PRECISE-RA: Predicting Remission and StratifyingRisk in Rheumatoid Arthritis Patients Treated withbDMARDs—A Robust Machine Learning Approach

PRECISE-RA: Predicting Remission and StratifyingRisk in Rheumatoid Arthritis Patients Treated withbDMARDs—A Robust Machine Learning Approach | 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 PRECISE-RA: Predicting Remission and StratifyingRisk in Rheumatoid Arthritis Patients Treated withbDMARDs—A Robust Machine Learning Approach Fatemeh Salehi, Bjoern M. Eskofier, Emmanuelle Salin, Sara Bayat, and 4 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5941518/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 04 Jul, 2025 Read the published version in Scientific Reports → Version 1 posted 11 You are reading this latest preprint version Abstract Rheumatoid arthritis (RA) is a chronic autoimmune disease affecting millions worldwide, leading to inflammation, joint damage, and reduced quality of life. Although biological disease-modifying antirheumatic drugs (bDMARDs) are effective, they are costly, and up to 40% of patients do not achieve remission within six months. Accurate prediction of treatment response is crucial for optimizing care, minimizing side effects, and enhancing cost efficiency. This study proposes a robust machine learning framework for predicting six-month remission in RA patients using baseline routine clinical data. The framework also integrates risk stratification and explainability to enhance its clinical applicability. We evaluated multiple machine learning models, AdaBoost, Random Forest, XGBoost, and Support Vector Machines, using data from Austrian RA patients. We externally validated the results on an independent dataset from the Erlangen Hospital. To improve the reliability of probability estimates for actionable risk stratification, we employed calibration techniques, including Platt scaling, Isotonic regression, Beta calibration, and Spline calibration. We generated calibration curves to assess and visualize the alignment between predicted probabilities and observed outcomes. In addition, we used SHapley Additive exPlanations (SHAP) to analyze the contributions of different patient characteristics to the prediction of RA remission. AdaBoost demonstrated stronger performance than the other models, achieving an accuracy of 85.71% and a Brier score of 0.13 with isotonic regression calibration. SHAP identified DAS28, visual analog scales (VAS), age, and swollen joint count (SJC) as important characteristics for the prediction of RA remission. We also stratified patients into low-, medium-, and high-risk categories based on model predictions to support follow-up scheduling and treatment prioritization. Our framework predicts RA remission before the initiation of bDMARD therapy. It enables personalized care, actionable risk stratification, and optimized resource allocation. Its robustness was validated on two different individual cohort datasets, which highlights its potential for integration into routine clinical workflows. Health sciences/Rheumatology Biological sciences/Biological techniques/Bioinformatics Physical sciences/Engineering/Biomedical engineering Full Text Additional Declarations No competing interests reported. Supplementary Files SupplementaryFiles.pdf Cite Share Download PDF Status: Published Journal Publication published 04 Jul, 2025 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 27 May, 2025 Reviews received at journal 12 May, 2025 Reviewers agreed at journal 27 Apr, 2025 Reviews received at journal 14 Mar, 2025 Reviewers agreed at journal 11 Mar, 2025 Reviewers agreed at journal 05 Mar, 2025 Reviewers invited by journal 18 Feb, 2025 Editor assigned by journal 18 Feb, 2025 Editor invited by journal 04 Feb, 2025 Submission checks completed at journal 03 Feb, 2025 First submitted to journal 01 Feb, 2025 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-5941518","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":411220547,"identity":"df2dd9c2-2cbe-42eb-8067-7009fc5975da","order_by":0,"name":"Fatemeh