Dynamic modeling of hospitalized COVID-19 patients reveals disease state dependent risk factors

Dynamic modeling of hospitalized COVID-19 patients reveals disease state dependent risk factors | 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 Dynamic modeling of hospitalized COVID-19 patients reveals disease state dependent risk factors Braden Soper, Jose Cadena, Sam Nguyen, Ryan Chan, Paul Kiszka, and 8 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-923677/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 31 Dec, 2021 Read the published version in Journal of the American Medical Informatics Association → Version 1 posted You are reading this latest preprint version Abstract The global pandemic of the SARS-CoV-2 coronavirus has significantly strained hospital resources worldwide. Improved understanding of the COVID-19 disease trajectory for patients requiring hospitalization would allow for the development of more targeted preventative, diagnostic and therapeutic strategies. A covariate-dependent, continuous-time hidden Markov model with four states (moderate-illness, severe-illness, discharged, and deceased) was used to model the dynamic progression of COVID-19 during the course of hospitalization. All model parameters were estimated using the electronic health records of 1,362 patients from ProMedica Health System admitted between March 20, 2020 and December 29, 2020 with a positive nasopharyngeal PCR test for SARS-CoV-2. Demographic characteristics, co-morbidities, vital signs and laboratory test results were retrospectively evaluated to predict clinical progression and outcomes. Several patient-level covariates were associated with differential impacts on the risk of progression. Specifically, while being male, being black or having a medical co-morbidity were all associated with an increased risk of progressing from the moderate to severe disease state, these factors resulted in a decreased risk of transitioning from the severe to the deceased disease state. Body mass index (BMI) alone was not found to be associated with an increased risk of disease progression, while higher age was associated with an increased risk in progressing from moderate to severe and from severe to deceased states. Regardless of the differential risk profiles, all covariates considered other than BMI and asthma were associated with an overall increased risk of transitioning to the deceased state. Recent studies have not included analyses of the temporal progression of COVID-19, making the current study a unique modeling-based approach to understand the dynamics of COVID-19 in hospitalized patients. Such dynamic risk stratification models have the potential not only to improve clinical outcomes in COVID-19, but also a myriad of other acute and chronic diseases that, to date, have largely been assessed only by static modeling techniques. Health sciences/Medical research/Biomarkers/Predictive markers Health sciences/Diseases/Infectious diseases/Viral infection Biological sciences/Computational biology and bioinformatics/Machine learning Biological sciences/Computational biology and bioinformatics/Statistical methods Biological sciences/Systems biology/Time series Full Text Additional Declarations There is NO Competing Interest. Cite Share Download PDF Status: Published Journal Publication published 31 Dec, 2021 Read the published version in Journal of the American Medical Informatics Association → 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-923677","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":54871483,"identity":"98b8c2e7-218d-4088-a338-4be116b676a3","order_by":0,"name":"Braden Soper","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAs0lEQVRIiWNgGAWjYNCCHzYyfAzMDSToYOxJ42FjYCRFCwPbYRK0yLf3HnxcwXOeh026sYHxS8VhwloMzpxLNjxjcZuHTeZgA7PMGWK0SOSYSTbwALVIJDYwS7alEeGwGTnmPxvYzpGgheFGjhljA9sBsBbGj202RDgM6BfJxp5ksJbDDGeI0AIKsY8NP+zk+CWSDz78USFBhMMYeBDMwzy4leHQwviDOC2jYBSMglEwwgAAMVU0Numca9cAAAAASUVORK5CYII=","orcid":"https://orcid.org/0000-0002-0308-708X","institution":"Lawrence Livermore National Laboratory","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Braden","middleName":"","lastName":"Soper","suffix":""},{"id":54871484,"identity":"8b0d914d-aa9e-4d11-a133-b352597526b4","order_by":1,"name":"Jose Cadena","email":"","orcid":"","institution":"Lawrence Livermore National Laboratory","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Jose","middleName":"","lastName":"Cadena","suffix":""},{"id":54871485,"identity":"4968aadc-39e7-4904-a0d3-2a2fe13055f7","order_by":2,"name":"Sam Nguyen","email":"","orcid":"","institution":"Lawrence Livermore National Laboratory","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Sam","middleName":"","lastName":"Nguyen","suffix":""},{"id":54871486,"identity":"33ccbdf1-e563-4697-816f-5224b6568b6b","order_by":3,"name":"Ryan Chan","email":"","orcid":"","institution":"Lawrence Livermore National Laboratory","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Ryan","middleName":"","lastName":"Chan","suffix":""},{"id":54871487,"identity":"aa128104-82a6-45f8-846f-b600613ef5d1","order_by":4,"name":"Paul Kiszka","email":"","orcid":"","institution":"ProMedica Health System","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Paul","middleName":"","lastName":"Kiszka","suffix":""},{"id":54871488,"identity":"d75031bb-fd20-478c-9706-8a2bac52f8cc","order_by":5,"name":"Lucas Womack","email":"","orcid":"","institution":"ProMedica Health System","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Lucas","middleName":"","lastName":"Womack","suffix":""},{"id":54871489,"identity":"c46bc079-0ed2-4399-8231-e8be64227ea5","order_by":6,"name":"Mark Work","email":"","orcid":"","institution":"ProMedica Health System","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Mark","middleName":"","lastName":"Work","suffix":""},{"id":54871490,"identity":"0c3429cf-af07-4662-b7c7-b0a83a01c7b2","order_by":7,"name":"Joan Duggan","email":"","orcid":"","institution":"University of Toledo","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Joan","middleName":"","lastName":"Duggan","suffix":""},{"id":54871491,"identity":"dfb19652-2760-4d27-85ec-51af6725a813","order_by":8,"name":"Steven Haller","email":"","orcid":"","institution":"University of Toledo","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Steven","middleName":"","lastName":"Haller","suffix":""},{"id":54871492,"identity":"6a8c6759-bba0-416e-8fc4-9c328b05fd74","order_by":9,"name":"Jennifer