Unified approach for Accurate Heart Disease Prediction using Machine Learning Techniques

Unified approach for Accurate Heart Disease Prediction using Machine Learning Techniques | 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 Unified approach for Accurate Heart Disease Prediction using Machine Learning Techniques Raghavendra Rao RV, Ram Mohan Reddy Ch, Hemanth K, Hruthik Chavan D This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7596820/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 04 Mar, 2026 Read the published version in Discover Computing → Version 1 posted 18 You are reading this latest preprint version Abstract Cardiovascular diseases (CVDs) account for a large share of worldwide morbidity, disability, and premature mortality, posing a critical challenge to public health. The risk and severity of these conditions can be greatly reduced by adopting early identification and proactive treatment strategies. As part of this effort, the main focus has been to estimate the probability that an individual will experience major cardiovascular events. Machine learning offers a promising alternative to conventional risk models, enhancing the accuracy of health outcome predictions. A machine learning pipeline that can predict heart disease using the XGBoost algorithm, advanced feature selection techniques, and automated hyperparameter tuning with Optuna is presented in this research. Initially, important features were derived using XGBoost-based importance scores, which improved model interpretability and reduced dimensionality. Optuna's Tree-structured Parzen Estimator (TPE) sampler was used to efficiently optimize the classification model by exploring the hyperparameter space. To tackle class imbalance, SMOTE was integrated into the pipeline. The final model outperformed the test dataset, proving 99.02% accuracy, 99.813% precision, 100% recall, 99.05% F1-score, and ROC-AUC of 0.9998. The dataset, which was obtained has 1,025 instances from the Cleveland, Hungary, Switzerland, and Long Beach V databases, and each has 14 features. The results highlight that integrating ensemble learning, feature selection, and hyperparameter tuning enhances the reliability of predictive models for cardiovascular disease detection. Cardiovascular Disease XGBoost Feature Selection Optuna Hyperparameter Optimisation SMOTE Tree-structured Parzen Estimator (TPE) Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 04 Mar, 2026 Read the published version in Discover Computing → Version 1 posted Editorial decision: Revision requested 30 Nov, 2025 Reviews received at journal 26 Nov, 2025 Reviews received at journal 19 Nov, 2025 Reviewers agreed at journal 19 Nov, 2025 Reviews received at journal 19 Nov, 2025 Reviewers agreed at journal 19 Nov, 2025 Reviewers agreed at journal 16 Nov, 2025 Reviews received at journal 16 Nov, 2025 Reviewers agreed at journal 14 Nov, 2025 Reviews received at journal 07 Nov, 2025 Reviews received at journal 03 Nov, 2025 Reviewers agreed at journal 31 Oct, 2025 Reviewers agreed at journal 30 Oct, 2025 Reviewers agreed at journal 30 Oct, 2025 Reviewers invited by journal 14 Oct, 2025 Editor assigned by journal 19 Sep, 2025 Submission checks completed at journal 19 Sep, 2025 First submitted to journal 12 Sep, 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-7596820","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":534303422,"identity":"d373148a-7d51-47c8-a4bb-c332009760b3","order_by":0,"name":"Raghavendra Rao RV","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAvUlEQVRIiWNgGAWjYPACmwQ4k41ILWmkazmcQEgFApjPPsC64UfN+Tzd/sMPHzDU2DHwSTfg1yJzLoHtZs+x28VmN9KMDRiOJTOwyRzAr0WCh4HtNhAlbrvBwybBwHaAgU2CgCMhWv6dS9x2/gz7D4Z/xGphbDuQuO1ADhsDkEGMFsa2m719yWC/SCT2JfMQoYX52I0f3+zyzM4ffvjhwzc7OfkZBLQwMDA2INhAxTyE1I+CUTAKRsEoIAIAACdEPIFq81owAAAAAElFTkSuQmCC","orcid":"","institution":"B.M.S.College of Engineering","correspondingAuthor":true,"prefix":"","firstName":"Raghavendra","middleName":"Rao","lastName":"RV","suffix":""},{"id":534303423,"identity":"0822f34a-6416-47d2-99cc-ba01cae9631d","order_by":1,"name":"Ram Mohan Reddy Ch","email":"","orcid":"","institution":"B.M.S.College of Engineering","correspondingAuthor":false,"prefix":"","firstName":"Ram","middleName":"Mohan Reddy","lastName":"Ch","suffix":""},{"id":534303424,"identity":"078b41e6-0b93-4a26-bc3b-231e66192546","order_by":2,"name":"Hemanth K","email":"","orcid":"","institution":"B.M.S.College of Engineering","correspondingAuthor":false,"prefix":"","firstName":"Hemanth","middleName":"","lastName":"K","suffix":""},{"id":534303425,"identity":"ba0fe5b4-385a-4c4d-883f-0bd1adcf7fcb","order_by":3,"name":"Hruthik Chavan D","email":"","orcid":"","institution":"B.M.S.College of Engineering","correspondingAuthor":false,"prefix":"","firstName":"Hruthik","middleName":"Chavan","lastName":"D","suffix":""}],"badges":[],"createdAt":"2025-09-12 05:53:10","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7596820/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7596820/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s10791-026-09979-x","type":"published","date":"2026-03-04T15:59:53+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":94600639,"identity":"85d7ef8f-8835-4cac-8b2d-0722e280a5ce","added_by":"auto","created_at":"2025-10-28 