Cost-Sensitive Feature Selection in Medical Diagnostics: Integrating Fuzzy Logic for Optimal Accuracy and Resource Efficiency

Cost-Sensitive Feature Selection in Medical Diagnostics: Integrating Fuzzy Logic for Optimal Accuracy and Resource Efficiency | 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 Cost-Sensitive Feature Selection in Medical Diagnostics: Integrating Fuzzy Logic for Optimal Accuracy and Resource Efficiency Felice Franchini, Giuseppe Pirlo, Lucia Sarcinella, Gianfranco Semeraro This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8268455/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 13 You are reading this latest preprint version Abstract The increasing pressures on healthcare systems highlight the need for resource-efficient and cost-effective decision-making frameworks. This study investigates cost-sensitive feature selection for medical diagnostics, focusing on frailty prediction as a case study. Frailty, characterized by gradual and imprecise clinical changes, is well-suited for fuzzy logic integration, which manages uncertainties in medical data and enhances decision-making. Three methodologies (Combinatorial Optimization, Multi-Objective Optimization, and Mono-Objective Optimization ) are evaluated to balance classification accuracy and resource costs. Combinatorial Optimization achieves high accuracy (> 94%) by exhaustively exploring feature subsets, though at significant computational expense. Multi-Objective Optimization constructs a Pareto-Optimal Frontier, identifying feature subsets with high accuracy (91.9–95%) and varied costs (€120–396.16), offering a versatile decision-making framework for balancing priorities. Mono-Objective Optimization emphasizes computational efficiency and cost minimization, identifying the most affordable subset (€2.3) but with lower accuracy (63.98%). Results underscore the utility of fuzzy logic in defining and optimizing cost-accuracy trade-offs, enabling interpretable and resource-efficient diagnostic tools. Combinatorial and Multi-Objective approaches are suited for scenarios requiring high diagnostic precision, while Mono-Objective methods are appropriate where cost constraints dominate. This work demonstrates how integrating fuzzy principles into AI-driven frameworks enhances decision-making in cost-sensitive healthcare applications. Future research should incorporate temporal costs and explore broader applications in cost-sensitive domains. Refining these methods with advanced fuzzy reasoning can further optimize adaptability and applicability, supporting the development of sustainable, accurate, and interpretable healthcare technologies. Value Based Procurement (VBP) Public Healthcare System Interpretable Machine Learning Models Cost-Accuracy Trade-Off Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 17 May, 2026 Reviews received at journal 11 May, 2026 Reviews received at journal 05 May, 2026 Reviewers agreed at journal 02 May, 2026 Reviews received at journal 30 Apr, 2026 Reviewers agreed at journal 29 Apr, 2026 Reviewers agreed at journal 28 Apr, 2026 Reviewers agreed at journal 28 Apr, 2026 Reviewers agreed at journal 28 Apr, 2026 Reviewers invited by journal 28 Apr, 2026 Editor assigned by journal 09 Dec, 2025 Submission checks completed at journal 08 Dec, 2025 First submitted to journal 03 Dec, 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-8268455","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":635065138,"identity":"f7e17dff-799e-4060-b995-6c7eadbca9b1","order_by":0,"name":"Felice Franchini","email":"","orcid":"","institution":"University of Studies of Bari “Aldo Moro”","correspondingAuthor":false,"prefix":"","firstName":"Felice","middleName":"","lastName":"Franchini","suffix":""},{"id":635065140,"identity":"8f335ede-1882-4127-b7ec-33be14de994b","order_by":1,"name":"Giuseppe Pirlo","email":"","orcid":"","institution":"University of Studies of Bari “Aldo Moro”","correspondingAuthor":false,"prefix":"","firstName":"Giuseppe","middleName":"","lastName":"Pirlo","suffix":""},{"id":635065141,"identity":"d601d5d8-7252-4f26-a26d-7e5344c5c8ec","order_by":2,"name":"Lucia Sarcinella","email":"","orcid":"","institution":"University of Studies of Bari “Aldo Moro”","correspondingAuthor":false,"prefix":"","firstName":"Lucia","middleName":"","lastName":"Sarcinella","suffix":""},{"id":635065142,"identity":"21dca3cd-e450-41e4-ade6-3c21ef6286c3","order_by":3,"name":"Gianfranco Semeraro","email":"data:image/png;base64,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","orcid":"","institution":"University of Studies of Bari “Aldo Moro”","correspondingAuthor":true,"prefix":"","firstName":"Gianfranco","middleName":"","lastName":"Semeraro","suffix":""}],"badges":[],"createdAt":"2025-12-03 09:23:42","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8268455/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8268455/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108806978,"identity":"1b79611f-df6c-46f2-8639-4fc0cf336a81","added_by":"auto","created_at":"2026-05-08 15:29:49","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":634024,"visible":true,"origin":"","legend":"","description":"","filename":"IJCISCostOptimizationFuzzyV4.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8268455/v1_covered_455b6a00-f1b8-4ad1-9c33-f4899e8e260c.