Construction and Application Study of a Machine Learning iSCOUT-guided Precision Radiotherapy Positioning Error Prediction Model for Breast Cancer

Construction and Application Study of a Machine Learning iSCOUT-guided Precision Radiotherapy Positioning Error Prediction Model for Breast Cancer | 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 Construction and Application Study of a Machine Learning iSCOUT-guided Precision Radiotherapy Positioning Error Prediction Model for Breast Cancer Fangfen Dong, Bing Wu, Weipei Wang, Zhixin Wang, Jiaming Li, Benhua Xu, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7688740/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 Methods The study utilized the cumulative results of 1,200 iSCOUT system scans from 80 breast cancer patients as research data. Initially, based on literature review and clinical practice experience, factors influencing patient positioning errors during treatment were identified, and relevant information was collected. This process yielded 13 feature values to serve as input variables for the machine learning model. The classification of the maximum positioning error in three translational directions was used as the output of the machine learning model. The maximum positioning error for each scan was categorized into two classes based on a 3mm threshold, which served as the target value for the machine learning model.Feature selection was performed using XGBoost to calculate feature importance, and the features were ranked accordingly. The top n most important features were selected for further analysis. The research data was then split into training and validation sets in an 8:2 ratio. A predictive model was trained using the training set, and its performance was preliminarily evaluated using the validation set. Finally, the predictive results of a predictive model were compared with those of reference models, including SVM-SVC and DecisionTreeClassifier, to assess the performance differences across models. Results Among the various training models, XGBoost showed higher accuracy. A predictive model constructed in this study achieved the highest prediction accuracy for patient .positioning errors on the 4th to 7th days of treatment, with a maximum accuracy of 71.87%. Conclusion Machine learning algorithms have demonstrated the capability to predict instances where a patient's positioning error exceeds 3mm. However, ongoing efforts are required to enhance their accuracy. To optimize iSCOUT image-guided frequency, enhance radiotherapy efficacy, and reduce radiotherapy side effects, more feature parameters need to be identified for model training. Machine learning positioning error error prediction image guidance precision radiotherapy Full Text Additional Declarations No competing interests reported. Supplementary Files SupplementaryMaterials.docx 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-7688740","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":549316525,"identity":"f0ebf54b-9607-4a26-b76a-e7e66576bc7c","order_by":0,"name":"Fangfen Dong","email":"","orcid":"","institution":"Fujian Medical University Union Hospital","correspondingAuthor":false,"prefix":"","firstName":"Fangfen","middleName":"","lastName":"Dong","suffix":""},{"id":549316526,"identity":"8da53976-c898-4161-aa15-fd75a1a37cb8","order_by":1,"name":"Bing Wu","email":"","orcid":"","institution":"Fujian Medical University","correspondingAuthor":false,"prefix":"","firstName":"Bing","middleName":"","lastName":"Wu","suffix":""},{"id":549316527,"identity":"fa0a7655-0c8c-4cd1-88dc-d66be34096c8","order_by":2,"name":"Weipei Wang","email":"","orcid":"","institution":"Fujian Medical University","correspondingAuthor":false,"prefix":"","firstName":"Weipei","middleName":"","lastName":"Wang","suffix":""},{"id":549316528,"identity":"1dff7a2a-3abc-4aaa-80e2-d90e3fb852c2","order_by":3,"name":"Zhixin Wang","email":"","orcid":"","institution":"Fujian Medical University","correspondingAuthor":false,"prefix":"","firstName":"Zhixin","middleName":"","lastName":"Wang","suffix":""},{"id":549316529,"identity":"7e5e4a14-b1ae-4e21-aaa4-60e47040c1e5","order_by":4,"name":"Jiaming