Utilization of a Dynamic Machine Learning-Based Model for Predicting Resting Energy Expenditure in Evaluating Postoperative Complications Associated with Gastric Cancers

Utilization of a Dynamic Machine Learning-Based Model for Predicting Resting Energy Expenditure in Evaluating Postoperative Complications Associated with Gastric Cancers | 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 Utilization of a Dynamic Machine Learning-Based Model for Predicting Resting Energy Expenditure in Evaluating Postoperative Complications Associated with Gastric Cancers Dinghua YANG, Jun Xu, Qianzheng Zhou, Hongda Liu, Yiwen Xia, Tengyun Li, and 7 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8550434/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 7 You are reading this latest preprint version Abstract Background traditional indicators (e.g., prognostic nutritional index [PNI], body mass index [BMI], systemic immune–inflammation index [SII], neutrophil-to-lymphocyte ratio [NLR], and platelet-to-lymphocyte ratio [PLR]) have limited performance in predicting postoperative complications after gastrectomy. Resting energy expenditure (REE) reflects basal metabolism and may change in response to surgical stress; however, the prognostic value of perioperative REE dynamics in gastric cancer remains unclear. Methods We retrospectively analyzed 193 patients who underwent elective gastrectomy for gastric cancer. REE was measured by indirect calorimetry (COSMED Quark CPET) preoperatively (pre-OP) and on postoperative day 1 (POD1). REE metrics were expressed as the ratio of measured REE to the Harris–Benedict predicted value (preH-B% and D1H-B%). Postoperative complications were defined as Clavien–Dindo grade ≥ II. Candidate predictors were screened using random forest, support vector machine, and LASSO. Logistic regression was used to develop and compare a combined model incorporating metabolic indices with a model based on traditional predictors alone. Discrimination and incremental value were evaluated using AUC (DeLong’s test), integrated discrimination improvement (IDI), and net reclassification improvement (NRI). Results Postoperative complications occurred in 11.9% of patients (23/193). PreH-B% was positively associated with BMI and more advanced tumor stage (P < 0.05), whereas D1H-B% was associated with the extent of resection (P < 0.05). Across feature-selection methods, preH-B% and D1H-B% consistently ranked as the most important predictors. The combined model (preH-B%, D1H-B%, plus traditional predictors) showed superior discrimination compared with the traditional-predictors-only model (AUC 0.803 [95% CI 0.704–0.903] vs 0.654 [95% CI 0.538–0.771]; DeLong P = 0.0049). The combined model achieved a sensitivity of 89.41% and a specificity of 60.87%. Conclusion Perioperative REE dynamics, quantified by preH-B% and D1H-B%, improve prediction of postoperative complications after gastrectomy when integrated with traditional indicators. These findings support incorporating objective metabolic measurements into perioperative risk stratification for gastric cancer. Resting energy expenditure Gastric cancer Postoperative complications Machine learning Prediction model Metabolic stress Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 23 Mar, 2026 Reviews received at journal 20 Mar, 2026 Reviewers agreed at journal 02 Mar, 2026 Reviewers invited by journal 05 Feb, 2026 Editor assigned by journal 23 Jan, 2026 Submission checks completed at journal 23 Jan, 2026 First submitted to journal 22 Jan, 2026 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-8550434","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":586882431,"identity":"ba09a7a3-0b1f-46ec-9378-cbf50439c975","order_by":0,"name":"Dinghua YANG","email":"","orcid":"","institution":"Nanjing Medical University","correspondingAuthor":false,"prefix":"","firstName":"Dinghua","middleName":"","lastName":"YANG","suffix":""},{"id":586882435,"identity":"6f4c9966-3c93-413a-a241-04ef8d700c75","order_by":1,"name":"Jun Xu","email":"","orcid":"","institution":"Nanjing Medical University","correspondingAuthor":false,"prefix":"","firstName":"Jun","middleName":"","lastName":"Xu","suffix":""},{"id":586882436,"identity":"8de5757e-29c6-40df-9c63-12d0796515bb","order_by":2,"name":"Qianzheng Zhou","email":"","orcid":"","institution":"Nanjing Medical University","correspondingAuthor":false,"prefix":"","firstName":"Qianzheng","middleName":"","lastName":"Zhou","suffix":""},{"id":586882437,"identity":"358c15ef-368f-43dc-bb74-90a8a80f2e28","order_by":3,"name":"Hongda