An entropy weighted hybrid feature selection approach for heart disease prediction using machine learning

An entropy weighted hybrid feature selection approach for heart disease prediction using machine learning | 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 An entropy weighted hybrid feature selection approach for heart disease prediction using machine learning Rais Shaikh, Avinash Sharma This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9230963/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 12 You are reading this latest preprint version Abstract Heart disease still maintains a spot on the top of the list of leading causes of mortality worldwide. Predicting the occurrence of heart disease at early stages will greatly impact the effectiveness of clinical practices and ultimately improve patient outcomes. The authors present a new tool called the Entropy-Weighted Hybrid Feature Selector (EWHFS); it is a mathematically based multi-criteria feature evaluation architecture that is specifically designed for high-dimensional, noisy biomedical data. The EWHFS framework integrates three separate but complementary types of discriminant signals (entropy-based Information Gain (IG), Fisher-ratio Class Separability (FS) and an Anti-Correlation Index (ACI) calculated from absolute Pearson dependencies) into a single weighted optimization solution. First, each of these three metrics is normalized through entropy-based scaling to minimize dominance bias and to allow for probabilistic comparison of results. Next, a composite hybrid feature score is calculated using a constrained linear weighting approach that maximizes mutual information, inter-class divergence, and redundancy representational penalty simultaneously. This constrained linear weighted model for the hybrid feature score optimizes a tri-objective function under the boundaries of monotonicity, additivity and bounded relevance. The use of EWHFS in the UCI Heart Disease dataset confirms that this method provides a small, but complete and very informative subset of features from which to build classifiers, thus achieving the best possible balance between stability and overfitting of classifiers. The architecture's complexity is O(n·m), making it easier to apply to large-scale clinical prediction pipes. The mathematically formulated weighting scheme used in EWHFS makes it a stronger competitor compared to classical filtering, wrapper, and embedded feature selections methods, due in part to its strength in handling collinearity issues. Heart Disease Prediction Entropy-Weighted Hybrid Feature Selection (EWHFS) Information Gain (IG) Fisher-ratio class separability (FS) Anti-Correlation Index (ACI) UCI Dataset Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 12 May, 2026 Reviews received at journal 10 May, 2026 Reviews received at journal 06 May, 2026 Reviewers agreed at journal 04 May, 2026 Reviewers agreed at journal 04 May, 2026 Reviewers agreed at journal 02 May, 2026 Reviewers agreed at journal 29 Apr, 2026 Reviewers invited by journal 29 Apr, 2026 Editor assigned by journal 19 Apr, 2026 Editor invited by journal 19 Apr, 2026 Submission checks completed at journal 18 Apr, 2026 First submitted to journal 18 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-9230963","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":635234910,"identity":"62ba8d14-5e4a-4ef7-acae-b8d4761bb285","order_by":0,"name":"Rais Shaikh","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA70lEQVRIiWNgGAWjYDACCQaGg40NDAxsDMwHHwD5PHwkaGFLNgBpYSNGCyNIC1CxmQSIIqhFfnbzw4Mzd9yT5+M/Y1b5NcdOBujCh49u4NFicOeYwcGNZ4oN2yTSym7LbksGOozN2DgHnxaJBIODD9sSGNskmLfdltzGDNTCwyaNT4v8jPQPIC32bfwHzIolt9UT1sJwIwfosLaExDaGFDPGj9sOE9ZicCOn4ODMtoRkoF+SpRm3HedhYybgF6DDNn/sbUuwnd9/+ODHn9uq7fnZmx8+xuswZMDMAyaJVQ4CjD9IUT0KRsEoGAUjBgAAllRLJq2Ql3UAAAAASUVORK5CYII=","orcid":"","institution":"Oriental University ,Indore (M.P.)","correspondingAuthor":true,"prefix":"","firstName":"Rais","middleName":"","lastName":"Shaikh","suffix":""},{"id":635234911,"identity":"6764acd2-4a65-462c-b4a7-ff9f60b0973d","order_by":1,"name":"Avinash Sharma","email":"","orcid":"","institution":"Oriental University ,Indore (M.P.)","correspondingAuthor":false,"prefix":"","firstName":"Avinash","middleName":"","lastName":"Sharma","suffix":""}],"badges":[],"createdAt":"2026-03-26 07:54:36","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9230963/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9230963/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108806486,"identity":"c51f7ff3-2aa4-4c28-88e0-61d2e188d900","added_by":"auto","created_at":"2026-05-08 15:28:42","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":600384,"visible":true,"origin":"","legend":"","description":"","filename":"HeartDiseasePredictionUsingMachineLearning.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9230963/v1_covered_c6b6ea0d-a7ce-47cd-8283-339f0a6fb4c7.