Interpretable Hybrid Metaheuristic Optimization with Iteration-Level Behavior Analysis for Clinical Feature Selection in Heart Disease Prediction

Interpretable Hybrid Metaheuristic Optimization with Iteration-Level Behavior Analysis for Clinical Feature Selection in Heart Disease Prediction | 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 Interpretable Hybrid Metaheuristic Optimization with Iteration-Level Behavior Analysis for Clinical Feature Selection in Heart Disease Prediction Shamsuddeen Adamu, Hitham Alhussian, Said Jadid Abdulkadir, Majdy Mohamed Eltayeb Eltahir, and 7 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9392962/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 10 You are reading this latest preprint version Abstract Cardiovascular disease prediction demands more than accurate models; it requires feature selection processes that are transparent, reproducible, and diagnostically interpretable. Existing wrapper-based metaheuristic selectors typically operate as black boxes, reporting final accuracy without exposing how features were chosen or whether the selection would replicate across data samples. This gap undermines clinical trust and limits the interpretability of any downstream model. We propose WaOA-MRFO, an adaptive hybrid optimizer that couples Walrus Optimization Algorithm exploration with Manta Ray Foraging Optimization exploitation through stagnation-aware diversity control. The framework is accompanied by a structured, iteration-level diagnostic suite that tracks population diversity , convergence behavior, and feature selection stability throughout the search, making the optimization process directly observable rather than opaque. Under 5 × 5 nested cross-validation on the Cleveland heart disease co-hort (n = 261), WaOA-MRFO achieves an AUC of 0.8431 ± 0.0555, statistically equivalent to the all-features baseline (AUC = 0.8474, p = 0.619), while reducing the feature set by 61%. It matches LASSO and recursive feature elimination on identical splits, and significantly outperforms uninformed selection at matched dimensionality (∆AUC = +0.091, p < 0.001). A stable four-feature core (exang, ca, thalch, oldpeak) emerges in more than 70% of folds, and the top two features are selected universally, evidencing reproducible signal extraction. Ablation analysis identifies bit-flip mutation as the sole statistically significant contributor to subset consistency (p = 0.028, Cohens d = 0.531), while the diagnostic suite reveals that the adaptive weight mechanism and diversity injection each serve targeted roles under specific operating conditions. These results establish that competitive predictive performance with feature sets reduced by 61% is achievable without sacrificing decision-theoretic utility. WaOAMRFO hybrid optimization feature selection interpretable machine learning heart disease prediction Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 07 May, 2026 Reviews received at journal 26 Apr, 2026 Reviews received at journal 24 Apr, 2026 Reviewers agreed at journal 21 Apr, 2026 Reviewers agreed at journal 20 Apr, 2026 Reviewers agreed at journal 19 Apr, 2026 Reviewers invited by journal 19 Apr, 2026 Editor assigned by journal 13 Apr, 2026 Submission checks completed at journal 13 Apr, 2026 First submitted to journal 12 Apr, 2026 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-9392962","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":629653546,"identity":"a94ab7e2-3599-4028-8be3-5ef6d4d8171d","order_by":0,"name":"Shamsuddeen Adamu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA0klEQVRIiWNgGAWjYDACCTBpw8PG3sDATIqWNDl+ngOkaTlsLDkjgUgt8rObn2782cacuOHmG8PPBRU2DPzt3Ql4tRjcOWZ2m7eNLXHD7Rxj6Rln0hgkzpzdgF+LRILZbcY2HpAWA2netsNAkVz8WuRnpH+7+bNNAuiwM8a/idLCcCPH7AZvmwHQ+zxmxNlicCOn7DbPuQRgIKeVWfOcSeMh6Begw7bd/FH2HxiVhzff5qmwkeNv7yXgMATgMACRPMQqBwH2B6SoHgWjYBSMghEEAMoXSAavGdZ5AAAAAElFTkSuQmCC","orcid":"","institution":"Universiti Teknologi Petronas","correspondingAuthor":true,"prefix":"","firstName":"Shamsuddeen","middleName":"","lastName":"Adamu","suffix":""},{"id":629653548,"identity":"0872b2b1-6098-4ea7-8534-8948abb86fc4","order_by":1,"name":"Hitham Alhussian","email":"","orcid":"","institution":"Universiti Teknologi