Salehi","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABSklEQVRIie2QwUrDQBBAJywkl4Fcp1TML2wJxB7U/krDgqdUCkLx0EOksL0Ee/U3/AITFnKq9ZpDQWsh50KhCJXqRtuDDQWPgnmw7OzsvJ1hASoq/iBW+LXFerGQAY91BgEIAG1WZM2SgjHbKca3gvFWqcn2bxTYKgU8PaBYT8lrdj0FZ5jczLvdqYP2Y/LS7E+P3JTlBL3TkoKCucE4Bz72B+4dzxsRXQpOaY5eanoEk4t9pQXCrHekAg6+rCNXxgOhR2Qq9J5Djwx9td/FnlvrzkaBM5oN11ppRfb45I02Cl1prbTyUVJImKwT6qcyXzKt+BEEHtSkQm5i0SUuK3O3HqS6IJsNisFERIFLtVuFlOJVsz0R5cH82TLoq2NnJJIlvqszPVhjSSvVsqV1ny1656Vf3qk/Tox2UfuQsI+x+G1lRUVFxX/gE43Ob1mEJo0GAAAAAElFTkSuQmCC","orcid":"","institution":"University of Erlangen-Nuremberg","correspondingAuthor":true,"prefix":"","firstName":"Fatemeh","middleName":"","lastName":"Salehi","suffix":""},{"id":411220549,"identity":"e14ce59e-0ce5-41be-aafd-c190e06836c7","order_by":1,"name":"Bjoern M. Eskofier","email":"","orcid":"","institution":"University of Erlangen-Nuremberg","correspondingAuthor":false,"prefix":"","firstName":"Bjoern","middleName":"M.","lastName":"Eskofier","suffix":""},{"id":411220551,"identity":"72c13dd7-62c2-499d-9cb4-e69e3152524c","order_by":2,"name":"Emmanuelle Salin","email":"","orcid":"","institution":"University of Erlangen-Nuremberg","correspondingAuthor":false,"prefix":"","firstName":"Emmanuelle","middleName":"","lastName":"Salin","suffix":""},{"id":411220552,"identity":"f74858a1-1862-483e-a576-9e2456002235","order_by":3,"name":"Sara Bayat","email":"","orcid":"","institution":"Universitätsklinikum Erlangen","correspondingAuthor":false,"prefix":"","firstName":"Sara","middleName":"","lastName":"Bayat","suffix":""},{"id":411220553,"identity":"bc74ddb9-9231-4d4c-bc36-ccd8a144cc18","order_by":4,"name":"Georg Schett","email":"","orcid":"","institution":"Universitätsklinikum Erlangen","correspondingAuthor":false,"prefix":"","firstName":"Georg","middleName":"","lastName":"Schett","suffix":""},{"id":411220554,"identity":"d64ca9d3-5157-42f9-8471-43e37a43513f","order_by":5,"name":"Arnd Kleyer","email":"","orcid":"","institution":"Charité - University Medicine Berlin","correspondingAuthor":false,"prefix":"","firstName":"Arnd","middleName":"","lastName":"Kleyer","suffix":""},{"id":411220555,"identity":"a6e14475-b3a2-417f-876f-0ffeba7aac0a","order_by":6,"name":"Benjamin Smarr","email":"","orcid":"","institution":"University of California, San Diego","correspondingAuthor":false,"prefix":"","firstName":"Benjamin","middleName":"","lastName":"Smarr","suffix":""},{"id":411220557,"identity":"879b184f-aa1d-4fc0-8f66-56c3b00c71d5","order_by":7,"name":"Ruth Fritsch-Stork","email":"","orcid":"","institution":"Sigmund Freud University Vienna","correspondingAuthor":false,"prefix":"","firstName":"Ruth","middleName":"","lastName":"Fritsch-Stork","suffix":""}],"badges":[],"createdAt":"2025-02-01 11:23:16","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5941518/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5941518/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-09975-z","type":"published","date":"2025-07-04T15:57:21+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":86181102,"identity":"e061a17d-f762-40a0-8c94-748f15b6f696","added_by":"auto","created_at":"2025-07-07 16:23:20","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":4330295,"visible":true,"origin":"","legend":"","description":"","filename":"PreciseRA3.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5941518/v1_covered_9c34051a-0280-417f-86cb-61c08c38b617.pdf"},{"id":75484914,"identity":"f3c1ea8e-3364-46ab-b3df-84a2eb77f212","added_by":"auto","created_at":"2025-02-05 06:10:47","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":139069,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryFiles.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5941518/v1/160257f4c42c3959cca6c1da.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"PRECISE-RA: Predicting Remission and StratifyingRisk in Rheumatoid Arthritis Patients Treated withbDMARDs—A Robust Machine Learning Approach","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-5941518/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5941518/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eRheumatoid arthritis (RA) is a chronic autoimmune disease affecting millions worldwide, leading to inflammation, joint damage, and reduced quality of life. Although biological disease-modifying antirheumatic drugs (bDMARDs) are effective, they are costly, and up to 40% of patients do not achieve remission within six months. Accurate prediction of treatment response is crucial for optimizing care, minimizing side effects, and enhancing cost efficiency.