Li","email":"","orcid":"","institution":"Fujian Medical University","correspondingAuthor":false,"prefix":"","firstName":"Jiaming","middleName":"","lastName":"Li","suffix":""},{"id":549316530,"identity":"51173f55-48f7-4141-b796-f390fff0d9fd","order_by":5,"name":"Benhua Xu","email":"","orcid":"","institution":"Fujian Medical University Union Hospital","correspondingAuthor":false,"prefix":"","firstName":"Benhua","middleName":"","lastName":"Xu","suffix":""},{"id":549316531,"identity":"fc576164-5449-41d7-b766-011f0dc72fe9","order_by":6,"name":"Yong Yang","email":"","orcid":"","institution":"Fujian Medical University Union Hospital","correspondingAuthor":false,"prefix":"","firstName":"Yong","middleName":"","lastName":"Yang","suffix":""},{"id":549316532,"identity":"ab464e7c-1d1c-465e-8fc0-23ea616995b6","order_by":7,"name":"Yifa Zhao","email":"","orcid":"","institution":"Zhangpu County Hospital","correspondingAuthor":false,"prefix":"","firstName":"Yifa","middleName":"","lastName":"Zhao","suffix":""},{"id":549316533,"identity":"2ed157f0-328b-44fe-88c0-83ebdce4b19e","order_by":8,"name":"Xiaobo Li","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA40lEQVRIiWNgGAWjYBACPmYGhgMgxM/M2GDwwcBGjqAWNpgWyfbmA4UzCtKMCWuBUAcYDM4cS/jM8+FwImEt7DyGB35U3JFjuJFjuNnGgDmBgf3w0Q34HcaWcLDnzDNjxhk5xsY5Bmx5DDxpaTfwa2E+cIC37XBis0SOGVALTzGDBI8ZAS2MDQf/ArW0SeSY/7YwkEhsIKyF+cBhkC09PMcSjBkMDIjRwpZwWAboFwn25gOGPQYJxmyE/MLPf8b44xtgiNkfBkbljz//5fjZDx/DqwWLvaQpHwWjYBSMglGADQAA+Z9KoRhKTusAAAAASUVORK5CYII=","orcid":"","institution":"Fujian Medical University Union Hospital","correspondingAuthor":true,"prefix":"","firstName":"Xiaobo","middleName":"","lastName":"Li","suffix":""}],"badges":[],"createdAt":"2025-09-23 02:39:21","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7688740/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7688740/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":96756746,"identity":"ed59195f-eb88-460c-875b-ef53a21df736","added_by":"auto","created_at":"2025-11-25 18:08:01","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":747339,"visible":true,"origin":"","legend":"","description":"","filename":"ConstructionandApplicationStudyofaMachineLearningiSCOUTguidedPrecisionRadiotherapyPositioningErrorPredictionModelforBreastCancer2.docx","url":"https://assets-eu.researchsquare.com/files/rs-7688740/v1/5a87879fd664fcc89c781608.docx"},{"id":96915625,"identity":"094cd3ad-6e58-4c26-9a87-0f7589569491","added_by":"auto","created_at":"2025-11-27 14:07:27","extension":"jpg","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":640248,"visible":true,"origin":"","legend":"","description":"","filename":"figure2.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7688740/v1/1466c926f4cf85a6c3fb1c0c.jpg"},{"id":96756776,"identity":"7d848de5-a989-4160-9228-b28bd1ccdbd5","added_by":"auto","created_at":"2025-11-25 18:08:02","extension":"jpg","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":10995582,"visible":true,"origin":"","legend":"","description":"","filename":"flowchart.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7688740/v1/fa8f4ec1c85a8c55729afbd2.jpg"},{"id":96915695,"identity":"1a12a3ff-c538-40ed-bbeb-f21f78a381d3","added_by":"auto","created_at":"2025-11-27 14:07:32","extension":"xlsx","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":10686,"visible":true,"origin":"","legend":"","description":"","filename":"Table1.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-7688740/v1/c0167d3dd48aa4d34e7f80f8.xlsx"},{"id":96756748,"identity":"2a6d297a-e551-424c-8e7e-6b9f596d3079","added_by":"auto","created_at":"2025-11-25 18:08:01","extension":"xlsx","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":10075,"visible":true,"origin":"","legend":"","description":"","filename":"Table2.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-7688740/v1/9e3e4ceeb28f563406044147.xlsx"},{"id":96915971,"identity":"23203ec8-40f2-4a88-9e33-a37542aa822b","added_by":"auto","created_at":"2025-11-27 14:07:50","extension":"xlsx","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":10685,"visible":true,"origin":"","legend":"","description":"","filename":"Table3.