A Hybrid AutoML Ensemble Integrating Conventional Learners and Gradient-Boosting Models for Multi-Outcome Prediction in ICU Patients with Pseudomonas aeruginosa

A Hybrid AutoML Ensemble Integrating Conventional Learners and Gradient-Boosting Models for Multi-Outcome Prediction in ICU Patients with Pseudomonas aeruginosa | 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 A Hybrid AutoML Ensemble Integrating Conventional Learners and Gradient-Boosting Models for Multi-Outcome Prediction in ICU Patients with Pseudomonas aeruginosa LV Xiao-chun, Ren Qi, Zhu Lihong, CHEN Kun, Jian-bing WANG, CHEN Fang, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7125109/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 Carbapenem-resistant Pseudomonas aeruginosa (PA) jeopardises intensive-care patients worldwide. We developed a real-time, interpretable hybrid automated machine learning (AutoML) ensemble to predict multiple outcomes. A retrospective cohort of 847 ICU admissions with PA (2018–2024) underwent VTF–MI–L1 feature selection; XGBoost, LightGBM, CatBoost, random forests and linear/logistic regressors were ensembled via bagging, voting, stacking and boosting. Nested five-fold cross-validation evaluated performance (AUC for classification; MSE, RMSE, MAE and R² for regression); SHAP explained predictions, and inference latency was recorded. Across four regression endpoints—carbapenem-resistance rate (CRR), average CRR of the last two isolates (CRR-PA-Last2), ICU length of stay (ICU-LOS) and time from ICU admission to death (ICU-Death interval)—XGBoost regressor (XGB-R) performed best (mean MSE = 9.76 × 10³, RMSE = 64.11, MAE = 25.24, R² = 0.77; mean Friedman rank = 1.95). For classification, the Voting Classifier achieved the highest AUC (0.842) for in-hospital mortality (IHM), whereas the LightGBM classifier led for antimicrobial susceptibility of the last PA isolate before discharge (LastPaAST, AUC = 0.981). SHAP highlighted age, cumulative carbapenem exposure, the durations of mechanical ventilation (MV-days), central venous catheterisation (CVC-days) and urinary catheterisation (UC-days) as key contributors. All top models produced predictions in < 50 ms, supporting bedside antimicrobial-stewardship and infection-control decisions; multicentre prospective validation is warranted. Health sciences/Diseases Health sciences/Medical research Biological sciences/Microbiology Health sciences/Risk factors Antimicrobial resistance Pseudomonas aeruginosa Intensive care unit Gradient boosting Automated machine learning Full Text Additional Declarations No competing interests reported. Supplementary Files SupplementaryFileS1ZhejiangHospitalIRBapprovalChineseoriginal.pdf SupplementaryFileS2ZhejiangHospitalIRBapprovalEnglishtranslation.pdf SupplementaryTableS1.xlsx SupplementaryTableS2.xlsx SupplementaryDataS1.xlsx SupplementaryDataS2.xlsx SupplementaryFigureS1.pdf SupplementaryFigureS2.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-7125109","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":489079694,"identity":"86d25547-1ffd-4442-94c6-0dc759d83e5a","order_by":0,"name":"LV Xiao-chun","email":"","orcid":"","institution":"Zhejiang Hospital","correspondingAuthor":false,"prefix":"","firstName":"LV","middleName":"","lastName":"Xiao-chun","suffix":""},{"id":489079698,"identity":"ba8e7c7b-eeaa-4e7c-a737-50b863f8861f","order_by":1,"name":"Ren Qi","email":"","orcid":"","institution":"Zhejiang Hospital","correspondingAuthor":false,"prefix":"","firstName":"Ren","middleName":"","lastName":"Qi","suffix":""},{"id":489079702,"identity":"fc83f313-9b01-4326-8f46-4cc5d07f8fb2","order_by":2,"name":"Zhu Lihong","email":"","orcid":"","institution":"Zhejiang Hospital","correspondingAuthor":false,"prefix":"","firstName":"Zhu","middleName":"","lastName":"Lihong","suffix":""},{"id":489079703,"identity":"cd1bf8e2-eccc-49d6-a274-09a059f6fb18","order_by":3,"name":"CHEN Kun","email":"","orcid":"","institution":"Zhejiang University","correspondingAuthor":false,"prefix":"","firstName":"CHEN","middleName":"","lastName":"Kun","suffix":""},{"id":489079704,"identity":"fbf41d24-b665-43b1-ba7e-a7d055cbe6ad","order_by":4,"name":"Jian-bing