Predicting Mortality and Risk Factors in Cystic Fibrosis Using a Boruta- Enhanced Machine Learning Pipeline: Comparative Evaluation of Ensemble and Penalized Regression Models

Predicting Mortality and Risk Factors in Cystic Fibrosis Using a Boruta- Enhanced Machine Learning Pipeline: Comparative Evaluation of Ensemble and Penalized Regression Models | 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 Research Article Predicting Mortality and Risk Factors in Cystic Fibrosis Using a Boruta- Enhanced Machine Learning Pipeline: Comparative Evaluation of Ensemble and Penalized Regression Models Farzaneh Hamidi, Anoshirvan Kazemnejad, Maryam Hassanzad, Mina Jahangiri This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8908152/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 Background Early and accurate prediction of mortality risk in patients with cystic fibrosis (CF) can guide clinical decision-making and resource allocation, especially in settings with limited access to advanced therapies. Traditional prognostic tools often rely on one or a few variables (e.g. FEV₁) and may fail to capture complex, nonlinear interactions among clinical and laboratory features. Methods We collected clinical and laboratory data from 349 CF patients monitored at Masih Daneshvari Hospital (Tehran, 2021–2024), excluding records with unavailable vital status. After filtering out features with > 30% missingness, we applied the Boruta algorithm to select relevant predictors. The dataset was split 80/20 into training and test sets. To address missingness, we performed multiple imputation (MICE, m = 5) separately on training and test sets to avoid leakage. On each imputed training fold, we applied SMOTE (K = 5, dup_size = 4) to balance classes, and trained three models: Random Forest (300 trees), XGBoost (eta = 0.1, max_depth = 6, 100 rounds), and penalized logistic regression (elastic net, α = 0.5, λ via 5-fold CV). For each model-imputation pair, optimal probability thresholds were derived using the Youden index on training predictions; final thresholds were the median across imputations. Test predictions were pooled by averaging probabilities across imputations and applying the median threshold. Models were evaluated on accuracy, sensitivity, specificity, precision, F1-score, and AUC (ROC; PRROC for precision-recall). Results Boruta selected 17 predictors (e.g. ALP, WBC, PCO₂, respiratory distress). In the test set, Random Forest achieved 0.83 accuracy, specificity 0.91, sensitivity 0.40, precision 0.89, F1 0.90, and AUC 0.75. XGBoost achieved 0.85 accuracy, specificity = 0.89, sensitivity = 0.60, precision = 0.92, F1 = 0.91, and AUC = 0.77. Penalized logistic regression (GLMnet) achieved accuracy = 0.81, specificity = 0.70, sensitivity = 0.70, precision = 0.94, F1 = 0.88, and AUC = 0.75. Conclusions Among the evaluated models, XGBoost offers the best balance of sensitivity and specificity, making it a promising candidate for clinical deployment in mortality risk stratification in CF. The selected 17 features are biologically plausible and align with CF pathophysiology. Future work should validate our findings in multi-center cohorts and incorporate longitudinal data to further improve prognostic performance. Artificial intelligence Cystic Fibrosis Classification Class-imbalanced dataset Full Text Additional Declarations No competing interests reported. Supplementary Files supplementary1.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-8908152","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":612788977,"identity":"09689ce5-1e2a-4315-9336-83d13c92fbc4","order_by":0,"name":"Farzaneh Hamidi","email":"","orcid":"","institution":"Tarbiat Modares University","correspondingAuthor":false,"prefix":"","firstName":"Farzaneh","middleName":"","lastName":"Hamidi","suffix":""},{"id":612788978,"identity":"769ebc9e-7e05-49bd-b8cf-93d85afb418f","order_by":1,"name":"Anoshirvan Kazemnejad","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA7UlEQVRIiWNgGAWjYBACCRiDH5nDkECMFskGkrUYHEDWgg9Ith9/+OgGg12e8bXDB2/83GNjz8B++AHDwz24tUjzJCQb5zAkF5vdTku27HmWltjAk2bAkPAMtxY5hoRj0jkMzInbbueYSfAcOAz0RQ7QLwfwaOF/2P47h6E+cfPsHDPJPwf+2zPwv8GvRVoimY05h+Fw4gbpHDNpngMHGBskCNgiOeMZM9BhxxNnAP1iLXMgObFN4pnBAXxaJM6nP/ycw1Cd2D87+eDNNwfs7Pn5kx8+/IFHCxgw/kPisAExIQ2jYBSMglEwCggAAN46TksG6DLfAAAAAElFTkSuQmCC","orcid":"","institution":"Tarbiat Modares University","correspondingAuthor":true,"prefix":"","firstName":"Anoshirvan","middleName":"","lastName":"Kazemnejad","suffix":""},{"id":612788979,"identity":"7e9aba59-ab64-46aa-9e97-dac338bcdf18","order_by":2,"name":"Maryam Hassanzad","email":"","orcid":"","institution":"Shahid Beheshti University of Medical Sciences","correspondingAuthor":false,"prefix":"","firstName":"Maryam","middleName":"","lastName":"Hassanzad","suffix":""},{"id":612788980,"identity":"0b31a672-1a37-4c97-97d3-b1a7a17d9b4f","order_by":3,"name":"Mina Jahangiri","email":"","orcid":"","institution":"Tarbiat Modares University","correspondingAuthor":false,"prefix":"","firstName":"Mina","middleName":"","lastName":"Jahangiri","suffix":""}],"badges":[],"createdAt":"2026-02-18 10:11:12","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8908152/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8908152/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108628557,"identity":"9ccf8326-c084-4890-8730-f8b35c2fa013","added_by":"auto","created_at":"2026-05-06 16:11:28","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":393225,"visible":true,"origin":"","legend":"","description":"","filename":"RevisedCF2draftpaper.