Interpretable Survival Prediction for Bladder Cancer Patients based on Cox Proportional Hazards and SHAP Values

Interpretable Survival Prediction for Bladder Cancer Patients based on Cox Proportional Hazards and SHAP Values | 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 Interpretable Survival Prediction for Bladder Cancer Patients based on Cox Proportional Hazards and SHAP Values Shidong Gu, Jian Kang, Jirui Niu, Guangzhi Xu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9176722/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: Bladder cancer remains a significant clinical challenge due to its biological complexity and patient heterogeneity, particularly in predicting survival outcomes. Necrosis by Sodium Overload (NECSO) has been implicated in necrotic cell death mechanisms, which may influence tumor progression and prognosis. Current prognostic models often lack interpretability, limiting their utility in guiding personalized treatment strategies. This study aimed to develop an interpretable survival prediction model for bladder cancer patients using Cox proportional hazards analysis combined with SHAP (SHapley Additive exPlanations) values to identify key prognostic factors and enhance clinical decision-making. Methods: We utilized data from TCGA and GSE39281 to screen sodium overload related genes, identifying 81 candidate genes for model construction. Cox proportional hazards analysis was employed to evaluate the association between these genes and patient survival. SHAP values were used to quantify the contribution of each gene to the model's predictions, ensuring interpretability. The model's performance was assessed using risk scores and 5-year AUC curves. Results: The Cox single-factor model demonstrated a risk score of 2.807, while the multi-factor model showed a slightly lower risk score of 2.518. The 5-year AUC curve reached 0.716, indicating moderate predictive accuracy. SHAP analysis identified ELN, MYC, and AKAP13 as the most influential genes affecting survival outcomes. These findings highlight distinct molecular pathways associated with bladder cancer progression and prognosis. Conclusions: Our study successfully developed an interpretable survival prediction model for bladder cancer patients using Cox proportional hazards analysis and SHAP values. The identified key genes provide insights into potential therapeutic targets and biological mechanisms, including those related to NECSO. SHAP Bladder Cancer Survival Cox 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-9176722","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":633492296,"identity":"e2ea80f8-7f88-46b3-95f4-64ace2452a79","order_by":0,"name":"Shidong Gu","email":"","orcid":"","institution":"Heilongjiang Provincial Hospital \u0026 Harbin Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Shidong","middleName":"","lastName":"Gu","suffix":""},{"id":633492297,"identity":"9c408637-5472-49b6-a436-cbe8f4d53130","order_by":1,"name":"Jian Kang","email":"","orcid":"","institution":"Second Hospital of Anhui Medical University","correspondingAuthor":false,"prefix":"","firstName":"Jian","middleName":"","lastName":"Kang","suffix":""},{"id":633492298,"identity":"d941bfd0-52ba-42a7-a925-fde3b7e49ef6","order_by":2,"name":"Jirui Niu","email":"","orcid":"","institution":"The Fourth Affiliated Hospital of Harbin Medical University","correspondingAuthor":false,"prefix":"","firstName":"Jirui","middleName":"","lastName":"Niu","suffix":""},{"id":633492299,"identity":"1816995e-5b3d-4c34-bcd3-c9dc68b77efc","order_by":3,"name":"Guangzhi Xu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA2klEQVRIiWNgGAWjYLCCBwwScvz8zQcYEojWksBgYSw541gCSVoqEjccyDEgTrU5e/OxBwkVEowNB858/vBwhx0Df3s3fssse46lGySckWBmbO7dJpF4JplB4szZDXi1GNzIMZNIbJNgY2Y4u40hsY2ZwUAil4CW+2+AWv5J8LAx5Dz+kNhWT4SWGzxALQ0SEjwMOQxA6w4T1mLZkwb0yzEJAwmJYyAXHuch6Bdz9sPHHnyoqavff7758cefbdVy/O29BBzGwMCGIsCDVzlWLaNgFIyCUTAKMAAAWW1IaNGICMAAAAAASUVORK5CYII=","orcid":"","institution":"Heilongjiang Provincial Hospital \u0026 Harbin Institute of Technology","correspondingAuthor":true,"prefix":"","firstName":"Guangzhi","middleName":"","lastName":"Xu","suffix":""}],"badges":[],"createdAt":"2026-03-20 08:25:51","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9176722/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9176722/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":109096777,"identity":"dcc97cf8-27a5-46aa-bbfe-ffa34559d587","added_by":"auto","created_at":"2026-05-12 14:05:35","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1037985,"visible":true,"origin":"","legend":"","description":"","filename":"BMC.