosted decision trees (GBDT) and selective classification (SC) on consecutive patients transported by ambulance to the ED with chest pain and/or anginal equivalents. On the task of ACS classification with 23 prehospital covariates, we found the fusion of the two (GBDT+SC) improves the best reported sensitivity and specificity by 8% and 23% respectively. Accordingly, GBDT+SC is safer than current machine learning approaches to rule-in and rule-out of ACS in the prehospital setting.","manuscriptTitle":"Selective classification with machine learning uncertainty estimates improves ACS prediction: A retrospective study in the prehospital setting. ","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-06-05 04:38:07","doi":"10.21203/rs.3.rs-4437265/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-06-17T09:18:26+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-14T00:38:29+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"170768808584711297733668892393942720994","date":"2025-06-02T06:24:16+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"135570889695748557464786689149533155895","date":"2025-04-27T10:15:16+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"513036093177284000735888534076904541","date":"2025-04-22T07:46:42+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-03-20T20:45:13+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"336124301510439573712981085125994684039","date":"2025-02-21T09:46:42+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"194622909311642964573391201827460780888","date":"2024-10-07T14:53:46+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-08-07T14:11:45+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-07-30T12:25:21+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2024-05-27T13:34:44+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-05-23T13:23:41+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2024-05-17T14:11:21+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"c42d498b-73b5-4431-841c-02042572ff60","owner":[],"postedDate":"June 5th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":32753086,"name":"Health sciences/Cardiology"},{"id":32753087,"name":"Physical sciences/Mathematics and computing/Computer science"}],"tags":[],"updatedAt":"2026-01-12T16:15:02+00:00","versionOfRecord":{"articleIdentity":"rs-4437265","link":"https://doi.org/10.1038/s41598-025-24340-w","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2026-01-08 15:58:08","publishedOnDateReadable":"January 8th, 2026"},"versionCreatedAt":"2024-06-05 04:38:07","video":"","vorDoi":"10.1038/s41598-025-24340-w","vorDoiUrl":"https://doi.org/10.1038/s41598-025-24340-w","workflowStages":[]},"version":"v1","identity":"rs-4437265","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4437265","identity":"rs-4437265","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}