WANG","email":"","orcid":"","institution":"Zhejiang University","correspondingAuthor":false,"prefix":"","firstName":"Jian-bing","middleName":"","lastName":"WANG","suffix":""},{"id":489079705,"identity":"b439ab98-096f-453d-b51c-7d7a7627458a","order_by":5,"name":"CHEN Fang","email":"","orcid":"","institution":"Zhejiang Hospital","correspondingAuthor":false,"prefix":"","firstName":"CHEN","middleName":"","lastName":"Fang","suffix":""},{"id":489079706,"identity":"17d365fb-e348-4a58-8c11-9e356a8bcb0c","order_by":6,"name":"JIN Kai-ling","email":"","orcid":"","institution":"Zhejiang Hospital","correspondingAuthor":false,"prefix":"","firstName":"JIN","middleName":"","lastName":"Kai-ling","suffix":""},{"id":489079707,"identity":"cf0195d3-cbe0-4439-8b6e-bddffc2a6051","order_by":7,"name":"LIN Kai","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA9ElEQVRIiWNgGAWjYBACPgY2BoYEBgYZMC+hAkgwMzfg1cIG1cID0XIGpIWRCC0MMC2MbWCSoJbEDw8Y7HjMGZiPPXg4rzaavx2o5UfFNnxaDkskMCTzWDawpRskbjueO+MwYwNjz5nbeLSwNwC1HOAxOMBjJpG47VhuA1ALM2MbXi3NPyBa+L9JJM45ljufsBa2YzBb2CQSG2pyNxDUwsyWZpFgkMxjcJjN3CDh2IHcjUAtB/H5hZ+9zfjmjwo7OYPjzc8e/qipy513/vDBBz8qcGthYAYRBmAGKIYOgwUP4FaP7i8GhjpiFY+CUTAKRsEIAgB6KU9uFtHXogAAAABJRU5ErkJggg==","orcid":"","institution":"Zhejiang Hospital","correspondingAuthor":true,"prefix":"","firstName":"LIN","middleName":"","lastName":"Kai","suffix":""}],"badges":[],"createdAt":"2025-07-15 01:38:06","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-7125109/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7125109/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":92716213,"identity":"d07a5482-bc22-4021-9b53-58600b3f2970","added_by":"auto","created_at":"2025-10-03 12:33:09","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1298860,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7125109/v1_covered_cd65727d-a204-4b85-a4b4-258c4b3f2c78.pdf"},{"id":87383870,"identity":"7c548a77-49a2-4b0d-9637-0b7699c9ace9","added_by":"auto","created_at":"2025-07-23 08:43:34","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":1914003,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryFileS1ZhejiangHospitalIRBapprovalChineseoriginal.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7125109/v1/c3797e1d0bfa05d2ae240ce4.pdf"},{"id":87380798,"identity":"42d6505d-014b-40d0-9159-54f463fb1044","added_by":"auto","created_at":"2025-07-23 08:35:34","extension":"pdf","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":193259,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryFileS2ZhejiangHospitalIRBapprovalEnglishtranslation.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7125109/v1/e0b8c017d7eb25d62eef1c1d.pdf"},{"id":87384933,"identity":"695da075-e8c5-420b-8ec1-9e1b29883671","added_by":"auto","created_at":"2025-07-23 08:51:34","extension":"xlsx","order_by":3,"title":"","display":"","copyAsset":false,"role":"supplement","size":12350,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryTableS1.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-7125109/v1/888247e8b16a85267c7fdecf.xlsx"},{"id":87387447,"identity":"da0dd922-e456-48e2-a55a-97e78533a53f","added_by":"auto","created_at":"2025-07-23 09:07:34","extension":"xlsx","order_by":4,"title":"","display":"","copyAsset":false,"role":"supplement","size":9839,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryTableS2.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-7125109/v1/e8f42b145f17247c2127af59.xlsx"},{"id":87380806,"identity":"aa3d22f9-0c08-4763-8b1b-8e1e3262a76d","added_by":"auto","created_at":"2025-07-23 08:35:34","extension":"xlsx","order_by":5,"title":"","display":"","copyAsset":false,"role":"supplement","size":215762,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryDataS1.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-7125109/v1/b35329e21aada1c9bccf9949.xlsx"},{"id":87380796,"identity":"bde4c27a-2c5d-46ad-b66f-b0742d1934f0","added_by":"auto","created_at":"2025-07-23 08:35:34","extension":"xlsx","order_by":6,"title":"","display":"","copyAsset":false,"role":"supplement","size":60933,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryDataS2.