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-7688740/v1/9ff83b79547e16c1f4d96a39.xlsx"},{"id":96756747,"identity":"1caa2d23-4a16-42d5-9916-fcafb793aa09","added_by":"auto","created_at":"2025-11-25 18:08:01","extension":"xlsx","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":10559,"visible":true,"origin":"","legend":"","description":"","filename":"Table4.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-7688740/v1/e0ec582c82ed7209e0c15000.xlsx"},{"id":96756751,"identity":"dc740ed6-c23a-4d81-98f6-6dba42855b5b","added_by":"auto","created_at":"2025-11-25 18:08:01","extension":"xlsx","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":10584,"visible":true,"origin":"","legend":"","description":"","filename":"Table5.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-7688740/v1/7d96b9f1d897b266a41ff452.xlsx"},{"id":96915213,"identity":"85aa73f9-b0a6-4ca0-b81a-e2e218113a01","added_by":"auto","created_at":"2025-11-27 14:06:59","extension":"json","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":10195,"visible":true,"origin":"","legend":"","description":"","filename":"39902e3599cd456aa9dee3ef5126664a.json","url":"https://assets-eu.researchsquare.com/files/rs-7688740/v1/12883a849793485b166eea84.json"},{"id":96756755,"identity":"3ac34eb2-adff-45eb-af99-11384077b9a9","added_by":"auto","created_at":"2025-11-25 18:08:01","extension":"docx","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":631717,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryMaterials.docx","url":"https://assets-eu.researchsquare.com/files/rs-7688740/v1/5b37e0f500fd4121d090a4cb.docx"},{"id":96756758,"identity":"e7c8d03b-06cb-47d4-8864-1d67cf6635fe","added_by":"auto","created_at":"2025-11-25 18:08:01","extension":"xml","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":80120,"visible":true,"origin":"","legend":"","description":"","filename":"39902e3599cd456aa9dee3ef5126664a1enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7688740/v1/51f444586d3a8803b54061d4.xml"},{"id":96915387,"identity":"cfbe3919-5ccf-4f25-98a4-c1601be42ba0","added_by":"auto","created_at":"2025-11-27 14:07:11","extension":"eps","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":181024,"visible":true,"origin":"","legend":"","description":"","filename":"drawingimage1.eps","url":"https://assets-eu.researchsquare.com/files/rs-7688740/v1/a6df29882b7f1b32a05852e0.eps"},{"id":96914809,"identity":"3a56d6d7-9258-49ac-9ee5-1c2c81dec2e4","added_by":"auto","created_at":"2025-11-27 14:06:23","extension":"jpg","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":640248,"visible":true,"origin":"","legend":"","description":"","filename":"figure2.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7688740/v1/dcdba602315e26be5e472547.jpg"},{"id":96915534,"identity":"ead95c12-8df9-4c3e-9ffe-8486cc4f0808","added_by":"auto","created_at":"2025-11-27 14:07:21","extension":"jpeg","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":903939,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7688740/v1/87a60a641796c693b66f9fd9.jpeg"},{"id":96915406,"identity":"f19eb943-c713-4d7d-ba9b-c91b9749e0c8","added_by":"auto","created_at":"2025-11-27 14:07:13","extension":"jpeg","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":468815,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7688740/v1/6d06109164a4d3fd936393cb.jpeg"},{"id":96756757,"identity":"7e7a935c-e248-4d9b-80d8-349a4d209b48","added_by":"auto","created_at":"2025-11-25 18:08:01","extension":"jpeg","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":153197,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7688740/v1/767b18b955aed714f091e9f8.jpeg"},{"id":96756764,"identity":"0128b318-66a1-4540-8bfe-7a402bf715b8","added_by":"auto","created_at":"2025-11-25 18:08:01","extension":"jpeg","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":579671,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7688740/v1/9c68f36e94b4d2845700f4c5.jpeg"},{"id":96756760,"identity":"cab6dde8-d579-4110-9a7a-5cf1416fd63b","added_by":"auto","created_at":"2025-11-25 