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Cost-Sensitive Feature Selection in Medical Diagnostics: Integrating Fuzzy Logic for Optimal Accuracy and Resource Efficiency","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"international-journal-of-computational-intelligence-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [International Journal of Computational Intelligence Systems](https://link.springer.com/journal/44196)","snPcode":"44196","submissionUrl":"https://submission.springernature.com/new-submission/44196/3","title":"International Journal of Computational Intelligence Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Open","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Value Based Procurement (VBP), Public Healthcare System, Interpretable Machine Learning Models, Cost-Accuracy Trade-Off","lastPublishedDoi":"10.21203/rs.3.rs-8268455/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8268455/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe increasing pressures on healthcare systems highlight the need for resource-efficient and cost-effective decision-making frameworks. This study investigates cost-sensitive feature selection for medical diagnostics, focusing on frailty prediction as a case study. Frailty, characterized by gradual and imprecise clinical changes, is well-suited for fuzzy logic integration, which manages uncertainties in medical data and enhances decision-making. Three methodologies (Combinatorial Optimization, Multi-Objective Optimization, and Mono-Objective Optimization ) are evaluated to balance classification accuracy and resource costs. Combinatorial Optimization achieves high accuracy (\u0026gt;\u0026thinsp;94%) by exhaustively exploring feature subsets, though at significant computational expense. Multi-Objective Optimization constructs a Pareto-Optimal Frontier, identifying feature subsets with high accuracy (91.9\u0026ndash;95%) and varied costs (\u0026euro;120\u0026ndash;396.16), offering a versatile decision-making framework for balancing priorities. Mono-Objective Optimization emphasizes computational efficiency and cost minimization, identifying the most affordable subset (\u0026euro;2.3) but with lower accuracy (63.98%). Results underscore the utility of fuzzy logic in defining and optimizing cost-accuracy trade-offs, enabling interpretable and resource-efficient diagnostic tools. Combinatorial and Multi-Objective approaches are suited for scenarios requiring high diagnostic precision, while Mono-Objective methods are appropriate where cost constraints dominate. This work demonstrates how integrating fuzzy principles into AI-driven frameworks enhances decision-making in cost-sensitive healthcare applications. Future research should incorporate temporal costs and explore broader applications in cost-sensitive domains. Refining these methods with advanced fuzzy reasoning can further optimize adaptability and applicability, supporting the development of sustainable, accurate, and interpretable healthcare technologies.\u003c/p\u003e","manuscriptTitle":"Cost-Sensitive Feature Selection in Medical Diagnostics: Integrating Fuzzy Logic for Optimal Accuracy and Resource Efficiency","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-07 09:37:42","doi":"10.21203/rs.3.rs-8268455/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2026-05-17T05:35:17+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-11T11:16:20+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-05T22:32:02+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"224544202183589650483833723977846395346","date":"2026-05-02T22:35:55+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-30T09:35:41+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"173539648803193173191216630477816333451","date":"2026-04-29T15:08:43+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"5681498381398913117730682720604449270","date":"2026-04-28T13:48:02+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"219573622578150900780003518650834698731","date":"2026-04-28T12:16:17+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"107479779141381419787623473657102701759","date":"2026-04-28T11:24:56+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-28T11:10:03+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-12-09T09:49:52+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-12-09T04:32:05+00:00","index":"","fulltext":""},{"type":"submitted","content":"International Journal of Computational Intelligence Systems","date":"2025-12-03T09:19:16+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"international-journal-of-computational-intelligence-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [International Journal of Computational Intelligence Systems](https://link.springer.com/journal/44196)","snPcode":"44196","submissionUrl":"https://submission.springernature.com/new-submission/44196/3","title":"International Journal of Computational Intelligence Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Open","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"9ea3e1c4-a6bc-4ddd-8296-671efff22572","owner":[],"postedDate":"May 7th, 2026","published":true,"recentEditorialEvents":[{"type":"editorInvitedReview","content":"","date":"2026-05-17T05:35:17+00:00","index":23,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-11T11:16:20+00:00","index":22,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-05T22:32:02+00:00","index":21,"fulltext":""},{"type":"reviewerAgreed","content":"224544202183589650483833723977846395346","date":"2026-05-02T22:35:55+00:00","index":20,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-30T09:35:41+00:00","index":17,"fulltext":""},{"type":"reviewerAgreed","content":"173539648803193173191216630477816333451","date":"2026-04-29T15:08:43+00:00","index":16,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-07T09:37:42+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-07 09:37:42","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8268455","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8268455","identity":"rs-8268455","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}