Early Prediction of Lung Cancer Employing Machine Learning: A Comprehensive Approach

Early Prediction of Lung Cancer Employing Machine Learning: A Comprehensive Approach | 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 Early Prediction of Lung Cancer Employing Machine Learning: A Comprehensive Approach Yusupha Sinjanka, Veerpal Kaur, Usman Ibrahim Musa, Karandeep Kaur This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3658489/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 The human lungs, crucial for supplying oxygen, are vulnerable to diseases such as lung cancer, a leading cause of mortality. Timely prediction of lung cancer is essential to enable early intervention by healthcare professionals, enhancing patient outcomes and saving lives. This study introduces a comprehensive Machine Learning (ML) model designed to predict lung cancer at an early stage, utilizing a dataset sourced from Kaggle. Built on the Random Forest algorithm, the model assesses a diverse set of characteristics and variables, including gender, age, and exposure to various environments and lifestyles. It accurately identifies individuals at a higher risk of developing early-stage lung cancer, facilitating prompt intervention and personalized treatment strategies. Key evaluation metrics demonstrating the model's effectiveness include precision, F1 score, recall, and accuracy. The findings indicate a model accuracy of approximately 97.9%, underscoring its potential as a valuable tool for enhancing the early detection of lung cancer. Lung Cancer Random Forest Algorithm Machine Learning Full Text 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-3658489","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":334922514,"identity":"b2425722-1686-4445-8595-77ddd7a70d68","order_by":0,"name":"Yusupha Sinjanka","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA/UlEQVRIiWNgGAWjYLACxgYGBjb2xoYDCQY1dvzsICEDIrTw8RxuPPCg4FiyZDOxWuQk0psPPvjAzLjhMAHVBjfSn0kX7rBjYGNIBDmMjdn4MO8xCYaCO3i05JhJzzyTDNRyEKRFhs/sMF+aBIPBM3xa2KR525gZ2BgbIbaYHeYxA2rB7Tyww3jb6hnYmBlBWpgZNzcT1JJgBtRymIGNDaplAzMBLZJn3hhbz2w7zsPGA9ZyLFniMF+yRQIeLXzH0x/eLmyrlpOf//zxxx9/gFHZ3nvwxoc/uLUoHGBgYAbSPEhiQHYCTg0MDPINEC3IgAebwlEwCkbBKBjBAACNjFN2MZTKiAAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0009-0005-8836-9391","institution":"Lovely Professional University","correspondingAuthor":true,"prefix":"","firstName":"Yusupha","middleName":"","lastName":"Sinjanka","suffix":""},{"id":334922515,"identity":"01c4c37e-fc86-4793-9a05-e41f7d5bdfc6","order_by":1,"name":"Veerpal Kaur","email":"","orcid":"","institution":"Lovely Professional University","correspondingAuthor":false,"prefix":"","firstName":"Veerpal","middleName":"","lastName":"Kaur","suffix":""},{"id":334922516,"identity":"e801eb07-94cc-4206-bb74-1b226c2a47e6","order_by":2,"name":"Usman Ibrahim Musa","email":"","orcid":"","institution":"Lovely Professional University","correspondingAuthor":false,"prefix":"","firstName":"Usman","middleName":"Ibrahim","lastName":"Musa","suffix":""},{"id":334922517,"identity":"1dc1d964-4825-4651-8f8b-2353e74b5457","order_by":3,"name":"Karandeep Kaur","email":"","orcid":"","institution":"Lovely Professional University","correspondingAuthor":false,"prefix":"","firstName":"Karandeep","middleName":"","lastName":"Kaur","suffix":""}],"badges":[],"createdAt":"2023-11-24 10:10:59","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3658489/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3658489/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":78339983,"identity":"93ece971-fe37-4411-ae85-0f61ae8ad656","added_by":"auto","created_at":"2025-03-12 08:37:07","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":742070,"visible":true,"origin":"","legend":"","description":"","filename":"LungCancerRFR.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3658489/v1_covered_21d01010-5ef6-4ac9-a780-a8ed85407b34.pdf"}],"financialInterests":"","formattedTitle":"Early Prediction of Lung Cancer Employing Machine Learning: A Comprehensive Approach","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":"Lung Cancer, Random Forest Algorithm, Machine Learning","lastPublishedDoi":"10.21203/rs.3.rs-3658489/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3658489/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The human lungs, crucial for supplying oxygen, are vulnerable to diseases such as lung cancer, a leading cause of mortality. Timely prediction of lung cancer is essential to enable early intervention by healthcare professionals, enhancing patient outcomes and saving lives. This study introduces a comprehensive Machine Learning (ML) model designed to predict lung cancer at an early stage, utilizing a dataset sourced from Kaggle. Built on the Random Forest algorithm, the model assesses a diverse set of characteristics and variables, including gender, age, and exposure to various environments and lifestyles. It accurately identifies individuals at a higher risk of developing early-stage lung cancer, facilitating prompt intervention and personalized treatment strategies. Key evaluation metrics demonstrating the model's effectiveness include precision, F1 score, recall, and accuracy. The findings indicate a model accuracy of approximately 97.9%, underscoring its potential as a valuable tool for enhancing the early detection of lung cancer.","manuscriptTitle":"Early Prediction of Lung Cancer Employing Machine Learning: A Comprehensive Approach","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-08-28 08:10:15","doi":"10.21203/rs.3.rs-3658489/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":"717dcb48-3fc8-4dd8-b010-5c8d32e6beed","owner":[],"postedDate":"August 28th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-03-12T08:29:01+00:00","versionOfRecord":[],"versionCreatedAt":"2024-08-28 08:10:15","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-3658489","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3658489","identity":"rs-3658489","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}