Hanrahan","email":"","orcid":"","institution":"University of Toledo","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Jennifer","middleName":"","lastName":"Hanrahan","suffix":""},{"id":54871493,"identity":"a37bfa28-5468-4be0-82d4-6d7b5a0887a0","order_by":10,"name":"David Kennedy","email":"","orcid":"","institution":"University of Toledo","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"David","middleName":"","lastName":"Kennedy","suffix":""},{"id":54871494,"identity":"072b259f-00fe-46e6-88d8-5e08be83ce84","order_by":11,"name":"Deepa Mukundan","email":"","orcid":"","institution":"University of Toledo","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Deepa","middleName":"","lastName":"Mukundan","suffix":""},{"id":54871495,"identity":"594ff6cf-1625-4d63-b99c-56022fd1b6e8","order_by":12,"name":"Priyadip Ray","email":"","orcid":"","institution":"Lawrence Livermore National Laboratory","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Priyadip","middleName":"","lastName":"Ray","suffix":""}],"badges":[],"createdAt":"2021-09-21 05:20:39","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-923677/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-923677/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1093/jamia/ocac012","type":"published","date":"2022-01-01T02:48:43+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":18049439,"identity":"b20e6485-9c11-4065-bc0c-2ca6c975c5f0","added_by":"auto","created_at":"2022-02-09 02:49:00","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2841896,"visible":true,"origin":"","legend":"","description":"","filename":"CovidHMMsubmission.pdf","url":"https://assets-eu.researchsquare.com/files/rs-923677/v1_covered.pdf"},{"id":14111209,"identity":"9a3e743d-27e8-447d-9094-20bcc8970106","added_by":"auto","created_at":"2021-09-29 14:53:57","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2836796,"visible":true,"origin":"","legend":"","description":"","filename":"CovidHMMsubmission.pdf","url":"https://assets-eu.researchsquare.com/files/rs-923677/v1_covered.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Dynamic modeling of hospitalized COVID-19 patients reveals disease state dependent risk factors","fulltext":[{"header":"Full Text","content":"This preprint is available for \u003ca href='/article/rs-923677/latest.pdf' target='_blank'\u003edownload as a PDF\u003c/a\u003e."}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"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-923677/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-923677/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The global pandemic of the SARS-CoV-2 coronavirus has significantly strained hospital resources worldwide. Improved understanding of the COVID-19 disease trajectory for patients requiring hospitalization would allow for the development of more targeted preventative, diagnostic and therapeutic strategies. A covariate-dependent, continuous-time hidden Markov model with four states (moderate-illness, severe-illness, discharged, and deceased) was used to model the dynamic progression of COVID-19 during the course of hospitalization. All model parameters were estimated using the electronic health records of 1,362 patients from ProMedica Health System admitted between March 20, 2020 and December 29, 2020 with a positive nasopharyngeal PCR test for SARS-CoV-2. Demographic characteristics, co-morbidities, vital signs and laboratory test results were retrospectively evaluated to predict clinical progression and outcomes. Several patient-level covariates were associated with differential impacts on the risk of progression. Specifically, while being male, being black or having a medical co-morbidity were all associated with an increased risk of progressing from the moderate to severe disease state, these factors resulted in a decreased risk of transitioning from the severe to the deceased disease state. Body mass index (BMI) alone was not found to be associated with an increased risk of disease progression, while higher age was associated with an increased risk in progressing from moderate to severe and from severe to deceased states. Regardless of the differential risk profiles, all covariates considered other than BMI and asthma were associated with an overall increased risk of transitioning to the deceased state. Recent studies have not included analyses of the temporal progression of COVID-19, making the current study a unique modeling-based approach to understand the dynamics of COVID-19 in hospitalized patients. Such dynamic risk stratification models have the potential not only to improve clinical outcomes in COVID-19, but also a myriad of other acute and chronic diseases that, to date, have largely been assessed only by static modeling techniques.","manuscriptTitle":"Dynamic modeling of hospitalized COVID-19 patients reveals disease state dependent risk factors","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2021-09-29 14:53:47","doi":"10.21203/rs.3.rs-923677/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":"3135a5c1-d666-4d13-8e6a-acd076e01394","owner":[],"postedDate":"September 29th, 2021","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":7520277,"name":"Health sciences/Medical research/Biomarkers/Predictive markers"},{"id":7520278,"name":"Health sciences/Diseases/Infectious diseases/Viral infection"},{"id":7520279,"name":"Biological sciences/Computational biology and bioinformatics/Machine learning"},{"id":7520280,"name":"Biological sciences/Computational biology and bioinformatics/Statistical methods"},{"id":7520281,"name":"Biological sciences/Systems biology/Time series"}],"tags":[],"updatedAt":"2022-02-09T02:48:43+00:00","versionOfRecord":{"articleIdentity":"rs-923677","link":"https://doi.org/10.1093/jamia/ocac012","journal":{"identity":"journal-of-the-american-medical-informatics-association","isVorOnly":true,"title":"Journal of the American Medical Informatics Association"},"publishedOn":"2022-01-01 02:48:43","publishedOnDateReadable":"January 1st, 2022"},"versionCreatedAt":"2021-09-29 14:53:47","video":"","vorDoi":"10.1093/jamia/ocac012","vorDoiUrl":"https://doi.org/10.1093/jamia/ocac012","workflowStages":[]},"version":"v1","identity":"rs-923677","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-923677","identity":"rs-923677","version":["v1"]},"buildId":"FbvkV6FR0MCFSLy54lSbu","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}