Uncovering Sex-Specific Symptom Networks: NLP-Based Clustering in Cancer Emergencies

Uncovering Sex-Specific Symptom Networks: NLP-Based Clustering in Cancer Emergencies | 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 Article Uncovering Sex-Specific Symptom Networks: NLP-Based Clustering in Cancer Emergencies Juan G. Diaz Ochoa, Natalie Layer, Christian U. Menzel, Martina Müller, and 4 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7084787/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 10 You are reading this latest preprint version Abstract Understanding symptom patterns in emergency care of patients with cancer is crucial for accurate stratification and personalized decision-making. We applied natural language processing (NLP) to Emergency Department (ED) records to extract symptom data and linked these records with structured metadata (age, sex, and diagnosis) to construct patient similarity networks. A fine-tuned BioGottBERT model running entirely on secure in-house systems encoded patients as embeddings; pairwise similarities were then calculated to construct a patient graph. Using edge-betweenness clustering, we identified clinically meaningful and stable patient subgroups based on symptom profiles and demographic similarity. We identified distinct stratification patterns among polysymptomatic, oligosymptomatic, and atypical cases, as well as differences in symptom variability across cancer types, including gastrointestinal and lung cancer. Of clinical relevance, our findings underscore the intrinsic role of sex in symptom expression. Our approach demonstrates how NLP and graph-based clustering can uncover latent patient structures from unstructured data, supporting personalized diagnostics and enabling seamless integration into local hospital-based infrastructure and workflows. Biological sciences/Cancer Biological sciences/Computational biology and bioinformatics Health sciences/Health care Physical sciences/Mathematics and computing Natural Language Processing (NLP) Emergency Oncology Symptom Networks Patient Stratification Sex Differences Free-Text Analysis Similarity Clustering Edge Betweenness Clinical Decision Support Unstructured Data Analysis Sex-Specific Symptom Patterns Learning Cancer Center (LCC) Anamnesis Mining Resource-Efficient AI Health Informatics Full Text Additional Declarations Competing interest reported. JGDO works for PerMediQ GmbH. The other authors declare that they have no conflicts of interest. Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 22 Apr, 2026 Reviewers agreed at journal 09 Apr, 2026 Reviews received at journal 23 Nov, 2025 Reviewers agreed at journal 15 Nov, 2025 Reviewers agreed at journal 13 Nov, 2025 Reviewers invited by journal 30 Oct, 2025 Editor invited by journal 15 Jul, 2025 Editor assigned by journal 11 Jul, 2025 Submission checks completed at journal 10 Jul, 2025 First submitted to journal 09 Jul, 2025 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-7084787","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":483448424,"identity":"8c15554c-f3c8-4045-ab97-1da599346099","order_by":0,"name":"Juan G. Diaz Ochoa","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA7klEQVRIiWNgGAWjYBAC9gYQySYBYzEwtgEJCXxaGOFaeA6QpgWkLAEhgF/LjORnDxjKLOTlZ749+Lgyx0a2jz2B8cYHvFrSzA0YzkkYNs7OSzY8uy3NuI3nAbPlDLxaEswkGNskGJulc8wkG7cdTmyTSGCT5sGrJf0bSIt9m+QZ85+N2/5DtPzBo0VwRg7YlsQeCR4zxsZtByBa8HlfmudNmUTCOYnkGTx5yUCHJQP98rDZsgePFj729G0SH8rqbOe3nz34sXGbnez89uSDN37gswYEEsAk3MuJDYQ0wABcSwKxOkbBKBgFo2CEAACRIkjU/oaOjQAAAABJRU5ErkJggg==","orcid":"","institution":"PerMediQ GmbH","correspondingAuthor":true,"prefix":"","firstName":"Juan","middleName":"G. Diaz","lastName":"Ochoa","suffix":""},{"id":483448425,"identity":"dd081696-388e-400b-9789-0993c5750cfa","order_by":1,"name":"Natalie Layer","email":"","orcid":"","institution":"Klinikum Stuttgart, Stuttgart Cancer Center - Tumorzentrum Eva Mayr-Stihl DE","correspondingAuthor":false,"prefix":"","firstName":"Natalie","middleName":"","lastName":"Layer","suffix":""},{"id":483448426,"identity":"89f797ec-009f-458d-84dc-543811069709","order_by":2,"name":"Christian U. Menzel","email":"","orcid":"","institution":"Klinikum Stuttgart","correspondingAuthor":false,"prefix":"","firstName":"Christian","middleName":"U.","lastName":"Menzel","suffix":""},{"id":483448427,"identity":"81b18c53-7cf4-40bc-b240-84f202df5292","order_by":3,"name":"Martina Müller","email":"","orcid":"","institution":"University Hospital Regensburg","correspondingAuthor":false,"prefix":"","firstName":"Martina","middleName":"","lastName":"Müller","suffix":""},{"id":483448428,"identity":"b390804a-430e-49bb-8f4e-f98b209cae56","order_by":4,"name":"Tobias Schilling","email":"","orcid":"","institution":"Klinikum Stuttgart","correspondingAuthor":false,"prefix":"","firstName":"Tobias","middleName":"","lastName":"Schilling","suffix":""},{"id":483448429,"identity":"e299d572-f49f-4bab-a7c6-3f2d3d95a76b","order_by":5,"name":"Gerald Illerhaus","email":"","orcid":"","institution":"Klinikum Stuttgart, Stuttgart Cancer Center - Tumorzentrum Eva Mayr-Stihl