Protein-based Diagnosis and Analysis of Co-pathologies Across Neurodegenerative Diseases: Large-Scale AI-Boosted CSF and Plasma Classification

Protein-based Diagnosis and Analysis of Co-pathologies Across Neurodegenerative Diseases: Large-Scale AI-Boosted CSF and Plasma Classification | 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 Biological Sciences - Article Protein-based Diagnosis and Analysis of Co-pathologies Across Neurodegenerative Diseases: Large-Scale AI-Boosted CSF and Plasma Classification Carlos Cruchaga, Ying Xu, Daniel Western, Gyujin Heo, Kwangsik Nho, and 23 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6933762/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 Neurodegenerative diseases (including Alzheimer’s disease, Parkinson’s disease, Frontotemporal dementia, and Dementia with Lewy bodies) pose diagnostic challenges due to overlapping pathology and clinical heterogeneity. We leveraged proteomic data from more than 21,000 cerebrospinal fluid and plasma samples to develop and validate explainable, boosting-based multi-disease AI classifiers. The models achieved weighted AUCs in the testing datasets of 0.97 for CSF and 0.88 for plasma, equivalent to traditional biomarkers. The model was validated with neuropathological and clinical data, confirming robust generalizability without any retraining. Using zero-shot learning, we classified disease subtypes including autosomal dominant AD and prodromal PD and clarified disease states for those with conflicting clinical information. The model also showed the ability to prioritize cognitively normal individuals at disease risk. This framework enabled the identification and quantification of continuous, individual-level disease probabilities that allow for the quantification of overlap across diseases and co-pathologies within an individual. Through this work, we establish a benchmark computational framework for enhancing diagnostic precision in NDs. Biological sciences/Computational biology and bioinformatics/Proteome informatics Biological sciences/Computational biology and bioinformatics/Machine learning Biological sciences/Neuroscience/Diseases of the nervous system/Neurodegeneration Full Text Additional Declarations Yes there is potential Competing Interest. CC has received research support from GSK and EISAI. CC is a member of the scientific advisory board of Circular Genomics and owns stocks. CC is a member of the scientific advisory board of ADmit. There is an invention disclosure for the prediction models, including protein IDs, alternative proteins and weights, cut off and algorithms. CC has served on scientific advisory for GSK and Novo Nordisk. AJS has received support from Avid Radiopharmaceuticals, a subsidiary of Eli Lilly (in kind contribution of PET tracer precursor) and participated in Scientific Advisory Boards (Bayer Oncology, Eisai, Novo Nordisk, and Siemens Medical Solutions USA, Inc) and an Observational Study Monitoring Board (MESA, NIH NHLBI), as well as several other NIA External Advisory Committees. He also serves as Editor-in-Chief of Brain Imaging and Behavior, a Springer-Nature Journal. Supplementary Files 04CSFPlasmaClassifierSupplementaryTables.xlsx Supplementary Tables 03CSFPlasmaSupplementaryFigures.docx Supplementary Figures 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-6933762","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Biological Sciences - Article","associatedPublications":[],"authors":[{"id":493060877,"identity":"764af9b4-f81f-428b-929e-64d4bc1a42bb","order_by":0,"name":"Carlos Cruchaga","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA1ElEQVRIiWNgGAWjYJACZjDJ3gAiLYA4gVgtPAdAqiVI0SKRQKQW/tlnDD8X1NTK8898Yyb584cEAz97jgFeLRLncoylZxw7bjjjdo6ZNA/QFsmeN/i1GPDwmDHzsB1j3CCdu00a5DCDGwRsgWj5d8x+g+TZbZI/gFrsidLC21aTuEGCd5sEyGEGEoT8coatWJq370DyjDP5n6150iR4JM48K8Crhb+HeeNnnm91tv3txxJv/rCxkeNvT96AVwsUHIazeIhRDgJ1xCocBaNgFIyCkQgAcPo8e7VqSz0AAAAASUVORK5CYII=","orcid":"https://orcid.org/0000-0002-0276-2899","institution":"Washington University School of Medicine","correspondingAuthor":true,"prefix":"","firstName":"Carlos","middleName":"","lastName":"Cruchaga","suffix":""},{"id":493060878,"identity":"3565ded2-8555-43b3-b1d3-693a00a125dc","order_by":1,"name":"Ying Xu","email":"","orcid":"https://orcid.org/0009-0006-0387-2439","institution":"Washington University in St