18:08:01","extension":"jpeg","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":577139,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7688740/v1/9ddb9ba9b704e252dfd6ea0b.jpeg"},{"id":96915082,"identity":"a415f069-674d-4998-88ba-dc138c2a171b","added_by":"auto","created_at":"2025-11-27 14:06:50","extension":"jpeg","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":596991,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7688740/v1/b13f357a9ace6465916698bd.jpeg"},{"id":96914971,"identity":"d2310f8a-550f-4a29-b4a0-26d3e4847382","added_by":"auto","created_at":"2025-11-27 14:06:41","extension":"jpg","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":10995582,"visible":true,"origin":"","legend":"","description":"","filename":"flowchart.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7688740/v1/1f7ca8a7eea0c38a997bc3bb.jpg"},{"id":96756765,"identity":"ce4f0384-5a34-4f11-b9e4-ebca95cffca2","added_by":"auto","created_at":"2025-11-25 18:08:01","extension":"png","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":81848,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefigure2.png","url":"https://assets-eu.researchsquare.com/files/rs-7688740/v1/aa2943a5f1156095b6ac4a1b.png"},{"id":96914029,"identity":"1ab4dc06-b8ab-4d25-bfca-93e4f89ce7e8","added_by":"auto","created_at":"2025-11-27 14:05:13","extension":"png","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":207628,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7688740/v1/d6cfd252e1355c9478b75c47.png"},{"id":96915874,"identity":"67fbd982-103d-4ac5-991e-edab98e624b3","added_by":"auto","created_at":"2025-11-27 14:07:43","extension":"png","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":91487,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7688740/v1/37bd83d35bd2b7f165b79c2f.png"},{"id":96756768,"identity":"08a1a2d8-189a-4c5d-ad6a-9a1564f07626","added_by":"auto","created_at":"2025-11-25 18:08:01","extension":"png","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":26641,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7688740/v1/ffd5e238be753ae06a6ea16b.png"},{"id":96915306,"identity":"34023d42-a6db-4dfe-99a7-9d829b5b8b0d","added_by":"auto","created_at":"2025-11-27 14:07:05","extension":"png","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":106027,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7688740/v1/db27ec0172bd4a61a7d8a874.png"},{"id":96915912,"identity":"9349b340-2e63-48ed-b6e3-0165d2fa0945","added_by":"auto","created_at":"2025-11-27 14:07:46","extension":"png","order_by":25,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":110635,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7688740/v1/a696456393d9cca054118988.png"},{"id":96756770,"identity":"e829753d-69fc-4fb4-b356-ca74bfa44086","added_by":"auto","created_at":"2025-11-25 18:08:01","extension":"png","order_by":26,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":114789,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7688740/v1/bf5666209c0608aa1b2805b9.png"},{"id":96756773,"identity":"f68a4960-ab7a-475d-87e5-4ca9c311fa6d","added_by":"auto","created_at":"2025-11-25 18:08:01","extension":"png","order_by":27,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1958740,"visible":true,"origin":"","legend":"","description":"","filename":"Onlineflowchart.png","url":"https://assets-eu.researchsquare.com/files/rs-7688740/v1/5195320ae9e89392e95df945.png"},{"id":96756769,"identity":"e77ddb9a-8f72-4375-af69-1608bc614c70","added_by":"auto","created_at":"2025-11-25 18:08:01","extension":"xml","order_by":28,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":77148,"visible":true,"origin":"","legend":"","description":"","filename":"39902e3599cd456aa9dee3ef5126664a1structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7688740/v1/9fdd4f5a7af9fd71ca230e1e.xml"},{"id":96756774,"identity":"86603192-a4cc-4892-a8e9-ad73f7eef58f","added_by":"auto","created_at":"2025-11-25 18:08:02","extension":"html","order_by":29,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":90017,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7688740/v1/5b73bd7168b8a08d2b641eca.html"},{"id":99789125,"identity":"8a93ef83-ea77-4bc1-ae3c-e153cc60dfc7","added_by":"auto","created_at":"2026-01-08 