Evaluating the Impact of Common Clinical Confounders on Performance of Deep-Learning based Sepsis Risk Assessment

Evaluating the Impact of Common Clinical Confounders on Performance of Deep-Learning based Sepsis Risk Assessment | 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 Evaluating the Impact of Common Clinical Confounders on Performance of Deep-Learning based Sepsis Risk Assessment Shikha Chaganti, Vivek Singh, Alisdair Edward Gent, Rishikesan Kamaleswaran, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4017967/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 Machine learning based early identification of sepsis in the Emergency department remains a challenging problem, primarily due to the lack of a gold standard for sepsis diagnosis and the corresponding labels required as part of training. In this work, we present a deep learning based predictive model to enable early identification of patients at risk of developing sepsis based on data from the first 24 hours of admission. The predictive model is based on the existing routine blood test results commonly performed on patients CBC (Complete Blood Count), CMP (Comprehensive Metabolic Panel), and Lipid panel, together with vitals, age and sex. To address the challenge of label uncertainty as a part of training process, we explore two different definitions, namely, Sepsis-3 and Adult Sepsis Event and analyze the advantages and drawbacks of each in the context of patient clinical parameters and comorbidities. We particularly analyze the influence of the ground truth label quality on the performance of the overall deep learning system. We see that the model is able to identify patients in the first 24 hours with 83.7% sensitivity and 80% specificity. Our findings underscore the limitations of using individual labels for sepsis and emphasize the superiority of ensemble classifiers based on multiple heterogeneous labels, in the identification of patients with sepsis. The variable performance of the model across different sub-cohorts with specific clinical conditions underscores the need for tailored approaches in sepsis diagnosis, particularly when dealing with patients with confounding comorbidities. Physical sciences/Mathematics and computing/Computer science Health sciences/Health care/Diagnosis Full Text Additional Declarations Competing interest reported. S.C., V.S., and A.K. are employees of Siemens Healthineers, a for-profit healthcare company. Supplementary Files SupplementaryMaterial.docx 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-4017967","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":289133984,"identity":"54454ff9-f703-4a04-93b1-af376ec5d1c0","order_by":0,"name":"Shikha Chaganti","email":"data:image/png;base64,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","orcid":"","institution":"Siemens Healthineers (United States)","correspondingAuthor":true,"prefix":"","firstName":"Shikha","middleName":"","lastName":"Chaganti","suffix":""},{"id":289133985,"identity":"bfcdf250-5a4d-4c70-ae6f-fa222957a28c","order_by":1,"name":"Vivek Singh","email":"","orcid":"","institution":"Siemens Healthineers (United States)","correspondingAuthor":false,"prefix":"","firstName":"Vivek","middleName":"","lastName":"Singh","suffix":""},{"id":289133986,"identity":"2ef21c67-adf7-47ff-b3c8-4af14324e3be","order_by":2,"name":"Alisdair Edward Gent","email":"","orcid":"","institution":"Duke University","correspondingAuthor":false,"prefix":"","firstName":"Alisdair","middleName":"Edward","lastName":"Gent","suffix":""},{"id":289133987,"identity":"43f1b3a1-20f4-4a92-95e1-7a980a01b0df","order_by":3,"name":"Rishikesan Kamaleswaran","email":"","orcid":"","institution":"Duke University","correspondingAuthor":false,"prefix":"","firstName":"Rishikesan","middleName":"","lastName":"Kamaleswaran","suffix":""},{"id":289133988,"identity":"0a761f9b-64c8-4a54-9cc7-ebfb4a8720ca","order_by":4,"name":"Ali Kamen","email":"","orcid":"","institution":"Siemens Healthineers (United States)","correspondingAuthor":false,"prefix":"","firstName":"Ali","middleName":"","lastName":"Kamen","suffix":""}],"badges":[],"createdAt":"2024-03-05 16:23:18","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4017967/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4017967/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":55723519,"identity":"7ba796f7-e371-4e35-b25b-38082acbf817","added_by":"auto","created_at":"2024-05-02 09:28:02","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1762912,"visible":true,"origin":"","legend":"","description":"","filename":"ComparisonofSepsisRiskPredictionModels6.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4017967/v1_covered_d48a54a4-d6cf-4fa1-8e8a-02830291a584.pdf"},{"id":54451426,"identity":"698fe719-2a22-4980-b5a6-0f3fe221ff6a","added_by":"auto","created_at":"2024-04-10 18:07:04","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":432748,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryMaterial.docx","url":"https://assets-eu.researchsquare.com/files/rs-4017967/v1/975e12172edbd9940f1e43c0.docx"}],"financialInterests":"Competing interest reported. S.C., V.S., and A.K. are employees of Siemens Healthineers, a for-profit healthcare company.","formattedTitle":"Evaluating the Impact of Common Clinical Confounders on Performance of Deep-Learning based Sepsis Risk Assessment","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":"","lastPublishedDoi":"10.21203/rs.3.rs-4017967/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4017967/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Machine learning based early identification of sepsis in the Emergency department remains a challenging problem, primarily due to the lack of a gold standard for sepsis diagnosis and the corresponding labels required as part of training. In this work, we present a deep learning based predictive model to enable early identification of patients at risk of developing sepsis based on data from the first 24 hours of admission. The predictive model is based on the existing routine blood test results commonly performed on patients CBC (Complete Blood Count), CMP (Comprehensive Metabolic Panel), and Lipid panel, together with vitals, age and sex. To address the challenge of label uncertainty as a part of training process, we explore two different definitions, namely, Sepsis-3 and Adult Sepsis Event and analyze the advantages and drawbacks of each in the context of patient clinical parameters and comorbidities. We particularly analyze the influence of the ground truth label quality on the performance of the overall deep learning system. We see that the model is able to identify patients in the first 24 hours with 83.7% sensitivity and 80% specificity. Our findings underscore the limitations of using individual labels for sepsis and emphasize the superiority of ensemble classifiers based on multiple heterogeneous labels, in the identification of patients with sepsis. The variable performance of the model across different sub-cohorts with specific clinical conditions underscores the need for tailored approaches in sepsis diagnosis, particularly when dealing with patients with confounding comorbidities.","manuscriptTitle":"Evaluating the Impact of Common Clinical Confounders on Performance of Deep-Learning based Sepsis Risk Assessment","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-04-10 18:06:59","doi":"10.21203/rs.3.rs-4017967/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":"474492b8-5269-4be6-b245-ca48a3dee623","owner":[],"postedDate":"April 10th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":30443129,"name":"Physical sciences/Mathematics and computing/Computer science"},{"id":30443130,"name":"Health sciences/Health care/Diagnosis"}],"tags":[],"updatedAt":"2024-05-02T09:25:18+00:00","versionOfRecord":[],"versionCreatedAt":"2024-04-10 18:06:59","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4017967","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4017967","identity":"rs-4017967","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}