Louis","correspondingAuthor":false,"prefix":"","firstName":"Ying","middleName":"","lastName":"Xu","suffix":""},{"id":493060879,"identity":"5d088ca3-7f92-4172-895c-c07797043ff9","order_by":2,"name":"Daniel Western","email":"","orcid":"https://orcid.org/0000-0003-3725-9553","institution":"Department of Psychiatry, Washington University School of Medicine, St. Louis, MO, USA","correspondingAuthor":false,"prefix":"","firstName":"Daniel","middleName":"","lastName":"Western","suffix":""},{"id":493060880,"identity":"39f66cc2-d9c9-4b1e-8d7b-6b9249a143ff","order_by":3,"name":"Gyujin Heo","email":"","orcid":"https://orcid.org/0000-0003-3499-2848","institution":"Washington University School of Medicine","correspondingAuthor":false,"prefix":"","firstName":"Gyujin","middleName":"","lastName":"Heo","suffix":""},{"id":493060881,"identity":"2fa036c8-866a-4f51-8ebc-d856f5a08493","order_by":4,"name":"Kwangsik Nho","email":"","orcid":"","institution":"Indiana University School of Medicine","correspondingAuthor":false,"prefix":"","firstName":"Kwangsik","middleName":"","lastName":"Nho","suffix":""},{"id":493060882,"identity":"5f6eec5d-b5be-435b-bcf2-fac82192fffd","order_by":5,"name":"Yen-Ning Huang","email":"","orcid":"","institution":"Indiana University","correspondingAuthor":false,"prefix":"","firstName":"Yen-Ning","middleName":"","lastName":"Huang","suffix":""},{"id":493060883,"identity":"c0c211c4-474b-45bd-8e59-947296f3f97a","order_by":6,"name":"Shiwei Liu","email":"","orcid":"https://orcid.org/0000-0003-4711-5959","institution":"Indiana University","correspondingAuthor":false,"prefix":"","firstName":"Shiwei","middleName":"","lastName":"Liu","suffix":""},{"id":493060884,"identity":"935ac4bd-10dc-4e20-8683-2cec4000b40d","order_by":7,"name":"Hamilton Oh","email":"","orcid":"https://orcid.org/0000-0001-8192-7593","institution":"Icahn School of Medicine at Mount Sinai","correspondingAuthor":false,"prefix":"","firstName":"Hamilton","middleName":"","lastName":"Oh","suffix":""},{"id":493060885,"identity":"6fbe1c20-f856-497c-a26b-ea99473f08c5","order_by":8,"name":"Yike Chen","email":"","orcid":"https://orcid.org/0009-0003-9181-8608","institution":"Washington University, School of Medicine","correspondingAuthor":false,"prefix":"","firstName":"Yike","middleName":"","lastName":"Chen","suffix":""},{"id":493060886,"identity":"8288cf52-25c2-4a13-8b20-389a04b8358a","order_by":9,"name":"Jigyasha Timsina","email":"","orcid":"https://orcid.org/0000-0003-4794-9187","institution":"Department of Psychiatry, Washington University School of Medicine, St. Louis, MO, USA","correspondingAuthor":false,"prefix":"","firstName":"Jigyasha","middleName":"","lastName":"Timsina","suffix":""},{"id":493060887,"identity":"5b589629-c70e-401a-a220-f4eb2fd16036","order_by":10,"name":"Menghan Liu","email":"","orcid":"https://orcid.org/0009-0008-9902-5983","institution":"Washington University in St. Louis","correspondingAuthor":false,"prefix":"","firstName":"Menghan","middleName":"","lastName":"Liu","suffix":""},{"id":493060888,"identity":"a044e0f5-02be-421c-a9ac-80482f88f9ea","order_by":11,"name":"Yixu Tang","email":"","orcid":"","institution":"Washington University in St. Louis","correspondingAuthor":false,"prefix":"","firstName":"Yixu","middleName":"","lastName":"Tang","suffix":""},{"id":493060889,"identity":"7685ee94-69ab-461b-bf5e-4bcf7641967b","order_by":12,"name":"Katherine Gong","email":"","orcid":"https://orcid.org/0009-0008-7614-9545","institution":"Washington University, School of Medicine","correspondingAuthor":false,"prefix":"","firstName":"Katherine","middleName":"","lastName":"Gong","suffix":""},{"id":493060890,"identity":"3bd84b68-82e5-4cf9-b430-2e0f1c029193","order_by":13,"name":"John Budde","email":"","orcid":"https://orcid.org/0000-0001-7778-7276","institution":"Washington University in St. Louis","correspondingAuthor":false,"prefix":"","firstName":"John","middleName":"","lastName":"Budde","suffix":""},{"id":493060891,"identity":"c485f54f-e1ed-4bf9-8d70-5e1e2359da80","order_by":14,"name":"Varsha Krish","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Varsha","middleName":"","lastName":"Krish","suffix":""},{"id":493060892,"identity":"c577ddf3-52e3-4ef1-ae51-ca4710779490","order_by":15,"name":"Farhad Imam","email":"","orcid":"https://orcid.org/0000-0003-2854-2568","institution":"Gates Ventures","correspondingAuthor":false,"prefix":"","firstName":"Farhad","middleName":"","lastName":"Imam","suffix":""},{"id":493060893,"identity":"80bdc42a-8430-4f25-ba82-ef72a7dbbf5b","order_by":16,"name":"Raquel