\u003c/p\u003e\n\u003cp\u003eThis study proposes a robust machine learning framework for predicting six-month remission in RA patients using baseline routine clinical data. The framework also integrates risk stratification and explainability to enhance its clinical applicability. We evaluated multiple machine learning models, AdaBoost, Random Forest, XGBoost, and Support Vector Machines, using data from Austrian RA patients. We externally validated the results on an independent dataset from the Erlangen Hospital. To improve the reliability of probability estimates for actionable risk stratification, we employed calibration techniques, including Platt scaling, Isotonic regression, Beta calibration, and Spline calibration. We generated calibration curves to assess and visualize the alignment between predicted probabilities and observed outcomes. In addition, we used SHapley Additive exPlanations (SHAP) to analyze the contributions of different patient characteristics to the prediction of RA remission.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eAdaBoost demonstrated stronger performance than the other models, achieving an accuracy of 85.71% and a Brier score of 0.13 with isotonic regression calibration. SHAP identified DAS28, visual analog scales (VAS), age, and swollen joint count (SJC) as important characteristics for the prediction of RA remission. We also stratified patients into low-, medium-, and high-risk categories based on model predictions to support follow-up scheduling and treatment prioritization.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eOur framework predicts RA remission before the initiation of bDMARD therapy. It enables personalized care, actionable risk stratification, and optimized resource allocation. Its robustness was validated on two different individual cohort datasets, which highlights its potential for integration into routine clinical workflows.\u003c/p\u003e","manuscriptTitle":"PRECISE-RA: Predicting Remission and StratifyingRisk in Rheumatoid Arthritis Patients Treated withbDMARDs—A Robust Machine Learning Approach","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-02-05 06:10:42","doi":"10.21203/rs.3.rs-5941518/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-05-27T06:42:23+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-05-12T09:01:31+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"30398681908382284173358028582449273930","date":"2025-04-27T06:24:28+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-03-14T21:11:50+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"286579106250758199842705864239254718809","date":"2025-03-11T18:29:04+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"132533197075011938935831754340366110269","date":"2025-03-05T21:25:30+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-02-18T06:33:35+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-02-18T06:21:57+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-02-04T19:54:21+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-02-03T11:29:35+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-02-01T11:21:13+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"dfea73da-361b-4b2e-8734-b22bb1818f0b","owner":[],"postedDate":"February 5th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":43847187,"name":"Health sciences/Rheumatology"},{"id":43847188,"name":"Biological sciences/Biological techniques/Bioinformatics"},{"id":43847189,"name":"Physical sciences/Engineering/Biomedical engineering"}],"tags":[],"updatedAt":"2025-07-07T16:20:35+00:00","versionOfRecord":{"articleIdentity":"rs-5941518","link":"https://doi.org/10.1038/s41598-025-09975-z","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2025-07-04 15:57:21","publishedOnDateReadable":"July 4th, 2025"},"versionCreatedAt":"2025-02-05 06:10:42","video":"","vorDoi":"10.1038/s41598-025-09975-z","vorDoiUrl":"https://doi.org/10.1038/s41598-025-09975-z","workflowStages":[]},"version":"v1","identity":"rs-5941518","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5941518","identity":"rs-5941518","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}