Petronas","correspondingAuthor":false,"prefix":"","firstName":"Hitham","middleName":"","lastName":"Alhussian","suffix":""},{"id":629653550,"identity":"374a2c50-2e53-4054-bd04-d66887cb46fb","order_by":2,"name":"Said Jadid Abdulkadir","email":"","orcid":"","institution":"Universiti Teknologi Petronas","correspondingAuthor":false,"prefix":"","firstName":"Said","middleName":"Jadid","lastName":"Abdulkadir","suffix":""},{"id":629653551,"identity":"0c089a9b-3f1b-47ff-b9dd-efb76ac91938","order_by":3,"name":"Majdy Mohamed Eltayeb Eltahir","email":"","orcid":"","institution":"King Khalid University","correspondingAuthor":false,"prefix":"","firstName":"Majdy","middleName":"Mohamed Eltayeb","lastName":"Eltahir","suffix":""},{"id":629653553,"identity":"fd981ee8-d5e0-42cd-a5ca-2d9ff5db27c3","order_by":4,"name":"Sallam O.F. Khairy","email":"","orcid":"","institution":"University of Nizwa","correspondingAuthor":false,"prefix":"","firstName":"Sallam","middleName":"O.F.","lastName":"Khairy","suffix":""},{"id":629653555,"identity":"68f131bf-ea78-4cbb-91d8-0f36fc550e6f","order_by":5,"name":"Gasim Hyder","email":"","orcid":"","institution":"University of Nizwa","correspondingAuthor":false,"prefix":"","firstName":"Gasim","middleName":"","lastName":"Hyder","suffix":""},{"id":629653556,"identity":"f410529c-8ce4-419f-b9e2-afd4b4042894","order_by":6,"name":"Fakhreldin Ali","email":"","orcid":"","institution":"Universiti Teknologi Petronas","correspondingAuthor":false,"prefix":"","firstName":"Fakhreldin","middleName":"","lastName":"Ali","suffix":""},{"id":629653558,"identity":"42ff62d8-c9b2-4be6-adb3-f7ac4738e417","order_by":7,"name":"Umar Audi Ismaíla","email":"","orcid":"","institution":"Universiti Teknologi Petronas","correspondingAuthor":false,"prefix":"","firstName":"Umar","middleName":"Audi","lastName":"Ismaíla","suffix":""},{"id":629653561,"identity":"66f76906-cecf-4da3-9bef-0c6d2884b611","order_by":8,"name":"Shamsu Abdullahi","email":"","orcid":"","institution":"Universiti Teknologi Petronas","correspondingAuthor":false,"prefix":"","firstName":"Shamsu","middleName":"","lastName":"Abdullahi","suffix":""},{"id":629653562,"identity":"4fc44b64-98cf-41a5-ad53-040c897ba1ff","order_by":9,"name":"Hussaini Mamman","email":"","orcid":"","institution":"Universiti Teknologi Petronas","correspondingAuthor":false,"prefix":"","firstName":"Hussaini","middleName":"","lastName":"Mamman","suffix":""},{"id":629653566,"identity":"8a51e351-e799-4086-afc6-f9571d606d3a","order_by":10,"name":"Mohammed Gamal Ragab","email":"","orcid":"","institution":"Universiti Teknologi Petronas","correspondingAuthor":false,"prefix":"","firstName":"Mohammed","middleName":"Gamal","lastName":"Ragab","suffix":""}],"badges":[],"createdAt":"2026-04-12 09:08:25","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9392962/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9392962/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":107884937,"identity":"8b7e4f28-812a-4aa9-adb7-9daa915816fc","added_by":"auto","created_at":"2026-04-27 09:17:58","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2557809,"visible":true,"origin":"","legend":"","description":"","filename":"5main3April26Final.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9392962/v1_covered_3c12bd3e-ee07-4b84-ae40-4ab9ce4f2fce.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Interpretable Hybrid Metaheuristic Optimization with Iteration-Level Behavior Analysis for Clinical Feature Selection in Heart Disease Prediction","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":"journal-of-king-saud-university-computer-and-information-sciences","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Journal of King Saud University Computer and Information Sciences](https://link.springer.com/journal/44443)","snPcode":"44443","submissionUrl":"https://submission.springernature.com/new-submission/44443/3","title":"Journal of King Saud University Computer and Information Sciences","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Open","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"WaOAMRFO, hybrid optimization, feature selection, interpretable machine learning, heart disease prediction","lastPublishedDoi":"10.21203/rs.3.rs-9392962/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9392962/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Cardiovascular disease prediction demands