Puerta","email":"","orcid":"https://orcid.org/0000-0002-1191-5893","institution":"Ace Alzheimer Center Barcelona – Universitat Internacional de Catalunya. Universitat de Barcelona (UB)","correspondingAuthor":false,"prefix":"","firstName":"Raquel","middleName":"","lastName":"Puerta","suffix":""},{"id":493060894,"identity":"23eca831-4bb1-4e4b-b562-6b188ce3d8ab","order_by":17,"name":"Amanda Cano","email":"","orcid":"","institution":"Fundacio ACE","correspondingAuthor":false,"prefix":"","firstName":"Amanda","middleName":"","lastName":"Cano","suffix":""},{"id":493060895,"identity":"f4809e91-aa46-49d8-95fa-fa272076ea9c","order_by":18,"name":"Marta Marquié","email":"","orcid":"https://orcid.org/0000-0002-0660-0950","institution":"ACE Alzheimer Center Barcelona","correspondingAuthor":false,"prefix":"","firstName":"Marta","middleName":"","lastName":"Marquié","suffix":""},{"id":493060896,"identity":"344ccbdc-e5dc-4ae1-a0dc-c1c4b834df48","order_by":19,"name":"Mercè Boada","email":"","orcid":"https://orcid.org/0000-0003-2617-3009","institution":"Universitat Internacional de Catalunya","correspondingAuthor":false,"prefix":"","firstName":"Mercè","middleName":"","lastName":"Boada","suffix":""},{"id":493060897,"identity":"31b8b333-95e3-4139-9199-510111ba0532","order_by":20,"name":"Pau Pastor","email":"","orcid":"https://orcid.org/0000-0002-7493-8777","institution":"Fundació Docència i Recerca MútuaTerrassa","correspondingAuthor":false,"prefix":"","firstName":"Pau","middleName":"","lastName":"Pastor","suffix":""},{"id":493060898,"identity":"58fc2152-e16f-4bfb-aa65-4327d98e5759","order_by":21,"name":"Agustín Ruiz","email":"","orcid":"https://orcid.org/0000-0003-2633-2495","institution":"Ace Alzheimer Center Barcelona","correspondingAuthor":false,"prefix":"","firstName":"Agustín","middleName":"","lastName":"Ruiz","suffix":""},{"id":493060899,"identity":"0329a015-5885-46bc-820c-65caa4fa33b0","order_by":22,"name":"Maria Fernández","email":"","orcid":"","institution":"Washington University School of Medicine","correspondingAuthor":false,"prefix":"","firstName":"Maria","middleName":"","lastName":"Fernández","suffix":""},{"id":493060900,"identity":"309986c4-db6e-42aa-ad9b-a228363cdbbd","order_by":23,"name":"David Bennett","email":"","orcid":"","institution":"Rush University Medical Center","correspondingAuthor":false,"prefix":"","firstName":"David","middleName":"","lastName":"Bennett","suffix":""},{"id":493060901,"identity":"3c8a5e06-fb4b-41fc-9d8a-a2e0c394608c","order_by":24,"name":"Gregory Klein","email":"","orcid":"","institution":"Rush University","correspondingAuthor":false,"prefix":"","firstName":"Gregory","middleName":"","lastName":"Klein","suffix":""},{"id":493060902,"identity":"ddcf88b7-94b9-4de4-a22b-eb104f73518f","order_by":25,"name":"Tony Wyss-Coray","email":"","orcid":"https://orcid.org/0000-0001-5893-0831","institution":"Stanford University","correspondingAuthor":false,"prefix":"","firstName":"Tony","middleName":"","lastName":"Wyss-Coray","suffix":""},{"id":493060903,"identity":"fafb643f-cf46-41cb-82b5-e96917d2d17c","order_by":26,"name":"Andrew Saykin","email":"","orcid":"https://orcid.org/0000-0002-1376-8532","institution":"Indiana University School of Medicine","correspondingAuthor":false,"prefix":"","firstName":"Andrew","middleName":"","lastName":"Saykin","suffix":""},{"id":493060904,"identity":"89dc76dc-98b7-4120-a93e-55ccaa4f1e02","order_by":27,"name":"Muhammad Ali","email":"","orcid":"https://orcid.org/0000-0002-1399-6631","institution":"Washington University School of Medicine","correspondingAuthor":false,"prefix":"","firstName":"Muhammad","middleName":"","lastName":"Ali","suffix":""}],"badges":[],"createdAt":"2025-06-19 21:50:30","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6933762/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6933762/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":93936986,"identity":"29bb6627-9c0f-423f-8e49-49d3818cf9db","added_by":"auto","created_at":"2025-10-20 13:05:08","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1593447,"visible":true,"origin":"","legend":"","description":"","filename":"01CSFPlasmaClassifierManuscriptV2PUB.