Prediction of major adverse cardiovascular events after immune checkpoint inhibitor related myocarditis with machine learning

Prediction of major adverse cardiovascular events after immune checkpoint inhibitor related myocarditis with machine learning | 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 Research Article Prediction of major adverse cardiovascular events after immune checkpoint inhibitor related myocarditis with machine learning Jing Lu, Rui Lu, Mingjun Lu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5854659/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 Objective Immune checkpoint inhibitors (ICIs) have come into widespread use in oncology in recent years and are associated with rare cardiotoxicity, including potentially fatal myocarditis. To date, no model of the occurrence of major adverse cardiovascular events (MACE) in ICI‐related myocarditis has been constructed. In this paper, To construet a machine-learning-based model through diagnosis and treatment data of patients with ICI-related myocarditis to predict MACE in ICI-related myocarditis patients. Methods 35 patients with ICI-related myocarditis from May 2019 to August 2023 at the First Affiliated Hospital of Guangzhou Medical University were selected as study subjects. The variables used for analvsis included basic information, immunotherapy-related indicators, laboratory indicators, cardiac examination-related indexes, and therapeutic regimen. Prediction model of the occurrence of MACE in ICI-related myocarditis patients was constructed with logistic regression, random forest (RF), extremegradient boosting, and light gradient boosting machine. Area under the curve (AUC) was adopted to evaluate the prediction efficacy of four prediction models. We also utilized SHapley Additive exPlanation (SHAP) values to explain the prediction model. Results MACE occurred in 17 patients, incidence of MACE was 48.6%. Comparatively, the RF model had the highest predictive performance among four models with an AUC of 0.892. The SHAP method reveals the top 6 predictors of MACE according to the importance ranking, and neutrophil to lymphocyte ratio was recognized as the most important predictor variable. Conclusions The machine learning methods were successfully established to predict MACE, and therefore, provides better treatment plans and optimal resource allocation for patients. Immune checkpoint inhibitors Myocarditis Major adverse cardiovascular events Machine learning Prediction model. 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-5854659","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":409689099,"identity":"2341990f-8cc3-48f4-bc75-788bc05b217d","order_by":0,"name":"Jing Lu","email":"","orcid":"","institution":"Guangzhou Fosun Chancheng Hospital","correspondingAuthor":false,"prefix":"","firstName":"Jing","middleName":"","lastName":"Lu","suffix":""},{"id":409689100,"identity":"62af960b-9a07-4415-9923-d4ee1c928fb1","order_by":1,"name":"Rui Lu","email":"","orcid":"","institution":"Affiliated Brain Hospital of Guangzhou Medical University","correspondingAuthor":false,"prefix":"","firstName":"Rui","middleName":"","lastName":"Lu","suffix":""},{"id":409689101,"identity":"4dbe6479-dd9c-4910-b0f4-7f5a46ce9e0e","order_by":2,"name":"Mingjun Lu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA6klEQVRIie2PMQuCQBSAnwi6nM1PDPsFwcmB2L/RxSlagmiIuAh06Qc0RD+j2ThwklobgrIgGovGGpK2FnUMuo93w4Pv43EAEskvohYPAZqgTybH2xDtVt2EABHCmWcec3jNYwQwDC0jGgaQVKjt2BDXTrQnNOlSNJboK1zNT7uSxBWN0DOjS5FklJor7OmgMdYtTYhLzUgQup5R31lhX+FEs+olxSTBAgOeVCfs+ElSLeBrXi9xATeCmJkqFJ4ic6ZVf9lm7IEDYTcOefx8jcZ2S5/m57KkQLPwa1fL9Y9yv1VLEolE8s+8Ad3FS/l73A4TAAAAAElFTkSuQmCC","orcid":"","institution":"The First Affiliate Hospital of Guang Zhou Medical University","correspondingAuthor":true,"prefix":"","firstName":"Mingjun","middleName":"","lastName":"Lu","suffix":""}],"badges":[],"createdAt":"2025-01-18 10:53:15","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5854659/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5854659/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":102537040,"identity":"f143f505-3708-495d-bdc8-3623c83b1fef","added_by":"auto","created_at":"2026-02-12 17:39:57","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":473068,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5854659/v1_covered_27b2519d-9f0e-4b8e-b213-6622b6d8373b.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Prediction of major adverse cardiovascular events after immune checkpoint inhibitor related myocarditis with machine learning","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"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":"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":"Immune checkpoint inhibitors, Myocarditis, Major adverse cardiovascular events, Machine learning, Prediction model.","lastPublishedDoi":"10.21203/rs.3.rs-5854659/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5854659/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cstrong\u003eObjective\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eImmune checkpoint inhibitors (ICIs) have come into widespread use in oncology in recent years and are associated with rare cardiotoxicity, including potentially fatal myocarditis. To date, no model of the occurrence of major adverse cardiovascular events (MACE) in ICI‐related myocarditis has been constructed. In this paper, To construet a machine-learning-based model through diagnosis and treatment data of patients with ICI-related myocarditis to predict MACE in ICI-related myocarditis patients.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eMethods\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e35 patients with ICI-related myocarditis from May 2019 to August 2023 at the First Affiliated Hospital of Guangzhou Medical University were selected as study subjects. The variables used for analvsis included basic information, immunotherapy-related indicators, laboratory indicators, cardiac examination-related indexes, and therapeutic regimen. Prediction model of the occurrence of MACE in ICI-related myocarditis patients was constructed with logistic regression, random forest (RF), extremegradient boosting, and light gradient boosting machine. Area under the curve (AUC) was adopted to evaluate the prediction efficacy of four prediction models. We also utilized SHapley Additive exPlanation (SHAP) values to explain the prediction model.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eResults\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eMACE occurred in 17 patients, incidence of MACE was 48.6%. Comparatively, the RF model had the highest predictive performance among four models with an AUC of 0.892. The SHAP method reveals the top 6 predictors of MACE according to the importance ranking, and neutrophil to lymphocyte ratio was recognized as the most important predictor variable.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConclusions\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe machine learning methods were successfully established to predict MACE, and therefore, provides better treatment plans and optimal resource allocation for patients.\u003c/p\u003e","manuscriptTitle":"Prediction of major adverse cardiovascular events after immune checkpoint inhibitor related myocarditis with machine learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-02-03 17:50:36","doi":"10.21203/rs.3.rs-5854659/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":"02e7b9b2-45ca-49cf-8407-ca4b0633fbb8","owner":[],"postedDate":"February 3rd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-02-12T17:39:13+00:00","versionOfRecord":[],"versionCreatedAt":"2025-02-03 17:50:36","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5854659","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5854659","identity":"rs-5854659","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}