Improving Hospital Length of Stay Prediction through Heterogeneous Data Integration from MIMIC-III Records

Improving Hospital Length of Stay Prediction through Heterogeneous Data Integration from MIMIC-III Records | 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 Improving Hospital Length of Stay Prediction through Heterogeneous Data Integration from MIMIC-III Records Ahmad F. Al Musawi, Pratip Rana, Sibtanu Raha, William C. Sleeman IV, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6753896/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 Accurate prediction of hospital length of stay (LoS) is a vital component in optimizing clinical workflows, resource allocation, and patient care. This study presents a comprehensive evaluation of machine learning models for both binary and multi-class LoS classification tasks using structured clinical variables, physiological measurements, and unstructured clinical notes. Seven data configurations were constructed from combinations of structured features (Z), including diagnoses, procedures, medications, laboratory tests, and microbiology results; MeSH-based symptoms (S); physiological signals (F); and textual representations (E): Z, F, E, ZS, ZSF, ZSE, and ZSEF. Five predictive models—Artificial Neural Networks (ANN), XGBoost, Logistic Regression (LR), Random Forest (RF), and Support Vector Machine (SVM)—were applied, with and without feature selection, where categorical features and Bag-of-Words representations were reduced to varied dimensions. Results indicate that the base structured feature set (Z) alone yields strong predictive performance across tasks. Moreover, the integration of additional data types—S, F, and E—either individually or in combination, consistently enhanced performance, with the ZSEF configuration achieving the highest F1-scores and AUC values in most cases. While the application of SMOTE did not yield substantial improvements in the global setting encompassing all hospital admissions, it demonstrated enhanced performance in disease-specific cohorts, particularly for patients admitted with lung cancer. Among the evaluated models, XGBoost and ANN demonstrated superior generalizability. These findings underscore the effectiveness of multimodal data integration and feature reduction techniques in advancing predictive modeling for hospital length of stay across diverse patient populations. Biological sciences/Computational biology and bioinformatics/Data integration Biological sciences/Computational biology and bioinformatics/Data mining Biological sciences/Computational biology and bioinformatics/Predictive medicine Full Text Additional Declarations No competing interests reported. Supplementary Files SupplementaryInformation.pdf 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-6753896","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":504216251,"identity":"cc40a488-7b02-4068-98b0-702021264def","order_by":0,"name":"Ahmad F. Al Musawi","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA0UlEQVRIie3NsQrCMBCA4ZNCHLzUNUVpXyHFUcFXqUsnZyfBQchk3X0LRXAuBOIizkoHFd+h1EVtEReRxm4O+Ze74T4OwGT6x+qvgWDJ+LXGOmK9CQmDagSADPlvpDlthE42lu2mwJTdBLj2ISgnTNJNC5VEpujGiQR0HB2BggBJEE7RulMTMFjqiJcTJ7sn6Cm8FmSiJTwnjIoEucLaNScB1xFf0nWXzh/oK+JfZnvmL3bncuJuo9UxS8O+q6xznI16nr3VfPmMVTs3mUwm0/eeTf9Ce1ICTmEAAAAASUVORK5CYII=","orcid":"","institution":"Virginia Commonwealth University","correspondingAuthor":true,"prefix":"","firstName":"Ahmad","middleName":"F. Al","lastName":"Musawi","suffix":""},{"id":504216252,"identity":"336bed91-b4de-4fcb-854d-f10bac1575cc","order_by":1,"name":"Pratip Rana","email":"","orcid":"","institution":"Old Dominion University","correspondingAuthor":false,"prefix":"","firstName":"Pratip","middleName":"","lastName":"Rana","suffix":""},{"id":504216253,"identity":"e74479a4-e1f7-45e5-8323-390562927798","order_by":2,"name":"Sibtanu Raha","email":"","orcid":"","institution":"EAB Global Inc.","correspondingAuthor":false,"prefix":"","firstName":"Sibtanu","middleName":"","lastName":"Raha","suffix":""},{"id":504216254,"identity":"58b4cb73-2bb5-4b7f-96e5-cde67eda2980","order_by":3,"name":"William C. Sleeman IV","email":"","orcid":"","institution":"Veterans Health Administration","correspondingAuthor":false,"prefix":"","firstName":"William","middleName":"C. Sleeman","lastName":"IV","suffix":""},{"id":504216255,"identity":"0bce97f6-2ea6-417e-8e9c-78a06e89b599","order_by":4,"name":"Rishabh Kapoor","email":"","orcid":"","institution":"Veterans Health