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8908152/v1_covered_e51d2e68-06d3-45e9-b12a-11e2874f91e3.pdf"},{"id":105527446,"identity":"c5acd927-f7a8-4f59-9ca6-072fcc12cd4a","added_by":"auto","created_at":"2026-03-27 04:42:42","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":19161,"visible":true,"origin":"","legend":"","description":"","filename":"supplementary1.docx","url":"https://assets-eu.researchsquare.com/files/rs-8908152/v1/4c1ceed582768409b50f7d85.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"Predicting Mortality and Risk Factors in Cystic Fibrosis Using a Boruta- Enhanced Machine Learning Pipeline: Comparative Evaluation of Ensemble and Penalized Regression Models","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":"Artificial intelligence, Cystic Fibrosis, Classification, Class-imbalanced dataset","lastPublishedDoi":"10.21203/rs.3.rs-8908152/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8908152/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground\u003c/h2\u003e \u003cp\u003eEarly and accurate prediction of mortality risk in patients with cystic fibrosis (CF) can guide clinical decision-making and resource allocation, especially in settings with limited access to advanced therapies. Traditional prognostic tools often rely on one or a few variables (e.g. FEV₁) and may fail to capture complex, nonlinear interactions among clinical and laboratory features.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e \u003cp\u003eWe collected clinical and laboratory data from 349 CF patients monitored at Masih Daneshvari Hospital (Tehran, 2021\u0026ndash;2024), excluding records with unavailable vital status. After filtering out features with \u0026gt;\u0026thinsp;30% missingness, we applied the Boruta algorithm to select relevant predictors. The dataset was split 80/20 into training and test sets. To address missingness, we performed multiple imputation (MICE, \u003cem\u003em\u003c/em\u003e\u0026thinsp;=\u0026thinsp;5) separately on training and test sets to avoid leakage. On each imputed training fold, we applied SMOTE (K\u0026thinsp;=\u0026thinsp;5, dup_size\u0026thinsp;=\u0026thinsp;4) to balance classes, and trained three models: Random Forest (300 trees), XGBoost (eta\u0026thinsp;=\u0026thinsp;0.1, max_depth\u0026thinsp;=\u0026thinsp;6, 100 rounds), and penalized logistic regression (elastic net, α\u0026thinsp;=\u0026thinsp;0.5, λ via 5-fold CV). For each model-imputation pair, optimal probability thresholds were derived using the Youden index on training predictions; final thresholds were the median across imputations. Test predictions were pooled by averaging probabilities across imputations and applying the median threshold. Models were evaluated on accuracy, sensitivity, specificity, precision, F1-score, and AUC (ROC; PRROC for precision-recall).\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e \u003cp\u003eBoruta selected 17 predictors (e.g. ALP, WBC, PCO₂, respiratory distress). In the test set, Random Forest achieved 0.83 accuracy, specificity 0.91, sensitivity 0.40, precision 0.89, F1 0.90, and AUC 0.75. XGBoost achieved 0.85 accuracy, specificity\u0026thinsp;=\u0026thinsp;0.89, sensitivity\u0026thinsp;=\u0026thinsp;0.60, precision\u0026thinsp;=\u0026thinsp;0.92, F1\u0026thinsp;=\u0026thinsp;0.91, and AUC\u0026thinsp;=\u0026thinsp;0.77. Penalized logistic regression (GLMnet) achieved accuracy\u0026thinsp;=\u0026thinsp;0.81, specificity\u0026thinsp;=\u0026thinsp;0.70, sensitivity\u0026thinsp;=\u0026thinsp;0.70, precision\u0026thinsp;=\u0026thinsp;0.94, F1\u0026thinsp;=\u0026thinsp;0.88, and AUC\u0026thinsp;=\u0026thinsp;0.75.\u003c/p\u003e\u003ch2\u003eConclusions\u003c/h2\u003e \u003cp\u003eAmong the evaluated models, XGBoost offers the best balance of sensitivity and specificity, making it a promising candidate for clinical deployment in mortality risk stratification in CF. The selected 17 features are biologically plausible and align with CF pathophysiology. Future work should validate our findings in multi-center cohorts and incorporate longitudinal data to further improve prognostic performance.\u003c/p\u003e","manuscriptTitle":"Predicting Mortality and Risk Factors in Cystic Fibrosis Using a Boruta- Enhanced Machine Learning Pipeline: Comparative Evaluation of Ensemble and Penalized Regression Models","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-27 04:42:37","doi":"10.21203/rs.3.rs-8908152/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":"18f14100-5832-45c8-ba1e-0183e0c1d1ea","owner":[],"postedDate":"March 27th, 2026","published":true,"recentEditorialEvents":[{"type":"decision","content":"Withdrawn","date":"2026-05-06T15:57:10+00:00","index":"","fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-05-06T16:11:16+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-27 04:42:37","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8908152","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8908152","identity":"rs-8908152","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}