12:48:49","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":731898,"visible":true,"origin":"","legend":"","description":"","filename":"ConstructionandApplicationStudyofaMachineLearningiSCOUTguidedPrecisionRadiotherapyPositioningErrorPredictionModelforBreastCancer2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7688740/v1_covered_022c20be-7a7b-4cec-9847-f5098fb13f6a.pdf"},{"id":96756754,"identity":"934c1dda-bcbc-474b-a68b-20fefbf15874","added_by":"auto","created_at":"2025-11-25 18:08:01","extension":"docx","order_by":5,"title":"","display":"","copyAsset":false,"role":"supplement","size":631717,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryMaterials.docx","url":"https://assets-eu.researchsquare.com/files/rs-7688740/v1/a48ae5ec055d0fe5120e330f.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"Construction and Application Study of a Machine Learning iSCOUT-guided Precision Radiotherapy Positioning Error Prediction Model for Breast Cancer","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":"Machine learning, positioning error, error prediction, image guidance, precision radiotherapy","lastPublishedDoi":"10.21203/rs.3.rs-7688740/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7688740/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eMethods\u003c/h2\u003e\u003cp\u003eThe study utilized the cumulative results of 1,200 iSCOUT system scans from 80 breast cancer patients as research data. Initially, based on literature review and clinical practice experience, factors influencing patient positioning errors during treatment were identified, and relevant information was collected. This process yielded 13 feature values to serve as input variables for the machine learning model. The classification of the maximum positioning error in three translational directions was used as the output of the machine learning model. The maximum positioning error for each scan was categorized into two classes based on a 3mm threshold, which served as the target value for the machine learning model.Feature selection was performed using XGBoost to calculate feature importance, and the features were ranked accordingly. The top n most important features were selected for further analysis. The research data was then split into training and validation sets in an 8:2 ratio. A predictive model was trained using the training set, and its performance was preliminarily evaluated using the validation set. Finally, the predictive results of a predictive model were compared with those of reference models, including SVM-SVC and DecisionTreeClassifier, to assess the performance differences across models.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e\u003cp\u003eAmong the various training models, XGBoost showed higher accuracy. A predictive model constructed in this study achieved the highest prediction accuracy for patient .positioning errors on the 4th to 7th days of treatment, with a maximum accuracy of 71.87%.\u003c/p\u003e\u003ch2\u003eConclusion\u003c/h2\u003e\u003cp\u003eMachine learning algorithms have demonstrated the capability to predict instances where a patient's positioning error exceeds 3mm. However, ongoing efforts are required to enhance their accuracy. To optimize iSCOUT image-guided frequency, enhance radiotherapy efficacy, and reduce radiotherapy side effects, more feature parameters need to be identified for model training.\u003c/p\u003e","manuscriptTitle":"Construction and Application Study of a Machine Learning iSCOUT-guided Precision Radiotherapy Positioning Error Prediction Model for Breast Cancer","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-25 18:07:56","doi":"10.21203/rs.3.rs-7688740/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":"711aa09a-60a4-4935-a086-74b4b6089434","owner":[],"postedDate":"November 25th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-01-02T04:39:12+00:00","versionOfRecord":[],"versionCreatedAt":"2025-11-25 18:07:56","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7688740","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7688740","identity":"rs-7688740","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}