Estimating Intraoperative Blood Loss in Gynecological Pelvic Surgeries Using Machine Learning

Estimating Intraoperative Blood Loss in Gynecological Pelvic Surgeries 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 Estimating Intraoperative Blood Loss in Gynecological Pelvic Surgeries Using Machine Learning Jianfeng Liu, Yong He, Shufei Zhang, Ya Xiao, Mao Chen, Li Hong This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8627296/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 Background Intraoperative blood loss is a frequent complication in gynecological pelvic surgeries and may increase operative difficulty and postoperative morbidity. An objective preoperative tool based on routinely collected variables could facilitate risk stratification and perioperative blood management. Methods We retrospectively reviewed medical records of 908 patients who underwent gynecological pelvic floor–related surgeries at Renmin Hospital of Wuhan University (December 2017 to December 2019). Intraoperative blood loss was dichotomized using 100 mL as the threshold. After preprocessing (median imputation, normalization) and dimensionality reduction, the dataset was split into training and validation sets (8:2). Six machine learning algorithms—Decision Tree (DT), Support Vector Machine (SVM), Random Forest (RF), Extreme Gradient Boosting (XGBoost), Adaptive Boosting (AdaBoost), and Gradient Boosting Decision Tree (GBDT)—were trained with grid-search tuning. Model performance was evaluated using accuracy, precision, recall, F1 score, AUROC, and calibration curves, with bootstrapping for confidence estimation. Model interpretability was assessed using SHapley Additive exPlanations (SHAP). Results Across the tested models, XGBoost showed the most favorable overall discrimination and calibration in the validation set (AUROC 0.71) and achieved an accuracy of 65.9%. SHAP analysis highlighted clinically plausible predictors related to coagulation and metabolic status, including total bile acids, platelet-related indices, and prothrombin activity, supporting interpretability and potential clinical usability. Conclusions Using routinely available preoperative data, a machine learning–based approach can support preoperative stratification of intraoperative blood-loss risk in gynecological pelvic surgeries. While external validation is warranted, the proposed model may assist perioperative planning and risk management. Pelvic floor surgery Intraoperative blood loss Machine learning Prediction model XGBoost Full Text Additional Declarations No competing interests reported. Supplementary Files supplementarymaterials.zip 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-8627296","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":586412264,"identity":"eb75d2c7-7b0c-45c6-86fd-9c88b986585a","order_by":0,"name":"Jianfeng Liu","email":"","orcid":"","institution":"Renmin Hospital of Wuhan University","correspondingAuthor":false,"prefix":"","firstName":"Jianfeng","middleName":"","lastName":"Liu","suffix":""},{"id":586412266,"identity":"27cd7019-0ffc-47b5-8678-c51b12a206f1","order_by":1,"name":"Yong He","email":"","orcid":"","institution":"Renmin Hospital of Wuhan University","correspondingAuthor":false,"prefix":"","firstName":"Yong","middleName":"","lastName":"He","suffix":""},{"id":586412267,"identity":"f789821c-4348-433a-89c7-ea85dfd394fd","order_by":2,"name":"Shufei Zhang","email":"","orcid":"","institution":"Renmin Hospital of Wuhan University","correspondingAuthor":false,"prefix":"","firstName":"Shufei","middleName":"","lastName":"Zhang","suffix":""},{"id":586412269,"identity":"fc521fef-b433-4ea0-9df4-a585069e54cc","order_by":3,"name":"Ya Xiao","email":"","orcid":"","institution":"Renmin Hospital of Wuhan University","correspondingAuthor":false,"prefix":"","firstName":"Ya","middleName":"","lastName":"Xiao","suffix":""},{"id":586412271,"identity":"93c041bc-7e93-4eac-8bef-9ebf9c8cccef","order_by":4,"name":"Mao Chen","email":"","orcid":"","institution":"Renmin Hospital of Wuhan University","correspondingAuthor":false,"prefix":"","firstName":"Mao","middleName":"","lastName":"Chen","suffix":""},{"id":586412272,"identity":"83cfdc63-8f22-4e39-9a2a-9178eb5641c4","order_by":5,"name":"Li Hong","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA00lEQVRIiWNgGAWjYDCCAwxsIEqGjb0BzGBsIFYLDxvPAVK1MEgkEKmF7/YBtgcfd9Ty8Em+MXvMw2Aju+EA87MH+LRInktgN5x55jgPm3SOuTEPQ5rxhgNs5gb4tBicYWCT5m07BtSSu02ah+Fw4oYDPGwSxGmRPAvS8p9oLTVAZbwgLQcIa5EEapGc2QZUxpP/TXKOQbLxzMNsZni18AG1SHxsq5OTbz+WJvGmwk6273jzM7xaGBj4PwCJwzB3AjEzfvUwUEecslEwCkbBKBiZAABwSD8nER3aWwAAAABJRU5ErkJggg==","orcid":"","institution":"Renmin