Liu","email":"","orcid":"","institution":"Nanjing Medical University","correspondingAuthor":false,"prefix":"","firstName":"Hongda","middleName":"","lastName":"Liu","suffix":""},{"id":586882438,"identity":"e6373007-8b53-4506-a0a8-6ba90ebe0436","order_by":4,"name":"Yiwen Xia","email":"","orcid":"","institution":"Nanjing Medical University","correspondingAuthor":false,"prefix":"","firstName":"Yiwen","middleName":"","lastName":"Xia","suffix":""},{"id":586882439,"identity":"15b988f6-b200-4f02-8ce3-09777fcf0c44","order_by":5,"name":"Tengyun Li","email":"","orcid":"","institution":"Nanjing Medical University","correspondingAuthor":false,"prefix":"","firstName":"Tengyun","middleName":"","lastName":"Li","suffix":""},{"id":586882440,"identity":"3f66f011-d12a-41dc-aac5-c6ef38ba8be4","order_by":6,"name":"Lei Qian","email":"","orcid":"","institution":"Nanjing Medical University","correspondingAuthor":false,"prefix":"","firstName":"Lei","middleName":"","lastName":"Qian","suffix":""},{"id":586882441,"identity":"da847654-5751-47e6-919e-b3f3d1848a25","order_by":7,"name":"Shenglong Xu","email":"","orcid":"","institution":"Nanjing Medical University","correspondingAuthor":false,"prefix":"","firstName":"Shenglong","middleName":"","lastName":"Xu","suffix":""},{"id":586882442,"identity":"793aea4b-1c4a-44f7-a981-3405c478417f","order_by":8,"name":"Xia Yang","email":"","orcid":"","institution":"Nanjing Medical University","correspondingAuthor":false,"prefix":"","firstName":"Xia","middleName":"","lastName":"Yang","suffix":""},{"id":586882443,"identity":"4a40d675-f1cd-4f1e-9189-9cc774a9c0b3","order_by":9,"name":"Yuxin Xu","email":"","orcid":"","institution":"Nanjing Medical University","correspondingAuthor":false,"prefix":"","firstName":"Yuxin","middleName":"","lastName":"Xu","suffix":""},{"id":586882444,"identity":"1b972d59-7462-4714-97d0-561eb0388823","order_by":10,"name":"Wenxing Zhou","email":"","orcid":"","institution":"Nanjing Medical University","correspondingAuthor":false,"prefix":"","firstName":"Wenxing","middleName":"","lastName":"Zhou","suffix":""},{"id":586882445,"identity":"3d8e88b4-519b-45a0-b061-fa98424c3761","order_by":11,"name":"Fengyuan Li","email":"","orcid":"","institution":"Nanjing Medical University","correspondingAuthor":false,"prefix":"","firstName":"Fengyuan","middleName":"","lastName":"Li","suffix":""},{"id":586882446,"identity":"6f3d2787-bff8-416c-82a5-a050d5b3a526","order_by":12,"name":"Hao Xu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAArElEQVRIiWNgGAWjYBACAwYGxgcMPDA2kVqYDUjWwiaBYBMDzCVyzKoLZLYlNrA3b5NgqLlDWItlzxmz2zN4bic28Bwrk2A49owIhx3vMbvNA9ICtE6CseEwEVoO85gVg7XIvyFWC9AWZogtPMRqOXOsWBqoxbiNJ63YIuEYMVpuJG/8zNtzW7af/fDGGx9qiNACBow9wNgBMRKI1AAEP4hXOgpGwSgYBSMQAAD6VjUzDXdBmgAAAABJRU5ErkJggg==","orcid":"","institution":"Nanjing Medical University","correspondingAuthor":true,"prefix":"","firstName":"Hao","middleName":"","lastName":"Xu","suffix":""}],"badges":[],"createdAt":"2026-01-08 10:39:45","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8550434/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8550434/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":102349353,"identity":"8f0eacec-b3fb-4df7-88c1-c1cd76f499e1","added_by":"auto","created_at":"2026-02-10 18:10:37","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1542500,"visible":true,"origin":"","legend":"","description":"","filename":"UtilizationofaDynamicMachineLearningBasedModelforPredictingRestingEnergyExpenditureinEvaluatingPostoperativeComplicationsAssociatedwithGastricCancer.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8550434/v1_covered_511f4093-8c3b-4893-afaf-0abc3ac2575d.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Utilization of a Dynamic Machine Learning-Based Model for Predicting Resting Energy Expenditure in Evaluating Postoperative Complications Associated with Gastric Cancers","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":"journal-of-cancer-research-and-clinical-oncology","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jocr","sideBox":"Learn more about [Journal of Cancer Research and Clinical Oncology](https://www.springer.com/journal/432)","snPcode":"432","submissionUrl":"https://submission.nature.com/new-submission/432/3","title":"Journal of Cancer Research and Clinical Oncology","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Resting energy expenditure, Gastric cancer, Postoperative complications, Machine learning, Prediction model, Metabolic stress","lastPublishedDoi":"10.21203/rs.3.rs-8550434/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8550434/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cb\u003eBackground\u003c/b\u003e\u003c/p\u003e \u003cp\u003etraditional indicators (e.g., prognostic nutritional index [PNI], body mass index [BMI], systemic immune\u0026ndash;inflammation index [SII], neutrophil-to-lymphocyte ratio [NLR], and platelet-to-lymphocyte ratio [PLR]) have limited performance in predicting postoperative complications after gastrectomy. Resting energy expenditure (REE) reflects basal metabolism and may change in response to surgical stress; however, the prognostic value of perioperative REE dynamics in gastric cancer remains unclear.