Machine learning derived serum anion gap trajectories in critically ill patients with sepsis: A retrospective study based on MIMIC-IV database

Machine learning derived serum anion gap trajectories in critically ill patients with sepsis: A retrospective study based on MIMIC-IV database | 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 Article Machine learning derived serum anion gap trajectories in critically ill patients with sepsis: A retrospective study based on MIMIC-IV database Tingting You, Xinyu Dong, Yan Zhang, Yonghui Zhang, Changlin Yin This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8466355/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 5 You are reading this latest preprint version Abstract This study aims to explore the classification of sepsis patients based on early anion gap (AG) trajectories and its association with prognosis. The study included 30,881 adult ICU patients with first-episode sepsis from the MIMIC-IV database. Latent class mixed modeling (LCMM) was employed to identify distinct AG dynamic evolution patterns. The results revealed that patients could be categorized into three clinically distinct AG trajectory classes: 1) Rapid Decline-Stabilization, 2) Stable, and 3) Progressive Deterioration. Patients in the Stable class exhibited the lowest 28-day mortality (21.7%), while those in the Progressive Deterioration class had the highest mortality (71.8%). After adjusting for confounders, multivariate Cox regression analysis indicated that, compared to the Stable class, patients in the Progressive Deterioration class had significantly increased risks of 7-day (HR=1.90, 95% CI: 1.67-2.15, p<0.001) and 28-day (HR=2.46, 95% CI: 2.22-2.73, p<0.001) mortality. The study demonstrates that AG dynamic trajectory classification helps identify distinct clinical phenotypes and prognostic risks in sepsis patients, with the Progressive Deterioration pattern being associated with markedly higher mortality, providing a valuable basis for tailored clinical interventions. Health sciences/Biomarkers Health sciences/Diseases Health sciences/Medical research Health sciences/Risk factors Sepsis Anion gap trajectory Latent class mixed model Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviewers invited by journal 07 May, 2026 Editor invited by journal 16 Jan, 2026 Editor assigned by journal 04 Jan, 2026 Submission checks completed at journal 04 Jan, 2026 First submitted to journal 28 Dec, 2025 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-8466355","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":641498653,"identity":"4b194d98-0db8-4950-957f-2abe3effb2ba","order_by":0,"name":"Tingting You","email":"","orcid":"","institution":"The First Affiliated Hospital (Southwest Hospital) of Army Medical University","correspondingAuthor":false,"prefix":"","firstName":"Tingting","middleName":"","lastName":"You","suffix":""},{"id":641498654,"identity":"db18c669-7106-42cf-9f55-817defa59c02","order_by":1,"name":"Xinyu Dong","email":"","orcid":"","institution":"The First Affiliated Hospital (Southwest Hospital) of Army Medical University","correspondingAuthor":false,"prefix":"","firstName":"Xinyu","middleName":"","lastName":"Dong","suffix":""},{"id":641498655,"identity":"70b84100-1898-4703-bf69-e7d6e96cec5f","order_by":2,"name":"Yan Zhang","email":"","orcid":"","institution":"The First Affiliated Hospital (Southwest Hospital) of Army Medical University","correspondingAuthor":false,"prefix":"","firstName":"Yan","middleName":"","lastName":"Zhang","suffix":""},{"id":641498656,"identity":"514b1327-9a70-404e-9025-0018c92e9a9a","order_by":3,"name":"Yonghui Zhang","email":"","orcid":"","institution":"The First Affiliated Hospital (Southwest Hospital) of Army Medical University","correspondingAuthor":false,"prefix":"","firstName":"Yonghui","middleName":"","lastName":"Zhang","suffix":""},{"id":641498657,"identity":"e4d563ff-437d-41a2-83c0-491035944849","order_by":4,"name":"Changlin Yin","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAzklEQVRIiWNgGAWjYFAC5oaDHwz+ycF4xGhhbHwsUXDAmIcULc0GPB8OJPYQrcXg+ME2CQmDO+n7xU6nSTBUWCc2sJ89gF/LmcQ2iQKDZ7k90rnbJBjOpCc28OQl4NdygxFkCzNEC2Pb4cQGCR4Dwlp4DJjTecBa/hGnBeh9g8MJEC0NRGiRPJMIDGSDNMOe27mbLRKOpRu38eTg18J3/PCBgx/+2Mizz87deONDjbVsP/sZ/FoUDiDzEoCYDa96IJBvIKRiFIyCUTAKRgEA+MBGfdBR8GgAAAAASUVORK5CYII=","orcid":"","institution":"The