Administration","correspondingAuthor":false,"prefix":"","firstName":"Rishabh","middleName":"","lastName":"Kapoor","suffix":""},{"id":504216256,"identity":"d45ff40b-193c-4799-bec9-55965970f6c5","order_by":5,"name":"Preetam Ghosh","email":"","orcid":"","institution":"Virginia Commonwealth University","correspondingAuthor":false,"prefix":"","firstName":"Preetam","middleName":"","lastName":"Ghosh","suffix":""}],"badges":[],"createdAt":"2025-05-26 22:38:10","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6753896/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6753896/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108088302,"identity":"837bfce4-64ee-4bc9-9171-48707a67072b","added_by":"auto","created_at":"2026-04-29 08:56:27","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1744331,"visible":true,"origin":"","legend":"","description":"","filename":"ICULoSmanuscript12.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6753896/v1_covered_9102e621-aef8-4ecc-919d-8a930d4e79ce.pdf"},{"id":89880432,"identity":"adf23ffd-aa3c-4128-b724-69f9bd3dbdbc","added_by":"auto","created_at":"2025-08-26 05:43:35","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":259305,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryInformation.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6753896/v1/758e2d115ad7bb421e955686.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Improving Hospital Length of Stay Prediction through Heterogeneous Data Integration from MIMIC-III Records","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-6753896/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6753896/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Accurate prediction of hospital length of stay (LoS) is a vital component in optimizing clinical workflows, resource allocation, and patient care. This study presents a comprehensive evaluation of machine learning models for both binary and multi-class LoS classification tasks using structured clinical variables, physiological measurements, and unstructured clinical notes. Seven data configurations were constructed from combinations of structured features (Z), including diagnoses, procedures, medications, laboratory tests, and microbiology results; MeSH-based symptoms (S); physiological signals (F); and textual representations (E): Z, F, E, ZS, ZSF, ZSE, and ZSEF. Five predictive models—Artificial Neural Networks (ANN), XGBoost, Logistic Regression (LR), Random Forest (RF), and Support Vector Machine (SVM)—were applied, with and without feature selection, where categorical features and Bag-of-Words representations were reduced to varied dimensions. Results indicate that the base structured feature set (Z) alone yields strong predictive performance across tasks. Moreover, the integration of additional data types—S, F, and E—either individually or in combination, consistently enhanced performance, with the ZSEF configuration achieving the highest F1-scores and AUC values in most cases. While the application of SMOTE did not yield substantial improvements in the global setting encompassing all hospital admissions, it demonstrated enhanced performance in disease-specific cohorts, particularly for patients admitted with lung cancer. Among the evaluated models, XGBoost and ANN demonstrated superior generalizability. These findings underscore the effectiveness of multimodal data integration and feature reduction techniques in advancing predictive modeling for hospital length of stay across diverse patient populations.","manuscriptTitle":"Improving Hospital Length of Stay Prediction through Heterogeneous Data Integration from MIMIC-III Records","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-26 05:35:29","doi":"10.21203/rs.3.rs-6753896/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":"081e0d2f-16ee-4b49-b569-c7459a8e30db","owner":[],"postedDate":"August 26th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":53572585,"name":"Biological sciences/Computational biology and bioinformatics/Data integration"},{"id":53572586,"name":"Biological sciences/Computational biology and bioinformatics/Data mining"},{"id":53572587,"name":"Biological sciences/Computational biology and bioinformatics/Predictive medicine"}],"tags":[],"updatedAt":"2026-04-29T08:55:35+00:00","versionOfRecord":[],"versionCreatedAt":"2025-08-26 05:35:29","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6753896","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6753896","identity":"rs-6753896","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}