19:17:34","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":262970,"visible":true,"origin":"","legend":"","description":"","filename":"UnifiedapproachforAccurateHeartDiseasePredictionusingMachineLearningTechniques18.09.2025.docx","url":"https://assets-eu.researchsquare.com/files/rs-7596820/v1/e875aa5a16c90dc7752912c4.docx"},{"id":94600662,"identity":"2102a168-efb4-4356-a839-c0a2614fcc9e","added_by":"auto","created_at":"2025-10-28 19:17:39","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6370,"visible":true,"origin":"","legend":"","description":"","filename":"4082e579e0654ced9259ac8697403a98.json","url":"https://assets-eu.researchsquare.com/files/rs-7596820/v1/16ee2d456b939d3168406a8a.json"},{"id":94600707,"identity":"e946aad6-3928-40d4-84a3-578c6422678b","added_by":"auto","created_at":"2025-10-28 19:17:56","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":81398,"visible":true,"origin":"","legend":"","description":"","filename":"4082e579e0654ced9259ac8697403a981enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7596820/v1/0917cebc854bac29fbf5ed81.xml"},{"id":94600664,"identity":"b1778698-76bf-4f61-a309-57bab34a450f","added_by":"auto","created_at":"2025-10-28 19:17:39","extension":"jpeg","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":238220,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7596820/v1/704a8f1c3c0d1e4f19c1006c.jpeg"},{"id":94600702,"identity":"47135e82-1ff2-41ca-9035-b3063834351f","added_by":"auto","created_at":"2025-10-28 19:17:54","extension":"png","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":15858,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7596820/v1/8affed9e17b834d2ae7e2431.png"},{"id":94600641,"identity":"356908d0-0c2f-4387-85be-a22c9f88c36e","added_by":"auto","created_at":"2025-10-28 19:17:34","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":24708,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7596820/v1/37cccf275005068cb1b42b29.png"},{"id":94600660,"identity":"b571a06f-66a6-450b-9bbd-8a9e9e85a3ef","added_by":"auto","created_at":"2025-10-28 19:17:39","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":14111,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7596820/v1/2f56b3893777a203ee55fab5.png"},{"id":94600764,"identity":"76ee8ba0-28c5-4e53-bab8-3888be0d6a73","added_by":"auto","created_at":"2025-10-28 19:17:57","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":56212,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7596820/v1/cf51e797fdeb4e81d0e0f5ec.png"},{"id":94600773,"identity":"4d06dcdf-d34a-4e96-a1f7-3e17061ffd02","added_by":"auto","created_at":"2025-10-28 19:17:58","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":45864,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7596820/v1/5f16e8f9cdf188516d91b39a.png"},{"id":94600774,"identity":"d3ddc652-08d1-47e8-8d38-7a30f9c6735a","added_by":"auto","created_at":"2025-10-28 19:17:58","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":36955,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7596820/v1/ce324521480cd3b0c6416a15.png"},{"id":94600661,"identity":"0f66084b-db96-4232-8185-798c1a763c82","added_by":"auto","created_at":"2025-10-28 19:17:39","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4985,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7596820/v1/f65339cd9799437047e28940.png"},{"id":94600663,"identity":"ffe32127-b413-44f4-9ce1-e1df837739c8","added_by":"auto","created_at":"2025-10-28 19:17:39","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":11609,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7596820/v1/ae595b13eb6d825b4aba32e7.png"},{"id":94600665,"identity":"2eea9559-777c-40b4-a557-7758011260c4","added_by":"auto","created_at":"2025-10-28 19:17:41","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5992,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7596820/v1/6ff610c9b295fae1e7c80b56.png"},{"id":94600709,"identity":"a1071236-1d53-48cb-8967-8e9452161757","added_by":"auto","created_at":"2025-10-28 19:17:57","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":12645,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7596820/v1/80d4280519b90c5984d97cce.png"},{"id":94600776,"identity":"33a344a2-4221-4132-b7dc-11db7cb23855","added_by":"auto","created_at":"2025-10-28 19:17:58","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":10219,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7596820/v1/8c35b89350063aaa682a9e61.png"},{"id":94600752,"identity":"7f415eea-16d5-4a9d-bcf1-081df3a958b8","added_by":"auto","created_at":"2025-10-28 19:17:57","extension":"xml","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":81154,"visible":true,"origin":"","legend":"","description":"","filename":"4082e579e0654ced9259ac8697403a981structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7596820/v1/4f50541eb5dfb254346df48a.xml"},{"id":94600695,"identity":"ac051e83-4186-47c5-9d95-c286ec5fa135","added_by":"auto","created_at":"2025-10-28 19:17:53","extension":"html","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":89315,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7596820/v1/33e44a89c7a8eeadee160dc8.html"},{"id":104250830,"identity":"51b5bfce-5609-422c-9bea-c8889ea32f91","added_by":"auto","created_at":"2026-03-09 16:09:29","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":481075,"visible":true,"origin":"","legend":"","description":"","filename":"UnifiedapproachforAccurateHeartDiseasePredictionusingMachineLearningTechniques18.09.2025.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7596820/v1_covered_631d8fa5-9a0e-42f2-9e89-a0343951ce20.