Disease screening using Artificial Intelligence

Disease screening using Artificial Intelligence | 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 Disease screening using Artificial Intelligence Auba Fuster-Palà, Francisco Luna-Perejón, Manuel Domínguez-Morales This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3969817/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract This work presents a disease detection classifier based on symptoms encoded by their severity. This model is presented as part of the solution to the saturation of the healthcare system, aiding in the initial screening stage. An open-source dataset was used, which underwent pre-processing and served as the data source to train and test various machine learning models, including SVM, Random Forests, KNN, and ANNs. A 3-phase optimization process is developed to obtain the best classifier: first, the dataset is pre-processed; secondly, a grid search is performed with several hypermarameters variations to each classifier; and, finally, the best models obtained are subjected to an additional filtering processes. The best-results model, selected based on the performance and the execution time, is a KNN with 2 neighbors, which achieves an accuracy and F1 score of over 98%. These results demonstrate the effectiveness and improvement of the evaluated models compared to previous studies, particularly in terms of accuracy. Although the ANN model has a longer execution time compared to KNN, it is retained in the work due to its potential to handle more complex datasets in a real clinical context. Disease screening Hospital overcrowding Machine Learning Artificial Intelligence Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted 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-3969817","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":274198411,"identity":"dccb9898-92d5-46b0-83c3-74b0900df227","order_by":0,"name":"Auba Fuster-Palà","email":"","orcid":"","institution":"Universidad de Sevilla","correspondingAuthor":false,"prefix":"","firstName":"Auba","middleName":"","lastName":"Fuster-Palà","suffix":""},{"id":274198412,"identity":"8f930a9d-c387-4ea3-9f39-0b67cd7f5783","order_by":1,"name":"Francisco Luna-Perejón","email":"","orcid":"","institution":"Universidad de Sevilla","correspondingAuthor":false,"prefix":"","firstName":"Francisco","middleName":"","lastName":"Luna-Perejón","suffix":""},{"id":274198413,"identity":"679cd1d6-ae81-4742-a71a-123029723cf9","order_by":2,"name":"Manuel Domínguez-Morales","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAxElEQVRIiWNgGAWjYFCCAwYMDAZgFuMDkrUwGxBrDVwhmwRR6nUbD298dKPgjt2G4+3Pqnn+MMjJNxDQYnbgWLFxjsGz5A1nDqTd5m1jMDY4QFDLGTPpHIPDyQY3Eo7d5m1gSNxAyGEILfcfthUDHVY/n7DDIFrsDG4wszHzsDEkMBB2GNgvhxMkz6QxS85tkzDcQFDLjcMbH+f8OWzPd/z4ww9v/tjIEwwxBgmIoYlQhcREDT9ErT0RSkfBKBgFo2CkAgD+fUaeMO93ZQAAAABJRU5ErkJggg==","orcid":"","institution":"Universidad de Sevilla","correspondingAuthor":true,"prefix":"","firstName":"Manuel","middleName":"","lastName":"Domínguez-Morales","suffix":""}],"badges":[],"createdAt":"2024-02-19 11:17:44","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3969817/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3969817/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":51609720,"identity":"56383464-f3db-4f39-9769-0d8095b4162f","added_by":"auto","created_at":"2024-02-25 19:24:55","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1082236,"visible":true,"origin":"","legend":"","description":"","filename":"JournalofMedicalSystemsDiseaseScreeningAI.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3969817/v1_covered_0bfa4333-cdee-40bb-931d-3295214b1f8d.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Disease screening using Artificial Intelligence","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"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":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Disease screening, Hospital overcrowding, Machine Learning, Artificial Intelligence","lastPublishedDoi":"10.21203/rs.3.rs-3969817/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3969817/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"This work presents a disease detection classifier based on symptoms encoded by their severity. This model is presented as part of the solution to the saturation of the healthcare system, aiding in the initial screening stage. An open-source dataset was used, which underwent pre-processing and served as the data source to train and test various machine learning models, including SVM, Random Forests, KNN, and ANNs. A 3-phase optimization process is developed to obtain the best classifier: first, the dataset is pre-processed; secondly, a grid search is performed with several hypermarameters variations to each classifier; and, finally, the best models obtained are subjected to an additional filtering processes. The best-results model, selected based on the performance and the execution time, is a KNN with 2 neighbors, which achieves an accuracy and F1 score of over 98\\%. These results demonstrate the effectiveness and improvement of the evaluated models compared to previous studies, particularly in terms of accuracy. Although the ANN model has a longer execution time compared to KNN, it is retained in the work due to its potential to handle more complex datasets in a real clinical context.","manuscriptTitle":"Disease screening using Artificial Intelligence","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-02-23 10:34:52","doi":"10.21203/rs.3.rs-3969817/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"3052ee27-1b5e-44e0-a861-5a4814858ed7","owner":[],"postedDate":"February 23rd, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-02-25T19:16:44+00:00","versionOfRecord":[],"versionCreatedAt":"2024-02-23 10:34:52","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-3969817","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3969817","identity":"rs-3969817","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}