Increasing the accuracy of ST-segment elevation detection in an ECG through automated visual rules

Increasing the accuracy of ST-segment elevation detection in an ECG through automated visual rules | 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 Increasing the accuracy of ST-segment elevation detection in an ECG through automated visual rules Lukas Hughes-Noehrer, Gabriel Strain, Adina Rahim, James Sinnott, and 4 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9537195/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Accurate identification of ST‑segment elevation on the electrocardiogram (ECG) is essential for diagnosing acute myocardial infarction, yet interpretation remains challenging due to noise, signal variability, differences in user expertise and limitations of existing automated methods. This study investigates whether novel, clinically motivated visualisation techniques -- including a novel heart‑rate–corrected ST‑analysis window (STc) -- can make ST‑segment elevation easier to detect. We conducted a mixed‑methods investigation comprising two components: (Part I) qualitative validation interviews with practising clinicians from emergency medicine, anaesthesia, critical care and cardiology, followed by (Part II) a preregistered online experiment with members of the public unfamiliar with ECG interpretation. In the clinician interviews (n = 6), participants described the visualisations as transparent, clinically coherent, helpful for training, and complementary to automated prompts. Clinicians particularly valued visual cues that provided a consistent and physiologically grounded ST‑analysis window; for this reason, we included STc, a heart‑rate--corrected interval that avoids reliance on arbitrary fixed millisecond cut-offs and mitigates heart‑rate--driven distortions in defining the end of the ST‑segment. In the online experiment (n = 303), participants classified single‑lead, single‑beat ECG images that either incorporated visualisations or displayed the visually unannotated signal. Accuracy and response times, analysed using generalised linear mixed models, showed that participants made significantly more accurate and faster decisions when visualisations were present. Performance differed across visualisation types: shading‑based designs were most effective when ST‑segment elevation was present, while J‑point markers were particularly helpful when elevation was absent. Overall, the findings demonstrate that intuitive, explainable visual cues can support accurate detection of ST‑segment elevation and have potential for future clinical decision‑support tools, training resources, and patient‑facing applications. Health sciences/Cardiology Biological sciences/Computational biology and bioinformatics Health sciences/Health care Health sciences/Medical research electrocardiogram ST elevation visualisation crowdsourced user validation Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted 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-9537195","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":630047043,"identity":"50b607df-838a-418a-8bd4-c5277116d4a6","order_by":0,"name":"Lukas Hughes-Noehrer","email":"data:image/png;base64,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","orcid":"","institution":"University of Manchester","correspondingAuthor":true,"prefix":"","firstName":"Lukas","middleName":"","lastName":"Hughes-Noehrer","suffix":""},{"id":630047044,"identity":"49c31a2a-b503-4e24-a8a8-fe72a015f917","order_by":1,"name":"Gabriel Strain","email":"","orcid":"","institution":"University of Manchester","correspondingAuthor":false,"prefix":"","firstName":"Gabriel","middleName":"","lastName":"Strain","suffix":""},{"id":630047045,"identity":"fce3b011-7a7b-4e68-91f7-56767fd58ddb","order_by":2,"name":"Adina Rahim","email":"","orcid":"","institution":"University of Manchester","correspondingAuthor":false,"prefix":"","firstName":"Adina","middleName":"","lastName":"Rahim","suffix":""},{"id":630047046,"identity":"19709488-f64a-4b87-8a61-08e87645e80e","order_by":3,"name":"James Sinnott","email":"","orcid":"","institution":"University of Manchester","correspondingAuthor":false,"prefix":"","firstName":"James","middleName":"","lastName":"Sinnott","suffix":""},{"id":630047047,"identity":"c0073b60-eef1-4883-8eb1-b2c4874d1e98","order_by":4,"name":"Jonathan Carlton","email":"","orcid":"","institution":"University of Manchester","correspondingAuthor":false,"prefix":"","firstName":"Jonathan","middleName":"","lastName":"Carlton","suffix":""},{"id":630047048,"identity":"5fede4d9-6639-4aef-a03c-7ec68b09a997","order_by":5,"name":"Crystal T. Wu","email":"","orcid":"","institution":"University of Manchester","correspondingAuthor":false,"prefix":"","firstName":"Crystal","middleName":"T.","lastName":"Wu","suffix":""},{"id":630047049,"identity":"5fc5ed3e-be97-42f0-a0a7-166845b4bbc2","order_by":6,"name":"Richard Body","email":"","orcid":"","institution":"University of