Explainable Machine Learning Model for Predicting Early Neurological Deterioration in Patients with Acute Ischemic Stroke

Explainable Machine Learning Model for Predicting Early Neurological Deterioration in Patients with Acute Ischemic Stroke | 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 Explainable Machine Learning Model for Predicting Early Neurological Deterioration in Patients with Acute Ischemic Stroke Tingting Huang, Shoucai Zhao, Kai Wang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9044703/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 8 You are reading this latest preprint version Abstract Objective This study aims to develop and validate predictive models for early neurological deterioration in patients with acute ischemic stroke using multiple machine learning methods. Methods A total of 1,285 patients with ischemic stroke admitted to Yijishan Hospital of Anhui Province from November 2020 to November 2024 were enrolled. The patients were randomly divided into a training set (70%) and a validation set (30%). Potential predictors were selected using a combination of Lasso regression and the Boruta algorithm. Seven machine learning algorithms—logistic regression, decision tree, random forest, XGBoost, k-nearest neighbor, light gradient boosting machine, and naïve Bayes—were used to build predictive models. Model performance was evaluated using AUC, sensitivity, specificity, and other indicators. Results Lasso regression and the Boruta algorithm jointly identified nine potential predictors: history of hypertension, TACI(Total Anterior Circulation Infarct), LACI(lacunar anterior circulation infarct), SII(Systemic Inflammatory Response Index), ARC(Acute-to-chronic glycemic ratio), HDL-C, LDL-C, ALB, and NIHSS . All seven machine learning models demonstrated good performance in both the training and validation sets. Among them, the XGBoost model performed best in the validation set, with an AUC of 0.881 (95% CI: 0.834–0.928), sensitivity of 0.746, and specificity of 0.874, showing superior overall predictive ability compared to other models. Decision curve analysis (DCA) and calibration plots indicated excellent clinical benefit and discrimination ability. Finally, the SHAP summary plot was used to visualize and interpret the XGBoost model. Conclusion This study successfully developed the first machine learning-based predictive model for progressive ischemic stroke. Through model comparison and explainability analysis, the XGBoost model demonstrated superior predictive accuracy and clinical applicability, providing a reliable tool for early intervention. Full Text Additional Declarations No competing interests reported. Supplementary Files Supplymaterial.docx Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 07 May, 2026 Reviewers agreed at journal 06 May, 2026 Reviewers agreed at journal 28 Apr, 2026 Reviewers invited by journal 30 Mar, 2026 Editor assigned by journal 30 Mar, 2026 Editor invited by journal 30 Mar, 2026 Submission checks completed at journal 26 Mar, 2026 First submitted to journal 26 Mar, 2026 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-9044703","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":615092094,"identity":"7f28b4dc-c539-4a2a-95c7-90a4c2e9ad72","order_by":0,"name":"Tingting Huang","email":"data:image/png;base64,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","orcid":"","institution":"The First Affiliated Hospital of Anhui Medical University","correspondingAuthor":true,"prefix":"","firstName":"Tingting","middleName":"","lastName":"Huang","suffix":""},{"id":615092097,"identity":"d3014b3e-5182-442b-bf0a-382eb8ab1413","order_by":1,"name":"Shoucai Zhao","email":"","orcid":"","institution":"First Affiliated Hospital of Wannan Medical College","correspondingAuthor":false,"prefix":"","firstName":"Shoucai","middleName":"","lastName":"Zhao","suffix":""},{"id":615092099,"identity":"d87dade7-1046-465f-972e-cedb16de573c","order_by":2,"name":"Kai Wang","email":"","orcid":"","institution":"The First Affiliated Hospital of Anhui Medical University","correspondingAuthor":false,"prefix":"","firstName":"Kai","middleName":"","lastName":"Wang","suffix":""}],"badges":[],"createdAt":"2026-03-06 00:38:18","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9044703/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9044703/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106093834,"identity":"09b4d8a8-fdc8-4f27-93c9-17de65f034b3","added_by":"auto","created_at":"2026-04-03 11:39:27","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":613277,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9044703/v1_covered_171f951b-8b61-4d04-bfd6-b3ab7a75f0ce.pdf"},{"id":105960689,"identity":"35be1e2b-c19f-4d1f-8d2f-3ba21118accb","added_by":"auto","created_at":"2026-04-01 23:04:05","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":276079,"visible":true,"origin":"","legend":"","description":"","filename":"Supplymaterial.docx","url":"https://assets-eu.researchsquare.com/files/rs-9044703/v1/3029fc536e5bc9bedc3333f7.