DE","correspondingAuthor":false,"prefix":"","firstName":"Gerald","middleName":"","lastName":"Illerhaus","suffix":""},{"id":483448430,"identity":"975216da-d602-4445-8125-929780949914","order_by":6,"name":"Markus Knott","email":"","orcid":"","institution":"Klinikum Stuttgart, Stuttgart Cancer Center - Tumorzentrum Eva Mayr-Stihl DE","correspondingAuthor":false,"prefix":"","firstName":"Markus","middleName":"","lastName":"Knott","suffix":""},{"id":483448431,"identity":"d33cec5c-3906-451a-9245-55055f8b0cc7","order_by":7,"name":"Alexander Krohn","email":"","orcid":"","institution":"Klinikum Stuttgart","correspondingAuthor":false,"prefix":"","firstName":"Alexander","middleName":"","lastName":"Krohn","suffix":""}],"badges":[],"createdAt":"2025-07-09 14:38:09","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7084787/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7084787/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":86465251,"identity":"0d832382-dbf7-4c91-9437-5c8666ed62f2","added_by":"auto","created_at":"2025-07-11 03:16:48","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1086188,"visible":true,"origin":"","legend":"","description":"","filename":"20250629MMSNLPPaper2GENDERAKJGDCAK003.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7084787/v1_covered_a0c7e29a-730f-4c07-b7d0-95543344a339.pdf"}],"financialInterests":"Competing interest reported. JGDO works for PerMediQ GmbH.\n\nThe other authors declare that they have no conflicts of interest.","formattedTitle":"Uncovering Sex-Specific Symptom Networks: NLP-Based Clustering in Cancer Emergencies","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Natural Language Processing (NLP), Emergency Oncology, Symptom Networks, Patient Stratification, Sex Differences, Free-Text Analysis, Similarity Clustering, Edge Betweenness, Clinical Decision Support, Unstructured Data Analysis, Sex-Specific Symptom Patterns, Learning Cancer Center (LCC), Anamnesis Mining, Resource-Efficient AI, Health Informatics","lastPublishedDoi":"10.21203/rs.3.rs-7084787/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7084787/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eUnderstanding symptom patterns in emergency care of patients with cancer is crucial for accurate stratification and personalized decision-making. We applied natural language processing (NLP) to Emergency Department (ED) records to extract symptom data and linked these records with structured metadata (age, sex, and diagnosis) to construct patient similarity networks. A fine-tuned BioGottBERT model running entirely on secure in-house systems encoded patients as embeddings; pairwise similarities were then calculated to construct a patient graph. Using edge-betweenness clustering, we identified clinically meaningful and stable patient subgroups based on symptom profiles and demographic similarity. We identified distinct stratification patterns among polysymptomatic, oligosymptomatic, and atypical cases, as well as differences in symptom variability across cancer types, including gastrointestinal and lung cancer. Of clinical relevance, our findings underscore the intrinsic role of sex in symptom expression. Our approach demonstrates how NLP and graph-based clustering can uncover latent patient structures from unstructured data, supporting personalized diagnostics and enabling seamless integration into local hospital-based infrastructure and workflows.\u003c/p\u003e","manuscriptTitle":"Uncovering Sex-Specific Symptom Networks: NLP-Based Clustering in Cancer Emergencies","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-07-11 02:52:41","doi":"10.21203/rs.3.rs-7084787/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2026-04-22T16:55:02+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"58016762024585521101613421794894960730","date":"2026-04-09T12:02:16+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-11-23T23:06:00+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"14569399777976260634666063847269497177","date":"2025-11-15T15:20:55+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"300495151200834491892269257186204440251","date":"2025-11-13T15:12:37+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-10-30T09:24:46+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-07-15T12:09:08+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-07-11T08:32:48+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-07-11T02:49:53+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-07-09T14:23:23+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"b10c48d2-8396-4d65-9d5f-bd72a4327fe1","owner":[],"postedDate":"July 11th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":51333778,"name":"Biological sciences/Cancer"},{"id":51333779,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":51333780,"name":"Health sciences/Health care"},{"id":51333781,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2025-10-30T09:38:14+00:00","versionOfRecord":[],"versionCreatedAt":"2025-07-11 02:52:41","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7084787","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7084787","identity":"rs-7084787","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}