Manchester","correspondingAuthor":false,"prefix":"","firstName":"Richard","middleName":"","lastName":"Body","suffix":""},{"id":630047050,"identity":"e73f7f31-c666-44d9-acb3-7b1ffc30ec5a","order_by":7,"name":"Caroline Jay","email":"","orcid":"","institution":"University of Manchester","correspondingAuthor":false,"prefix":"","firstName":"Caroline","middleName":"","lastName":"Jay","suffix":""}],"badges":[],"createdAt":"2026-04-27 06:26:08","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9537195/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9537195/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108007669,"identity":"e6ff379d-cb10-4335-a4b2-ff6e931143f4","added_by":"auto","created_at":"2026-04-28 13:01:18","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":879813,"visible":true,"origin":"","legend":"","description":"","filename":"ecgxnpjdigital.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9537195/v1_covered_bb259634-6250-4302-9faf-6a6e25069300.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Increasing the accuracy of ST-segment elevation detection in an ECG through automated visual rules","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"electrocardiogram, ST elevation, visualisation, crowdsourced, user validation","lastPublishedDoi":"10.21203/rs.3.rs-9537195/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9537195/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAccurate identification of ST‑segment elevation on the electrocardiogram (ECG) is essential for diagnosing acute myocardial infarction, yet interpretation remains challenging due to noise, signal variability, differences in user expertise and limitations of existing automated methods. This study investigates whether novel, clinically motivated visualisation techniques -- including a novel heart‑rate–corrected ST‑analysis window (STc) -- can make ST‑segment elevation easier to detect. We conducted a mixed‑methods investigation comprising two components:\u0026nbsp;(Part I) qualitative validation interviews with practising clinicians from emergency medicine, anaesthesia, critical care and cardiology, followed by (Part II) a preregistered online experiment with members of the public unfamiliar with ECG interpretation.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eIn the clinician interviews (n = 6), participants described the visualisations as transparent, clinically coherent, helpful for training, and complementary to automated prompts. Clinicians particularly valued visual cues that provided a consistent and physiologically grounded ST‑analysis window; for this reason, we included STc, a heart‑rate--corrected interval that avoids reliance on arbitrary fixed millisecond cut-offs and mitigates heart‑rate--driven distortions in defining the end of the ST‑segment.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eIn the online experiment (n = 303), participants classified single‑lead, single‑beat ECG images that either incorporated visualisations or displayed the visually unannotated signal. Accuracy and response times, analysed using generalised linear mixed models, showed that participants made significantly more accurate and faster decisions when visualisations were present. Performance differed across visualisation types: shading‑based designs were most effective when ST‑segment elevation was present, while J‑point markers were particularly helpful when elevation was absent.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eOverall, the findings demonstrate that intuitive, explainable visual cues can support accurate detection of ST‑segment elevation and have potential for future clinical decision‑support tools, training resources, and patient‑facing applications.\u003c/p\u003e","manuscriptTitle":"Increasing the accuracy of ST-segment elevation detection in an ECG through automated visual rules","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-28 11:58:27","doi":"10.21203/rs.3.rs-9537195/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"31b3d09d-640f-4523-9a36-f62939499861","owner":[],"postedDate":"April 28th, 2026","published":true,"recentEditorialEvents":[{"type":"decision","content":"Rejected","date":"2026-05-11T21:18:54+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-05-01T15:13:53+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-04-30T14:44:50+00:00","index":"","fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":67054009,"name":"Health sciences/Cardiology"},{"id":67054010,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":67054011,"name":"Health sciences/Health care"},{"id":67054012,"name":"Health sciences/Medical research"}],"tags":[],"updatedAt":"2026-05-11T21:25:15+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-28 11:58:27","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9537195","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9537195","identity":"rs-9537195","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}