Multi-Layer Machine Learning Identifies sST2 as a Predictor of Adverse Pregnancy Outcomes in Women with Heart Disease

Multi-Layer Machine Learning Identifies sST2 as a Predictor of Adverse Pregnancy Outcomes in Women with Heart Disease | 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 Multi-Layer Machine Learning Identifies sST2 as a Predictor of Adverse Pregnancy Outcomes in Women with Heart Disease Umair Arif This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9459444/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 Adverse pregnancy outcomes (APOs), including preeclampsia, preterm birth, and maternal heart failure, pose substantial risks for women with pre-existing heart disease. Soluble ST2 (sST2), a biomarker of cardiac stress, is associated with adverse cardiovascular events, yet its predictive role in high-risk pregnancies remains poorly defined. We implemented a sequential, multi-layer workflow integrating exploratory analysis, multivariable regression, and advanced machine learning. Layer 1 involved exploratory and univariate screening of 1,528 patient-level clinical records to identify potential predictors of APOs. sST2, NT-proBNP, and functional cardiac measures showed strong discriminative patterns, guiding downstream modeling. Layer 2 applied ridge logistic regression with bootstrap resampling to handle variable sparsity and perfect separation. sST2 emerged as the most stable and influential predictor (OR = 6.82), followed by heart rate and NT-proBNP, confirming biological and clinical relevance. Layer 3 incorporated synthetic data augmentation via CTGAN to address class imbalance and developed the Stable Dendritic Neural Model (SDNM), integrating clinical, demographic, and biomarker features. SDNM outperformed conventional machine learning models—including decision trees, random forests, gradient boosting, XGBoost, and LightGBM—achieving accuracy 0.993, F1-score 0.993, Cohen’s Kappa 0.986, MCC 0.988, and AUC 0.997, with excellent calibration (lowest Brier Score, ECE, and MCE) and minimal variance across repeated experiments. Interpretability analyses (SHAP and LIME) confirmed sST2, low birthweight, and preterm birth as dominant contributors to APO risk, supporting clinically actionable insights. Our findings establish sST2 as a robust early-risk biomarker for APOs and demonstrate the utility of a multi-layer, biologically informed machine learning framework for high-dimensional clinical risk prediction, bridging observational insights with precise, interpretable predictive modeling. Applied Statistics Adverse Pregnancy Outcomes (APOs) Soluble ST2 (sST2) Dendritic Neural Model (DNM) CTGAN Data Augmentation Risk Stratification Interpretability Full Text Additional Declarations The authors declare no competing interests. Supplementary Files supplymentryfile.docx Multi-Layer Machine Learning Identifies sST2 as a Predictor of Adverse Pregnancy Outcomes in Women with Heart Disease 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-9459444","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":625609743,"identity":"7d13fabc-1307-4015-9bb5-9afadb949c76","order_by":0,"name":"Umair Arif","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA90lEQVRIiWNgGAWjYJCCA2CSmf/j4x8VIAZzA5Fa2BmMjRnOgLQwEtYCAfwMZsKMbSAWAS0G1w4/PFy5xy6Pv5khjblwXm00fztQy4+Kbbi13E4zOHjmWXKxxGGGY49nbjueO+MwYwNjz5nbeLQkGBxsOMCc2HCYsd2Ad9uxXCCjgZmxDZ+W9A9ALfWJ8w8zs0nwzjmWO5+wlhyQLYcTNxxmY5PmbajJ3UBIi+TtnAKgluOJGw/zMBvOOHYgdyNQy0F8fuG7nb75Y8OB6sR5588wPvhQU5c77/zhgw9+VODWgg4Og8kDRKsHgjpSFI+CUTAKRsEIAQCdTmTg/oCo9AAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0009-0002-2973-5273","institution":"Xian Jiaotong University","correspondingAuthor":true,"prefix":"","firstName":"Umair","middleName":"","lastName":"Arif","suffix":""}],"badges":[],"createdAt":"2026-04-19 05:26:57","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-9459444/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9459444/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":107488983,"identity":"0b8407f6-b071-4c4c-9f86-2fc05adcf17b","added_by":"auto","created_at":"2026-04-22 02:46:20","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":680208,"visible":true,"origin":"","legend":"","description":"","filename":"article.