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9176722/v1_covered_af21565a-159a-436b-b8e2-4631c35fa710.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Interpretable Survival Prediction for Bladder Cancer Patients based on Cox Proportional Hazards and SHAP Values","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":"SHAP, Bladder Cancer, Survival, Cox","lastPublishedDoi":"10.21203/rs.3.rs-9176722/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9176722/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground:\u003c/h2\u003e \u003cp\u003eBladder cancer remains a significant clinical challenge due to its biological complexity and patient heterogeneity, particularly in predicting survival outcomes. Necrosis by Sodium Overload (NECSO) has been implicated in necrotic cell death mechanisms, which may influence tumor progression and prognosis. Current prognostic models often lack interpretability, limiting their utility in guiding personalized treatment strategies. This study aimed to develop an interpretable survival prediction model for bladder cancer patients using Cox proportional hazards analysis combined with SHAP (SHapley Additive exPlanations) values to identify key prognostic factors and enhance clinical decision-making.\u003c/p\u003e\u003ch2\u003eMethods:\u003c/h2\u003e \u003cp\u003eWe utilized data from TCGA and GSE39281 to screen sodium overload related genes, identifying 81 candidate genes for model construction. Cox proportional hazards analysis was employed to evaluate the association between these genes and patient survival. SHAP values were used to quantify the contribution of each gene to the model's predictions, ensuring interpretability. The model's performance was assessed using risk scores and 5-year AUC curves.\u003c/p\u003e\u003ch2\u003eResults:\u003c/h2\u003e \u003cp\u003eThe Cox single-factor model demonstrated a risk score of 2.807, while the multi-factor model showed a slightly lower risk score of 2.518. The 5-year AUC curve reached 0.716, indicating moderate predictive accuracy. SHAP analysis identified ELN, MYC, and AKAP13 as the most influential genes affecting survival outcomes. These findings highlight distinct molecular pathways associated with bladder cancer progression and prognosis.\u003c/p\u003e\u003ch2\u003eConclusions:\u003c/h2\u003e \u003cp\u003eOur study successfully developed an interpretable survival prediction model for bladder cancer patients using Cox proportional hazards analysis and SHAP values. The identified key genes provide insights into potential therapeutic targets and biological mechanisms, including those related to NECSO.\u003c/p\u003e","manuscriptTitle":"Interpretable Survival Prediction for Bladder Cancer Patients based on Cox Proportional Hazards and SHAP Values","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-04 13:21:39","doi":"10.21203/rs.3.rs-9176722/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":"73380cab-7b0f-490b-a4c8-4c620c4b4943","owner":[],"postedDate":"May 4th, 2026","published":true,"recentEditorialEvents":[{"type":"decision","content":"Rejected","date":"2026-05-12T12:40:32+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-09T17:08:35+00:00","index":158,"fulltext":""},{"type":"reviewerAgreed","content":"91368783469976415071623787607997252758","date":"2026-05-06T13:40:22+00:00","index":157,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-05T03:27:46+00:00","index":155,"fulltext":""},{"type":"reviewerAgreed","content":"9078917871524120344850256427681433384","date":"2026-05-04T03:27:23+00:00","index":152,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-05-12T13:46:57+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-04 13:21:39","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9176722","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9176722","identity":"rs-9176722","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}