Hospital of Wuhan University","correspondingAuthor":true,"prefix":"","firstName":"Li","middleName":"","lastName":"Hong","suffix":""}],"badges":[],"createdAt":"2026-01-17 16:23:26","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8627296/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8627296/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":107343759,"identity":"090abd9e-ceed-46ba-96d4-047f13fb2faa","added_by":"auto","created_at":"2026-04-20 14:43:06","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":782867,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8627296/v1_covered_85fbf150-1a58-44f2-b32a-60b6a5fff18a.pdf"},{"id":102249457,"identity":"951e7dd8-0586-4b92-9d07-fc44ffc48f2a","added_by":"auto","created_at":"2026-02-09 19:04:23","extension":"zip","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":511146,"visible":true,"origin":"","legend":"","description":"","filename":"supplementarymaterials.zip","url":"https://assets-eu.researchsquare.com/files/rs-8627296/v1/b28dbba84dc687c74e0e4ef1.zip"}],"financialInterests":"No competing interests reported.","formattedTitle":"Estimating Intraoperative Blood Loss in Gynecological Pelvic Surgeries Using Machine Learning","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":"Pelvic floor surgery, Intraoperative blood loss, Machine learning, Prediction model, XGBoost","lastPublishedDoi":"10.21203/rs.3.rs-8627296/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8627296/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground\u003c/h2\u003e \u003cp\u003eIntraoperative blood loss is a frequent complication in gynecological pelvic surgeries and may increase operative difficulty and postoperative morbidity. An objective preoperative tool based on routinely collected variables could facilitate risk stratification and perioperative blood management.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e \u003cp\u003e We retrospectively reviewed medical records of 908 patients who underwent gynecological pelvic floor\u0026ndash;related surgeries at Renmin Hospital of Wuhan University (December 2017 to December 2019). Intraoperative blood loss was dichotomized using 100 mL as the threshold. After preprocessing (median imputation, normalization) and dimensionality reduction, the dataset was split into training and validation sets (8:2). Six machine learning algorithms\u0026mdash;Decision Tree (DT), Support Vector Machine (SVM), Random Forest (RF), Extreme Gradient Boosting (XGBoost), Adaptive Boosting (AdaBoost), and Gradient Boosting Decision Tree (GBDT)\u0026mdash;were trained with grid-search tuning. Model performance was evaluated using accuracy, precision, recall, F1 score, AUROC, and calibration curves, with bootstrapping for confidence estimation. Model interpretability was assessed using SHapley Additive exPlanations (SHAP).\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e \u003cp\u003eAcross the tested models, XGBoost showed the most favorable overall discrimination and calibration in the validation set (AUROC 0.71) and achieved an accuracy of 65.9%. SHAP analysis highlighted clinically plausible predictors related to coagulation and metabolic status, including total bile acids, platelet-related indices, and prothrombin activity, supporting interpretability and potential clinical usability.\u003c/p\u003e\u003ch2\u003eConclusions\u003c/h2\u003e \u003cp\u003eUsing routinely available preoperative data, a machine learning\u0026ndash;based approach can support preoperative stratification of intraoperative blood-loss risk in gynecological pelvic surgeries. While external validation is warranted, the proposed model may assist perioperative planning and risk management.\u003c/p\u003e","manuscriptTitle":"Estimating Intraoperative Blood Loss in Gynecological Pelvic Surgeries Using Machine Learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-09 19:04:18","doi":"10.21203/rs.3.rs-8627296/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":"7dbe4da1-9ddd-4eed-a5f9-751fc235aae3","owner":[],"postedDate":"February 9th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-04-20T14:42:32+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-09 19:04:18","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8627296","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8627296","identity":"rs-8627296","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}