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9459444/v1_covered_c3f52441-4075-4c73-a77e-e901baa1b17b.pdf"},{"id":107419815,"identity":"1f06dbd6-8326-44ad-bacc-d52364d7bee0","added_by":"auto","created_at":"2026-04-21 10:20:33","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":3032242,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eMulti-Layer Machine Learning Identifies sST2 as a Predictor of Adverse Pregnancy Outcomes in Women with Heart Disease\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"supplymentryfile.docx","url":"https://assets-eu.researchsquare.com/files/rs-9459444/v1/1f5b7a4aab51c3f103e3cd18.docx"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003e\u003cstrong\u003eMulti-Layer Machine Learning Identifies sST2 as a Predictor of Adverse Pregnancy Outcomes in Women with Heart Disease\u003c/strong\u003e\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"Adverse Pregnancy Outcomes (APOs), Soluble ST2 (sST2), Dendritic Neural Model (DNM), CTGAN Data Augmentation, Risk Stratification, Interpretability","lastPublishedDoi":"10.21203/rs.3.rs-9459444/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9459444/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAdverse pregnancy outcomes (APOs), including preeclampsia, preterm birth, and maternal heart failure, pose substantial risks for women with pre-existing heart disease. Soluble ST2 (sST2), a biomarker of cardiac stress, is associated with adverse cardiovascular events, yet its predictive role in high-risk pregnancies remains poorly defined.\u003c/p\u003e \u003cp\u003eWe implemented a sequential, multi-layer workflow integrating exploratory analysis, multivariable regression, and advanced machine learning. Layer 1 involved exploratory and univariate screening of 1,528 patient-level clinical records to identify potential predictors of APOs. sST2, NT-proBNP, and functional cardiac measures showed strong discriminative patterns, guiding downstream modeling.\u003c/p\u003e \u003cp\u003eLayer 2 applied ridge logistic regression with bootstrap resampling to handle variable sparsity and perfect separation. sST2 emerged as the most stable and influential predictor (OR\u0026thinsp;=\u0026thinsp;6.82), followed by heart rate and NT-proBNP, confirming biological and clinical relevance.\u003c/p\u003e \u003cp\u003eLayer 3 incorporated synthetic data augmentation via CTGAN to address class imbalance and developed the Stable Dendritic Neural Model (SDNM), integrating clinical, demographic, and biomarker features. SDNM outperformed conventional machine learning models\u0026mdash;including decision trees, random forests, gradient boosting, XGBoost, and LightGBM\u0026mdash;achieving accuracy 0.993, F1-score 0.993, Cohen\u0026rsquo;s Kappa 0.986, MCC 0.988, and AUC 0.997, with excellent calibration (lowest Brier Score, ECE, and MCE) and minimal variance across repeated experiments. Interpretability analyses (SHAP and LIME) confirmed sST2, low birthweight, and preterm birth as dominant contributors to APO risk, supporting clinically actionable insights.\u003c/p\u003e \u003cp\u003eOur findings establish sST2 as a robust early-risk biomarker for APOs and demonstrate the utility of a multi-layer, biologically informed machine learning framework for high-dimensional clinical risk prediction, bridging observational insights with precise, interpretable predictive modeling.\u003c/p\u003e","manuscriptTitle":"Multi-Layer Machine Learning Identifies sST2 as a Predictor of Adverse Pregnancy Outcomes in Women with Heart Disease","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-21 10:20:29","doi":"10.21203/rs.3.rs-9459444/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":"38c8e81b-576e-4f3c-9344-71d4d46e58cf","owner":[],"postedDate":"April 21st, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":66588934,"name":"Applied Statistics"}],"tags":[],"updatedAt":"2026-04-21T10:20:30+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-21 10:20:29","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9459444","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9459444","identity":"rs-9459444","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}