First Affiliated Hospital (Southwest Hospital) of Army Medical University","correspondingAuthor":true,"prefix":"","firstName":"Changlin","middleName":"","lastName":"Yin","suffix":""}],"badges":[],"createdAt":"2025-12-28 14:38:15","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8466355/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8466355/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":109491755,"identity":"c0c01995-e7bf-46ca-96da-c3f0cd3bf929","added_by":"auto","created_at":"2026-05-18 18:05:43","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":520294,"visible":true,"origin":"","legend":"","description":"","filename":"manuscriptscientificreport1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8466355/v1_covered_d49f430a-6ca7-4926-922d-f6a09ee573b3.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Machine learning derived serum anion gap trajectories in critically ill patients with sepsis: A retrospective study based on MIMIC-IV database","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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Sepsis, Anion gap trajectory, Latent class mixed model","lastPublishedDoi":"10.21203/rs.3.rs-8466355/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8466355/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"This study aims to explore the classification of sepsis patients based on early anion gap (AG) trajectories and its association with prognosis. The study included 30,881 adult ICU patients with first-episode sepsis from the MIMIC-IV database. Latent class mixed modeling (LCMM) was employed to identify distinct AG dynamic evolution patterns. The results revealed that patients could be categorized into three clinically distinct AG trajectory classes: 1) Rapid Decline-Stabilization, 2) Stable, and 3) Progressive Deterioration. Patients in the Stable class exhibited the lowest 28-day mortality (21.7%), while those in the Progressive Deterioration class had the highest mortality (71.8%). After adjusting for confounders, multivariate Cox regression analysis indicated that, compared to the Stable class, patients in the Progressive Deterioration class had significantly increased risks of 7-day (HR=1.90, 95% CI: 1.67-2.15, p\u003c0.001) and 28-day (HR=2.46, 95% CI: 2.22-2.73, p\u003c0.001) mortality. The study demonstrates that AG dynamic trajectory classification helps identify distinct clinical phenotypes and prognostic risks in sepsis patients, with the Progressive Deterioration pattern being associated with markedly higher mortality, providing a valuable basis for tailored clinical interventions.","manuscriptTitle":"Machine learning derived serum anion gap trajectories in critically ill patients with sepsis: A retrospective study based on MIMIC-IV database","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-18 18:05:36","doi":"10.21203/rs.3.rs-8466355/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewersInvited","content":"","date":"2026-05-07T10:43:53+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-01-16T07:46:17+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-01-05T01:11:25+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-01-05T01:10:32+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-12-28T14:23:54+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"94fc2675-6b98-4487-b8ab-bd531cfb37b6","owner":[],"postedDate":"May 18th, 2026","published":true,"recentEditorialEvents":[{"type":"reviewersInvited","content":"31","date":"2026-05-07T10:43:53+00:00","index":"","fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":68237152,"name":"Health sciences/Biomarkers"},{"id":68237153,"name":"Health sciences/Diseases"},{"id":68237154,"name":"Health sciences/Medical research"},{"id":68237155,"name":"Health sciences/Risk factors"}],"tags":[],"updatedAt":"2026-05-18T18:05:36+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-18 18:05:36","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8466355","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8466355","identity":"rs-8466355","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}