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-7125109/v1/50690bf162644ec8e668ceed.xlsx"},{"id":87380813,"identity":"239d42cb-65c6-4365-9715-c360a88e3add","added_by":"auto","created_at":"2025-07-23 08:35:35","extension":"pdf","order_by":7,"title":"","display":"","copyAsset":false,"role":"supplement","size":2484746,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryFigureS1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7125109/v1/f37cbe5302f74fc0aaf5f7e6.pdf"},{"id":87380822,"identity":"d05358c3-cb7c-41f6-80b3-f433a2e035d2","added_by":"auto","created_at":"2025-07-23 08:35:35","extension":"pdf","order_by":8,"title":"","display":"","copyAsset":false,"role":"supplement","size":2459317,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryFigureS2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7125109/v1/f86d8f264495ff3fef23b49b.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Hybrid AutoML Ensemble Integrating Conventional Learners and Gradient-Boosting Models for Multi-Outcome Prediction in ICU Patients with Pseudomonas aeruginosa","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":true,"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":"Antimicrobial resistance, Pseudomonas aeruginosa, Intensive care unit, Gradient boosting, Automated machine learning","lastPublishedDoi":"10.21203/rs.3.rs-7125109/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7125109/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eCarbapenem-resistant \u003cem\u003ePseudomonas aeruginosa\u003c/em\u003e (PA) jeopardises intensive-care patients worldwide. We developed a real-time, interpretable hybrid automated machine learning (AutoML) ensemble to predict multiple outcomes. A retrospective cohort of 847 ICU admissions with PA (2018–2024) underwent VTF–MI–L1 feature selection; XGBoost, LightGBM, CatBoost, random forests and linear/logistic regressors were ensembled via bagging, voting, stacking and boosting. Nested five-fold cross-validation evaluated performance (AUC for classification; MSE, RMSE, MAE and R² for regression); SHAP explained predictions, and inference latency was recorded. Across four regression endpoints—carbapenem-resistance rate (CRR), average CRR of the last two isolates (CRR-PA-Last2), ICU length of stay (ICU-LOS) and time from ICU admission to death (ICU-Death interval)—XGBoost regressor (XGB-R) performed best (mean MSE = 9.76 × 10³, RMSE = 64.11, MAE = 25.24, R² = 0.77; mean Friedman rank = 1.95). For classification, the Voting Classifier achieved the highest AUC (0.842) for in-hospital mortality (IHM), whereas the LightGBM classifier led for antimicrobial susceptibility of the last PA isolate before discharge (LastPaAST, AUC = 0.981). SHAP highlighted age, cumulative carbapenem exposure, the durations of mechanical ventilation (MV-days), central venous catheterisation (CVC-days) and urinary catheterisation (UC-days) as key contributors. All top models produced predictions in \u0026lt; 50 ms, supporting bedside antimicrobial-stewardship and infection-control decisions; multicentre prospective validation is warranted.\u003c/p\u003e","manuscriptTitle":"A Hybrid AutoML Ensemble Integrating Conventional Learners and Gradient-Boosting Models for Multi-Outcome Prediction in ICU Patients with Pseudomonas aeruginosa","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-07-23 08:35:29","doi":"10.21203/rs.3.rs-7125109/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":"09f5728a-5ced-4f35-9f6c-79c05562a991","owner":[],"postedDate":"July 23rd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":51921230,"name":"Health sciences/Diseases"},{"id":51921231,"name":"Health sciences/Medical research"},{"id":51921232,"name":"Biological sciences/Microbiology"},{"id":51921233,"name":"Health sciences/Risk factors"}],"tags":[],"updatedAt":"2025-10-03T12:24:56+00:00","versionOfRecord":[],"versionCreatedAt":"2025-07-23 08:35:29","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7125109","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7125109","identity":"rs-7125109","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}