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Unified approach for Accurate Heart Disease Prediction using Machine Learning Techniques","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":"discover-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Discover Computing](https://link.springer.com/journal/10791)","snPcode":"10791","submissionUrl":"https://submission.springernature.com/new-submission/10791/3","title":"Discover Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Discover Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Cardiovascular Disease, XGBoost, Feature Selection, Optuna, Hyperparameter Optimisation, SMOTE, Tree-structured Parzen Estimator (TPE)","lastPublishedDoi":"10.21203/rs.3.rs-7596820/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7596820/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eCardiovascular diseases (CVDs) account for a large share of worldwide morbidity, disability, and premature mortality, posing a critical challenge to public health. The risk and severity of these conditions can be greatly reduced by adopting early identification and proactive treatment strategies. As part of this effort, the main focus has been to estimate the probability that an individual will experience major cardiovascular events. Machine learning offers a promising alternative to conventional risk models, enhancing the accuracy of health outcome predictions. A machine learning pipeline that can predict heart disease using the XGBoost algorithm, advanced feature selection techniques, and automated hyperparameter tuning with Optuna is presented in this research. Initially, important features were derived using XGBoost-based importance scores, which improved model interpretability and reduced dimensionality. Optuna's Tree-structured Parzen Estimator (TPE) sampler was used to efficiently optimize the classification model by exploring the hyperparameter space. To tackle class imbalance, SMOTE was integrated into the pipeline. The final model outperformed the test dataset, proving 99.02% accuracy, 99.813% precision, 100% recall, 99.05% F1-score, and ROC-AUC of 0.9998. The dataset, which was obtained has 1,025 instances from the Cleveland, Hungary, Switzerland, and Long Beach V databases, and each has 14 features. The results highlight that integrating ensemble learning, feature selection, and hyperparameter tuning enhances the reliability of predictive models for cardiovascular disease detection.\u003c/p\u003e","manuscriptTitle":"Unified approach for Accurate Heart Disease Prediction using Machine Learning Techniques","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-28 19:12:59","doi":"10.21203/rs.3.rs-7596820/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-12-01T04:18:07+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-11-26T10:19:34+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-11-19T17:01:08+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"73654851669661628589676612442712744662","date":"2025-11-19T16:50:30+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-11-19T10:55:33+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"17146847748181192229535660645652367096","date":"2025-11-19T09:56:07+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"30695232755569225718260091494673736939","date":"2025-11-16T13:00:57+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-11-16T10:46:18+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"281319265707684417203765872072973701486","date":"2025-11-14T10:10:39+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-11-07T10:03:58+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-11-03T09:25:23+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"234382560172901941247328836521667912222","date":"2025-10-31T04:40:24+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"37727230846849843468210405438750234893","date":"2025-10-30T16:49:54+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"254287727983407192674634690579895883414","date":"2025-10-30T16:25:37+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-10-14T06:00:02+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-09-19T06:54:58+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-09-19T06:53:50+00:00","index":"","fulltext":""},{"type":"submitted","content":"Discover Computing","date":"2025-09-12T05:37:44+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"discover-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Discover Computing](https://link.springer.com/journal/10791)","snPcode":"10791","submissionUrl":"https://submission.springernature.com/new-submission/10791/3","title":"Discover Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Discover Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"ffa2594b-d773-42b9-8b88-7a7678209ad7","owner":[],"postedDate":"October 28th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2026-03-09T16:05:51+00:00","versionOfRecord":{"articleIdentity":"rs-7596820","link":"https://doi.org/10.1007/s10791-026-09979-x","journal":{"identity":"discover-computing","isVorOnly":false,"title":"Discover Computing"},"publishedOn":"2026-03-04 15:59:53","publishedOnDateReadable":"March 4th, 2026"},"versionCreatedAt":"2025-10-28 19:12:59","video":"","vorDoi":"10.1007/s10791-026-09979-x","vorDoiUrl":"https://doi.org/10.1007/s10791-026-09979-x","workflowStages":[]},"version":"v1","identity":"rs-7596820","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7596820","identity":"rs-7596820","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}