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6933762/v1_covered_7b2b0b68-7220-4d03-8767-c4f20dc3e3c0.pdf"},{"id":87970978,"identity":"4b0efe6f-8c01-4bb2-91f4-2ac0d82e9dba","added_by":"auto","created_at":"2025-07-31 02:56:53","extension":"xlsx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":2653441,"visible":true,"origin":"","legend":"Supplementary Tables","description":"","filename":"04CSFPlasmaClassifierSupplementaryTables.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-6933762/v1/6f183a6c5d8f1802901bff39.xlsx"},{"id":87970979,"identity":"616422e2-b4a1-4450-a7a7-35f58784d48a","added_by":"auto","created_at":"2025-07-31 02:56:53","extension":"docx","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":4650922,"visible":true,"origin":"","legend":"Supplementary Figures","description":"","filename":"03CSFPlasmaSupplementaryFigures.docx","url":"https://assets-eu.researchsquare.com/files/rs-6933762/v1/1e61f5c63f853f512ece96fe.docx"}],"financialInterests":"\u003cb\u003eYes\u003c/b\u003e there is potential Competing Interest.\nCC has received research support from GSK and EISAI. CC is a member of the scientific advisory board of Circular Genomics and owns stocks. CC is a member of the scientific advisory board of ADmit. There is an invention disclosure for the prediction models, including protein IDs, alternative proteins and weights, cut off and algorithms. CC has served on scientific advisory for GSK and Novo Nordisk. AJS has received support from Avid Radiopharmaceuticals, a subsidiary of Eli Lilly (in kind contribution of PET tracer precursor) and participated in Scientific Advisory Boards (Bayer Oncology, Eisai, Novo Nordisk, and Siemens Medical Solutions USA, Inc) and an Observational Study Monitoring Board (MESA, NIH NHLBI), as well as several other NIA External Advisory Committees. He also serves as Editor-in-Chief of Brain Imaging and Behavior, a Springer-Nature Journal.","formattedTitle":"Protein-based Diagnosis and Analysis of Co-pathologies Across Neurodegenerative Diseases: Large-Scale AI-Boosted CSF and Plasma Classification","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"","lastPublishedDoi":"10.21203/rs.3.rs-6933762/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6933762/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Neurodegenerative diseases (including Alzheimer’s disease, Parkinson’s disease, Frontotemporal dementia, and Dementia with Lewy bodies) pose diagnostic challenges due to overlapping pathology and clinical heterogeneity. We leveraged proteomic data from more than 21,000 cerebrospinal fluid and plasma samples to develop and validate explainable, boosting-based multi-disease AI classifiers. The models achieved weighted AUCs in the testing datasets of 0.97 for CSF and 0.88 for plasma, equivalent to traditional biomarkers. The model was validated with neuropathological and clinical data, confirming robust generalizability without any retraining. Using zero-shot learning, we classified disease subtypes including autosomal dominant AD and prodromal PD and clarified disease states for those with conflicting clinical information. The model also showed the ability to prioritize cognitively normal individuals at disease risk. This framework enabled the identification and quantification of continuous, individual-level disease probabilities that allow for the quantification of overlap across diseases and co-pathologies within an individual. Through this work, we establish a benchmark computational framework for enhancing diagnostic precision in NDs.","manuscriptTitle":"Protein-based Diagnosis and Analysis of Co-pathologies Across Neurodegenerative Diseases: Large-Scale AI-Boosted CSF and Plasma Classification","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-07-31 02:56:49","doi":"10.21203/rs.3.rs-6933762/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":"500664ed-2381-43bc-bfb9-5909fa156279","owner":[],"postedDate":"July 31st, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":52354750,"name":"Biological sciences/Computational biology and bioinformatics/Proteome informatics"},{"id":52354751,"name":"Biological sciences/Computational biology and bioinformatics/Machine learning"},{"id":52354752,"name":"Biological sciences/Neuroscience/Diseases of the nervous system/Neurodegeneration"}],"tags":[],"updatedAt":"2025-10-20T12:56:56+00:00","versionOfRecord":[],"versionCreatedAt":"2025-07-31 02:56:49","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6933762","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6933762","identity":"rs-6933762","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}