more than accurate models; it requires feature selection processes that are transparent, reproducible, and diagnostically interpretable. Existing wrapper-based metaheuristic selectors typically operate as black boxes, reporting final accuracy without exposing how features were chosen or whether the selection would replicate across data samples. This gap undermines clinical trust and limits the interpretability of any downstream model. We propose WaOA-MRFO, an adaptive hybrid optimizer that couples Walrus Optimization Algorithm exploration with Manta Ray Foraging Optimization exploitation through stagnation-aware diversity control. The framework is accompanied by a structured, iteration-level diagnostic suite that tracks population diversity , convergence behavior, and feature selection stability throughout the search, making the optimization process directly observable rather than opaque. Under 5 × 5 nested cross-validation on the Cleveland heart disease co-hort (n = 261), WaOA-MRFO achieves an AUC of 0.8431 ± 0.0555, statistically equivalent to the all-features baseline (AUC = 0.8474, p = 0.619), while reducing the feature set by 61%. It matches LASSO and recursive feature elimination on identical splits, and significantly outperforms uninformed selection at matched dimensionality (∆AUC = +0.091, p \u003c 0.001). A stable four-feature core (exang, ca, thalch, oldpeak) emerges in more than 70% of folds, and the top two features are selected universally, evidencing reproducible signal extraction. Ablation analysis identifies bit-flip mutation as the sole statistically significant contributor to subset consistency (p = 0.028, Cohens d = 0.531), while the diagnostic suite reveals that the adaptive weight mechanism and diversity injection each serve targeted roles under specific operating conditions. These results establish that competitive predictive performance with feature sets reduced by 61% is achievable without sacrificing decision-theoretic utility.","manuscriptTitle":"Interpretable Hybrid Metaheuristic Optimization with Iteration-Level Behavior Analysis for Clinical Feature Selection in Heart Disease Prediction","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-27 09:17:27","doi":"10.21203/rs.3.rs-9392962/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-05-07T05:43:56+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-26T16:32:14+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-24T18:25:38+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"34382960488175519688312223915945805123","date":"2026-04-22T00:43:11+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"35066637952978594217483269543879084901","date":"2026-04-20T22:01:03+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"299697213954867202091431703719493336372","date":"2026-04-19T20:13:31+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-19T13:41:35+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-04-13T13:00:40+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-04-13T13:00:29+00:00","index":"","fulltext":""},{"type":"submitted","content":"Journal of King Saud University Computer and Information Sciences","date":"2026-04-12T08:57:23+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"journal-of-king-saud-university-computer-and-information-sciences","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Journal of King Saud University Computer and Information Sciences](https://link.springer.com/journal/44443)","snPcode":"44443","submissionUrl":"https://submission.springernature.com/new-submission/44443/3","title":"Journal of King Saud University Computer and Information Sciences","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Open","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"25145e0f-d25a-4632-ac72-5b190d47c78d","owner":[],"postedDate":"April 27th, 2026","published":true,"recentEditorialEvents":[{"type":"decision","content":"Revision requested","date":"2026-05-07T05:43:56+00:00","index":"","fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-16T04:24:01+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-27 09:17:27","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9392962","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9392962","identity":"rs-9392962","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}