\u003c/p\u003e\u003cp\u003e\u003cb\u003eMethods\u003c/b\u003e\u003c/p\u003e \u003cp\u003eWe retrospectively analyzed 193 patients who underwent elective gastrectomy for gastric cancer. REE was measured by indirect calorimetry (COSMED Quark CPET) preoperatively (pre-OP) and on postoperative day 1 (POD1). REE metrics were expressed as the ratio of measured REE to the Harris\u0026ndash;Benedict predicted value (preH-B% and D1H-B%). Postoperative complications were defined as Clavien\u0026ndash;Dindo grade\u0026thinsp;\u0026ge;\u0026thinsp;II. Candidate predictors were screened using random forest, support vector machine, and LASSO. Logistic regression was used to develop and compare a combined model incorporating metabolic indices with a model based on traditional predictors alone. Discrimination and incremental value were evaluated using AUC (DeLong\u0026rsquo;s test), integrated discrimination improvement (IDI), and net reclassification improvement (NRI).\u003c/p\u003e\u003cp\u003e\u003cb\u003eResults\u003c/b\u003e\u003c/p\u003e \u003cp\u003ePostoperative complications occurred in 11.9% of patients (23/193). PreH-B% was positively associated with BMI and more advanced tumor stage (P\u0026thinsp;\u0026lt;\u0026thinsp;0.05), whereas D1H-B% was associated with the extent of resection (P\u0026thinsp;\u0026lt;\u0026thinsp;0.05). Across feature-selection methods, preH-B% and D1H-B% consistently ranked as the most important predictors. The combined model (preH-B%, D1H-B%, plus traditional predictors) showed superior discrimination compared with the traditional-predictors-only model (AUC 0.803 [95% CI 0.704\u0026ndash;0.903] vs 0.654 [95% CI 0.538\u0026ndash;0.771]; DeLong P\u0026thinsp;=\u0026thinsp;0.0049). The combined model achieved a sensitivity of 89.41% and a specificity of 60.87%.\u003c/p\u003e\u003cp\u003e\u003cb\u003eConclusion\u003c/b\u003e\u003c/p\u003e \u003cp\u003ePerioperative REE dynamics, quantified by preH-B% and D1H-B%, improve prediction of postoperative complications after gastrectomy when integrated with traditional indicators. These findings support incorporating objective metabolic measurements into perioperative risk stratification for gastric cancer.\u003c/p\u003e","manuscriptTitle":"Utilization of a Dynamic Machine Learning-Based Model for Predicting Resting Energy Expenditure in Evaluating Postoperative Complications Associated with Gastric Cancers","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-10 18:10:23","doi":"10.21203/rs.3.rs-8550434/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-03-23T15:27:31+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-20T09:19:58+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"324541303914066615487340152185417015176","date":"2026-03-02T11:01:53+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-02-06T01:20:55+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-01-23T06:45:07+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-01-23T05:28:39+00:00","index":"","fulltext":""},{"type":"submitted","content":"Journal of Cancer Research and Clinical Oncology","date":"2026-01-22T16:00:17+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"journal-of-cancer-research-and-clinical-oncology","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jocr","sideBox":"Learn more about [Journal of Cancer Research and Clinical Oncology](https://www.springer.com/journal/432)","snPcode":"432","submissionUrl":"https://submission.nature.com/new-submission/432/3","title":"Journal of Cancer Research and Clinical Oncology","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"f2f2a551-bf41-4bda-95fe-b9646cf77441","owner":[],"postedDate":"February 10th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-04-27T08:00:43+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-10 18:10:23","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8550434","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8550434","identity":"rs-8550434","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}