Machine Learning Models for Subarachnoid Hemorrhagic Prognosis: A Multicenter Study Considering Circadian Rhythms and Timing Factor

Machine Learning Models for Subarachnoid Hemorrhagic Prognosis: A Multicenter Study Considering Circadian Rhythms and Timing Factor | 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 Machine Learning Models for Subarachnoid Hemorrhagic Prognosis: A Multicenter Study Considering Circadian Rhythms and Timing Factor Yongbo liu, Chengbao yang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5999012/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 BACKGROUND: Traditional statistical methods(e.g.,logistic regression)are widely used for prognostic prediction in SAH patients but may fail to capture complex non-linear interactions,such as between circadian rhythms and physiological parameters.Machine learning algorithms,particularly SVM with SHAP interpretability,offer a robust framework for handling high-dimensional data and improving predictive accuracy.This study innovatively integrates circadian rhythm-based time intervals(4-hour segments)into the model,addressing a gap in existing tools. METHODS: SAH patient data were obtained from the MIMIC-IV 3.1 ICU database and Liaoyang Central Hospital NICU(2018–2024)and divided into training(85%)and validation(15%)sets.Risk factors were screened using LASSO.Six machine learning models—LASSO regression,logistic regression,SVM,KNN,Decision Tree,and Random Forest—were developed and evaluated via 10-fold cross-validation." RESULTS: A total of 651 SAH patient data were analyzed(555 for training,96 for validation).Key factors including gender,age,admission time,smoking,diabetes,GCS,HR,SBP,and RPP were used to build the models.The SVM model,chosen for its high interpretability,achieved AUCs of 0.9351 and 0.7958,and F1 scores of 0.8496 and 0.7652,outperforming other models.A risk score calculator based on the SVM model is available at https://liuyongbo0312.shinyapps.io/myshinyapp/ CONCLUSION: This study developed a predictive model for the prognosis of subarachnoid hemorrhage(SAH)patients using machine learning and identified Support Vector Machine(SVM)as the optimal model.The study found that the time of onset has a certain impact on prognosis,offering new directions for future research and clinical practice. Clinicians can use the SVM model by inputting patient-specific parameters(e.g.,RPP,GCS,admission time segment)into the provided calculator to rapidly identify high-risk patients for targeted interventions. Machine Learning SHapley Additive exPlanations (SHAP) Aneurysmal subarachnoid hemorrhage (aSAH) Support Vector Machine Circadian rhythm 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-5999012","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":414997319,"identity":"764f02b4-6082-43f6-9eda-da3af62a25e8","order_by":0,"name":"Yongbo liu","email":"","orcid":"","institution":"The Third Clinical College of Jinzhou Medical University","correspondingAuthor":false,"prefix":"","firstName":"Yongbo","middleName":"","lastName":"liu","suffix":""},{"id":414997320,"identity":"8a4b2408-837d-4e16-b50c-750c4c8a9e84","order_by":1,"name":"Chengbao yang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABFklEQVRIiWNgGAWjYLACxgYgIQHEHwxsmPmZmQ8/IFoL44yKNHbJdrY0A6K1MPOcOcxvcJ5HQQKfaoPjZw+/+LnDJk8+uvnhA942ZmnjwzwMBgw1NtE4tZzJS7PsPZNWbHjnmLGBZBubsdlh3gMPGI6l5Tbg0nIgx8yYse1w4sYZCWYShm08yWaH+RIMGBsO49Zy/g1Iy3+glvRvEoltEvWbm3kMJPBquZFj/Jix7UDifIkcM4kDZwyYDZgJaJG88caMsbctOXGDzJliw4aKBGaJw8BATsDjF77zOcYffrbZJc6f3b7x8R+D/8z8/YcPP/hQY4NTi8IBBjYJSDggCyfgUA4C8g0MzB+gjFEwCkbBKBgF2AEA1RBiSzkyc1wAAAAASUVORK5CYII=","orcid":"","institution":"Liaoyang Central Hospital","correspondingAuthor":true,"prefix":"","firstName":"Chengbao","middleName":"","lastName":"yang","suffix":""}],"badges":[],"createdAt":"2025-02-10 12:08:32","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5999012/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5999012/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":76369801,"identity":"fc45545b-ac75-4b63-9887-c86cfd958016","added_by":"auto","created_at":"2025-02-15 17:31:34","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":849944,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5999012/v1_covered_19014ed2-ddf5-4d21-b320-d245d8e5f92f.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"\u003cp\u003eMachine Learning Models for Subarachnoid Hemorrhagic Prognosis: A Multicenter Study Considering Circadian Rhythms and Timing Factor \u003c/p\u003e","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":"Machine Learning, SHapley Additive exPlanations (SHAP), Aneurysmal subarachnoid hemorrhage (aSAH), Support Vector Machine, Circadian rhythm","lastPublishedDoi":"10.21203/rs.3.rs-5999012/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5999012/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cstrong\u003eBACKGROUND:\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eTraditional statistical methods(e.g.,logistic regression)are widely used for prognostic prediction in SAH patients but may fail to capture complex non-linear interactions,such as between circadian rhythms and physiological parameters.Machine learning algorithms,particularly SVM with SHAP interpretability,offer a robust framework for handling high-dimensional data and improving predictive accuracy.This study innovatively integrates circadian rhythm-based time intervals(4-hour segments)into the model,addressing a gap in existing tools.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eMETHODS:\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eSAH patient data were obtained from the MIMIC-IV 3.1 ICU database and Liaoyang Central Hospital NICU(2018–2024)and divided into training(85%)and validation(15%)sets.Risk factors were screened using LASSO.Six machine learning models—LASSO regression,logistic regression,SVM,KNN,Decision Tree,and Random Forest—were developed and evaluated via 10-fold cross-validation.\"\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eRESULTS:\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eA total of 651 SAH patient data were analyzed(555 for training,96 for validation).Key factors including gender,age,admission time,smoking,diabetes,GCS,HR,SBP,and RPP were used to build the models.The SVM model,chosen for its high interpretability,achieved AUCs of 0.9351 and 0.7958,and F1 scores of 0.8496 and 0.7652,outperforming other models.A risk score calculator based on the SVM model is available at \u003cem\u003ehttps://liuyongbo0312.shinyapps.io/myshinyapp/\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCONCLUSION:\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis study developed a predictive model for the prognosis of subarachnoid hemorrhage(SAH)patients using machine learning and identified Support Vector Machine(SVM)as the optimal model.The study found that the time of onset has a certain impact on prognosis,offering new directions for future research and clinical practice. Clinicians can use the SVM model by inputting patient-specific parameters(e.g.,RPP,GCS,admission time segment)into the provided calculator to rapidly identify high-risk patients for targeted interventions.\u003c/p\u003e","manuscriptTitle":"Machine Learning Models for Subarachnoid Hemorrhagic Prognosis: A Multicenter Study Considering Circadian Rhythms and Timing Factor","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-02-13 12:38:03","doi":"10.21203/rs.3.rs-5999012/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":"3381920c-5c34-47b1-846d-74e1cff81fca","owner":[],"postedDate":"February 13th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-02-15T17:23:23+00:00","versionOfRecord":[],"versionCreatedAt":"2025-02-13 12:38:03","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5999012","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5999012","identity":"rs-5999012","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}