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"An entropy weighted hybrid feature selection approach for heart disease prediction using machine learning","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":"discover-artificial-intelligence","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"diai","sideBox":"Learn more about [Discover Artificial Intelligence](https://www.springer.com/44163)","snPcode":"","submissionUrl":"","title":"Discover Artificial Intelligence","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Discover Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Heart Disease Prediction, Entropy-Weighted Hybrid Feature Selection (EWHFS), Information Gain (IG), Fisher-ratio class separability (FS), Anti-Correlation Index (ACI), UCI Dataset","lastPublishedDoi":"10.21203/rs.3.rs-9230963/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9230963/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eHeart disease still maintains a spot on the top of the list of leading causes of mortality worldwide. Predicting the occurrence of heart disease at early stages will greatly impact the effectiveness of clinical practices and ultimately improve patient outcomes. The authors present a new tool called the Entropy-Weighted Hybrid Feature Selector (EWHFS); it is a mathematically based multi-criteria feature evaluation architecture that is specifically designed for high-dimensional, noisy biomedical data. The EWHFS framework integrates three separate but complementary types of discriminant signals (entropy-based Information Gain (IG), Fisher-ratio Class Separability (FS) and an Anti-Correlation Index (ACI) calculated from absolute Pearson dependencies) into a single weighted optimization solution. First, each of these three metrics is normalized through entropy-based scaling to minimize dominance bias and to allow for probabilistic comparison of results. Next, a composite hybrid feature score is calculated using a constrained linear weighting approach that maximizes mutual information, inter-class divergence, and redundancy representational penalty simultaneously. This constrained linear weighted model for the hybrid feature score optimizes a tri-objective function under the boundaries of monotonicity, additivity and bounded relevance. The use of EWHFS in the UCI Heart Disease dataset confirms that this method provides a small, but complete and very informative subset of features from which to build classifiers, thus achieving the best possible balance between stability and overfitting of classifiers. The architecture's complexity is O(n\u0026middot;m), making it easier to apply to large-scale clinical prediction pipes. The mathematically formulated weighting scheme used in EWHFS makes it a stronger competitor compared to classical filtering, wrapper, and embedded feature selections methods, due in part to its strength in handling collinearity issues.\u003c/p\u003e","manuscriptTitle":"An entropy weighted hybrid feature selection approach for heart disease prediction using machine learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-08 05:46:14","doi":"10.21203/rs.3.rs-9230963/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2026-05-12T14:52:35+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-10T10:45:31+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-06T06:11:47+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"320105622141611460060970810277642630231","date":"2026-05-04T13:57:27+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"164418575843317377212194696022769528123","date":"2026-05-04T10:40:30+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"173065228494259624638978021290954675020","date":"2026-05-02T18:13:19+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"271839167979448894069416859422802106520","date":"2026-04-29T10:52:27+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-29T10:19:13+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-04-20T00:33:47+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-04-20T00:22:01+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-04-18T10:07:54+00:00","index":"","fulltext":""},{"type":"submitted","content":"Discover Artificial Intelligence","date":"2026-04-18T10:02:09+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"discover-artificial-intelligence","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"diai","sideBox":"Learn more about [Discover Artificial Intelligence](https://www.springer.com/44163)","snPcode":"","submissionUrl":"","title":"Discover Artificial Intelligence","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Discover Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"6fc90437-6c84-417a-a93e-b17327b20785","owner":[],"postedDate":"May 8th, 2026","published":true,"recentEditorialEvents":[{"type":"editorInvitedReview","content":"","date":"2026-05-12T14:52:35+00:00","index":59,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-10T10:45:31+00:00","index":58,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-06T06:11:47+00:00","index":57,"fulltext":""},{"type":"reviewerAgreed","content":"320105622141611460060970810277642630231","date":"2026-05-04T13:57:27+00:00","index":56,"fulltext":""},{"type":"reviewerAgreed","content":"164418575843317377212194696022769528123","date":"2026-05-04T10:40:30+00:00","index":53,"fulltext":""},{"type":"reviewerAgreed","content":"173065228494259624638978021290954675020","date":"2026-05-02T18:13:19+00:00","index":51,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-08T05:46:14+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-08 05:46:14","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9230963","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9230963","identity":"rs-9230963","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}