Interpretable Machine Learning for Mortality Risk Detection in National Health Data

Interpretable Machine Learning for Mortality Risk Detection in National Health Data | 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 Interpretable Machine Learning for Mortality Risk Detection in National Health Data J. CHA, E.D. CHA, E. Yoo, H. Song This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6926897/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: Accurate mortality prediction is essential for identifying high-risk individuals and guiding public health interventions. However, machine learning (ML) models trained on nationally representative data—such as NHANES, where mortality occurs in fewer than 10% of cases—often struggle with extreme class imbalance and limited interpretability, hindering practical utility. Objective: This study investigates whether loss-aware ML approaches can enhance both sensitivity and interpretability in predicting all-cause mortality, particularly in older and socioeconomically vulnerable populations where most mortality events occur. Methods: We used data from 4,188 U.S. adults in the 2011–2012 NHANES cycle, linked to the 2019 National Death Index. Four models—logistic regression, random forest, gradient boosting, and XGBoost—were trained under varying loss function strategies, without imputation or oversampling, to preserve real-world class imbalance. Performance was assessed via recall, F1-score, and PR-AUC. SHapley Additive ex- Planations (SHAP) were used for interpretability. Mortality label distributions across preprocessing strategies were statistically compared using chi-square tests. Results: Despite modest absolute metrics, the XGBoost model with class-weighted loss achieved the best recall (30.7%) and F1-score (35.4%), enabling identification of a substantial portion of deaths that baseline models missed. SHAP analysis revealed clinically consistent risk factors—age, HbA1c, systolic blood pressure, and poverty index—particularly concentrated in high-risk subgroups. Crucially, chi-square tests showed that both the raw (χ2 = 48.26, p < 0.0001) and SLOTE-imputed datasets (χ2 = 798.81, p < 0.0001) differed significantly from our analytic dataset in outcome distribution, underscoring the importance of rigorous preprocessing. These distortions, if ignored, could bias both model evaluation and real-world risk stratification. Conclusion: Even when predictive accuracy appears modest, transparent and statistically grounded models offer valuable insights for targeted outreach and equitable health policy. Our results demonstrate that interpretable, loss-aware ML can play a critical role in population-level mortality prediction. All code and data will be made publicly available upon peer-reviewed publication. Health Policy Management mortality prediction Interpretable Machine Learning SHAP Full Text Additional Declarations The authors declare no competing interests. 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-6926897","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":473354836,"identity":"9153e915-1c26-4fdc-a722-d9ec2798221d","order_by":0,"name":"J. CHA","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA70lEQVRIiWNgGAWjYBACxgYeBoYPNQw8EN4/BgYDIC1BSAvjjGNgLYwNBwyI0MIAVMzM2wDVTpQW5vazBz/bNhyWMZduPv74g4GNvDkD88HbPPgc1pOXLJ3bcJjHcs6xRKAtaYY7G9iSrfFqmcFjIJ3bd5vH4EaOIVDL4QSDAzxm0gS0GP+2bANpyf8I1PIfqIX/GyEtZtKMYC05IO8fANnChl9LT46ZZc+x/0AtaYYzzhgkG244zGZsOQePFsP2M8Y3ftSk2RvcSH7wocLATt7gePPDG2/waWnAEGLGoxwE5AnIj4JRMApGwShgYAAA2xJPn0XUAtMAAAAASUVORK5CYII=","orcid":"https://orcid.org/0000-0001-9534-8090","institution":"Gwinnett Technical College","correspondingAuthor":true,"prefix":"","firstName":"J.","middleName":"","lastName":"CHA","suffix":""},{"id":473354837,"identity":"986bc3d6-1839-4067-ae61-d0c4c9557b3c","order_by":1,"name":"E.D. CHA","email":"","orcid":"","institution":"Georgia Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"E.D.","middleName":"","lastName":"CHA","suffix":""},{"id":473354838,"identity":"c257b964-2d61-4ceb-a9ea-25f6c6d0d4da","order_by":2,"name":"E. Yoo","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"E.","middleName":"","lastName":"Yoo","suffix":""},{"id":473354839,"identity":"37257cef-d3e5-4408-9ada-fc5a69b5c7b8","order_by":3,"name":"H. Song","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"H.","middleName":"","lastName":"Song","suffix":""}],"badges":[],"createdAt":"2025-06-19 03:01:28","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-6926897/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6926897/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":85024692,"identity":"648bd879-c18e-4ff7-907e-f6f711f6cf33","added_by":"auto","created_at":"2025-06-20 05:39:26","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2337382,"visible":true,"origin":"","legend":"","description":"","filename":"ChaJManuscriptBMCMIDMupdated06142025.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6926897/v1_covered_9d34bc92-01e0-4551-96b5-5ef7b5fc437d.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eInterpretable Machine Learning for Mortality Risk\u003c/p\u003e\n\u003cp\u003eDetection in National Health Data\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Gwinnett Technical College","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":"mortality prediction, Interpretable Machine Learning, SHAP","lastPublishedDoi":"10.21203/rs.3.rs-6926897/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6926897/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eBackground: Accurate mortality prediction is essential for identifying high-risk individuals and guiding public health interventions. However, machine learning (ML) models trained on nationally representative data—such as NHANES, where mortality occurs in fewer than 10% of cases—often struggle with extreme class imbalance and limited interpretability, hindering practical utility.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eObjective: This study investigates whether loss-aware ML approaches can enhance both sensitivity and interpretability in predicting all-cause mortality, particularly in older and socioeconomically vulnerable populations where most mortality events occur.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eMethods: We used data from 4,188 U.S. adults in the 2011–2012 NHANES cycle, linked to the 2019 National Death Index. Four models—logistic regression, random forest, gradient boosting, and XGBoost—were trained under varying loss function strategies, without imputation or oversampling, to preserve real-world class imbalance. Performance was assessed via recall, F1-score, and PR-AUC. SHapley Additive ex- Planations (SHAP) were used for interpretability. Mortality label distributions across preprocessing strategies were statistically compared using chi-square tests.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eResults: Despite modest absolute metrics, the XGBoost model with class-weighted loss achieved the best recall (30.7%) and F1-score (35.4%), enabling identification of a substantial portion of deaths that baseline models missed. SHAP analysis revealed clinically consistent risk factors—age, HbA1c, systolic blood pressure, and poverty index—particularly concentrated in high-risk subgroups. Crucially, chi-square tests showed that both the raw (χ2 = 48.26, p \u0026lt; 0.0001) and SLOTE-imputed datasets (χ2 = 798.81, p \u0026lt; 0.0001) differed significantly from our analytic dataset in outcome distribution, underscoring the importance of rigorous preprocessing. These distortions, if ignored, could bias both model evaluation and real-world risk stratification.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eConclusion: Even when predictive accuracy appears modest, transparent and statistically grounded models offer valuable insights for targeted outreach and equitable health policy. Our results demonstrate that interpretable, loss-aware ML can play a critical role in population-level mortality prediction. All code and data will be made publicly available upon peer-reviewed publication.\u003c/p\u003e","manuscriptTitle":"Interpretable Machine Learning for Mortality Risk\nDetection in National Health Data","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-06-20 05:30:50","doi":"10.21203/rs.3.rs-6926897/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":"f273726b-9c2f-4ce3-972a-a059269dc75a","owner":[],"postedDate":"June 20th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":50270147,"name":"Health Policy"},{"id":50270148,"name":"Management"}],"tags":[],"updatedAt":"2025-06-20T05:30:50+00:00","versionOfRecord":[],"versionCreatedAt":"2025-06-20 05:30:50","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6926897","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6926897","identity":"rs-6926897","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}