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"Explainable Machine Learning Model for Predicting Early Neurological Deterioration in Patients with Acute Ischemic Stroke","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"bmc-neurology","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"nurl","sideBox":"Learn more about [BMC Neurology](http://bmcneurol.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/nurl","title":"BMC Neurology","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-9044703/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9044703/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eObjective\u003c/p\u003e\n\u003cp\u003eThis study aims to develop and validate predictive models for early neurological deterioration in patients with acute ischemic stroke using multiple machine learning methods.\u003c/p\u003e\n\u003cp\u003eMethods\u003c/p\u003e\n\u003cp\u003eA total of 1,285 patients with ischemic stroke admitted to Yijishan Hospital of Anhui Province from November 2020 to November 2024 were enrolled. The patients were randomly divided into a training set (70%) and a validation set (30%). Potential predictors were selected using a combination of Lasso regression and the Boruta algorithm. Seven machine learning algorithms—logistic regression, decision tree, random forest, XGBoost, k-nearest neighbor, light gradient boosting machine, and naïve Bayes—were used to build predictive models. Model performance was evaluated using AUC, sensitivity, specificity, and other indicators.\u003c/p\u003e\n\u003cp\u003eResults\u003c/p\u003e\n\u003cp\u003eLasso regression and the Boruta algorithm jointly identified nine potential predictors: history of hypertension, TACI(Total Anterior Circulation Infarct), LACI(lacunar anterior circulation infarct), SII(Systemic Inflammatory Response Index), ARC(Acute-to-chronic glycemic ratio), HDL-C, LDL-C, ALB, and NIHSS . All seven machine learning models demonstrated good performance in both the training and validation sets. Among them, the XGBoost model performed best in the validation set, with an AUC of 0.881 (95% CI: 0.834–0.928), sensitivity of 0.746, and specificity of 0.874, showing superior overall predictive ability compared to other models. Decision curve analysis (DCA) and calibration plots indicated excellent clinical benefit and discrimination ability. Finally, the SHAP summary plot was used to visualize and interpret the XGBoost model.\u003c/p\u003e\n\u003cp\u003eConclusion\u003c/p\u003e\n\u003cp\u003eThis study successfully developed the first machine learning-based predictive model for progressive ischemic stroke. Through model comparison and explainability analysis, the XGBoost model demonstrated superior predictive accuracy and clinical applicability, providing a reliable tool for early intervention.\u003c/p\u003e","manuscriptTitle":"Explainable Machine Learning Model for Predicting Early Neurological Deterioration in Patients with Acute Ischemic Stroke","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-01 23:04:01","doi":"10.21203/rs.3.rs-9044703/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2026-05-08T02:53:17+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"220539097218479435029110746072661578437","date":"2026-05-07T02:11:42+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"112730133119297926403302104441727814891","date":"2026-04-28T16:25:45+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-03-30T14:27:24+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-03-30T14:22:48+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-03-30T10:17:49+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-03-26T08:52:53+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Neurology","date":"2026-03-26T08:46:45+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-neurology","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"nurl","sideBox":"Learn more about [BMC Neurology](http://bmcneurol.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/nurl","title":"BMC Neurology","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"8b3e3140-9a8c-477f-9d50-2b53cbd737a9","owner":[],"postedDate":"April 1st, 2026","published":true,"recentEditorialEvents":[{"type":"editorInvitedReview","content":"","date":"2026-05-08T02:53:17+00:00","index":83,"fulltext":""},{"type":"reviewerAgreed","content":"220539097218479435029110746072661578437","date":"2026-05-07T02:11:42+00:00","index":82,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-04-01T23:04:01+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-01 23:04:01","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9044703","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9044703","identity":"rs-9044703","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}