Machine Learning–Based Prediction of Future MMSE Scores in Alzheimer’s Disease Using Plasma pTau217 and CSF pTau181/tTau Ratio in a Real-World Cohort

Machine Learning–Based Prediction of Future MMSE Scores in Alzheimer’s Disease Using Plasma pTau217 and CSF pTau181/tTau Ratio in a Real-World Cohort | 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 Machine Learning–Based Prediction of Future MMSE Scores in Alzheimer’s Disease Using Plasma pTau217 and CSF pTau181/tTau Ratio in a Real-World Cohort Davide Cianca, Edoardo Guido Torrigiani, Lorenzo Gaetani, Giovanna Nardi, and 6 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9222674/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 The prediction of cognitive decline in patients with Alzheimer’s disease (AD) is a compelling clinical challenge for treatment planning in the forthcoming era of disease modifying therapies. Fluid biomarkers of AD have proven their prognostic value, with various degrees of reliability, yet their integration into quantitative predictive models for future cognitive scores remains scarcely explored. In this study, we developed an ElasticNet model to predict MMSE scores at follow-up in a real-world cohort of 100 patients with cerebrospinal fluid (CSF) confirmed AD (CSF A+/T+), in all its clinical stages. A systematic feature selection procedure evaluated all available CSF and plasma biomarkers (CSF Aβ42/40, pTau181, tTau and plasma Aβ42/40, pTau181, pTau217, NfL and derived ratios) individually and in combinations of two and in panel models. Plasma pTau217 and CSF pTau181/tTau were identified as the optimal biomarker combination, achieving a strong cross-validated performance (R2 = 0.760; 95% CI: 0.681–0.845). Plasma pTau217 was the strongest biological predictor (permutation p = 0.002), while CSF pTau181/tTau ratio provided a smaller but significant independent contribution (p = 0.010). Our results prove that integrating plasma and CSF biomarkers into a machine learning model allows for proper quantitative estimation of cognitive decline trajectories in patients with biologically confirmed AD. Health sciences/Biomarkers Health sciences/Neurology Biological sciences/Neuroscience Alzheimer’s Disease Biomarkers CSF plasma Machine Learning Amyloid Phosphorylated Tau Full Text Additional Declarations Competing interest reported. G.B. received honoraria from Fujirebio and completed paid consultancies for the Parkinson’s Foundation; he received travel/educational grants from Fujirebio and the Alzheimer’s Association. L.P. served as a member of Advisory Boards for Fujirebio, IBL, Roche and Merck. L.Ga. has participated in advisory boards for and received writing or speaker honoraria and travel grants from Biogen, Eisai, Euroimmun, Fujirebio, Lilly, Novartis, Roche and Siemens Healthineers. E.G.T., D.C., F.P.P., G.N., I.N., L.Gm. and D.Ch. have nothing to disclose. Supplementary Files graficocorrelazionefeature.png graficobootstrapR2.png Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 27 Apr, 2026 Reviews received at journal 22 Apr, 2026 Reviews received at journal 21 Apr, 2026 Reviewers agreed at journal 21 Apr, 2026 Reviewers agreed at journal 21 Apr, 2026 Reviewers invited by journal 21 Apr, 2026 Editor assigned by journal 21 Apr, 2026 Editor invited by journal 14 Apr, 2026 Submission checks completed at journal 10 Apr, 2026 First submitted to journal 10 Apr, 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-9222674","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":627985521,"identity":"6296a1d4-21c2-46c2-9aa3-5133cf749777","order_by":0,"name":"Davide Cianca","email":"","orcid":"","institution":"University of Perugia","correspondingAuthor":false,"prefix":"","firstName":"Davide","middleName":"","lastName":"Cianca","suffix":""},{"id":627985522,"identity":"8611635e-8d62-4a3a-8ad3-a76478d0c077","order_by":1,"name":"Edoardo Guido Torrigiani","email":"","orcid":"","institution":"University of Perugia","correspondingAuthor":false,"prefix":"","firstName":"Edoardo","middleName":"Guido","lastName":"Torrigiani","suffix":""},{"id":627985524,"identity":"e931c068-b656-4557-9475-c60218166398","order_by":2,"name":"Lorenzo Gaetani","email":"","orcid":"","institution":"University of Perugia","correspondingAuthor":false,"prefix":"","firstName":"Lorenzo","middleName":"","lastName":"Gaetani","suffix":""},{"id":627985526,"identity":"db741ef4-cb1e-4211-9d81-6a982799451e","order_by":3,"name":"Giovanna Nardi","email":"","orcid":"","institution":"University of Perugia","correspondingAuthor":false,"prefix":"","firstName":"Giovanna","middleName":"","lastName":"Nardi","suffix":""},{"id":627985527,"identity":"39e4a34f-7b9c-475a-a436-8f1d628d7488","order_by":4,"name":"Federico Paolini Paoletti","email":"","orcid":"","institution":"University of Perugia","correspondingAuthor":false,"prefix":"","firstName":"Federico","middleName":"Paolini","lastName":"Paoletti","suffix":""},{"id":627985528,"identity":"3e5ae120-cb31-4057-a4e8-9389ea3dd0f4","order_by":5,"name":"Davide Chiasserini","email":"","orcid":"","institution":"University of Perugia","correspondingAuthor":false,"prefix":"","firstName":"Davide","middleName":"","lastName":"Chiasserini","suffix":""},{"id":627985529,"identity":"b8c06e08-ea68-4ce6-aea2-3350da4634e1","order_by":6,"name":"Lucilla Parnetti","email":"","orcid":"","institution":"University of Perugia","correspondingAuthor":false,"prefix":"","firstName":"Lucilla","middleName":"","lastName":"Parnetti","suffix":""},{"id":627985530,"identity":"4a7631a8-4cbc-41b1-8be1-ca0570e19b98","order_by":7,"name":"Igor Neri","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAyklEQVRIiWNgGAWjYBACNjiDvYGBIQFZhLAWngNQLQT1wIFEAropOAAf/+JjHxh32OTzSb4xe/BwRy0Dn3wDAYdJPEuewXgmzbJNOsfcIPHMccIOY5M4Y8zA2HbYgE06x0wise0Y0Vr+G7BJniFWC38PSMsBAzYJHpCWGmJsYUtmSGxLNmDjSSuTSDxzgIeNLQG/Fvn+w4cZPrbZGci3H94m+XNHnZx88wEC1oCiA24sY8NhHgLqgYAf2UzGhjrCOkbBKBgFo2DEAQCixTTlp5b4eAAAAABJRU5ErkJggg==","orcid":"","institution":"University of Perugia","correspondingAuthor":true,"prefix":"","firstName":"Igor","middleName":"","lastName":"Neri","suffix":""},{"id":627985531,"identity":"7817325c-9d06-416d-b5a4-b688869cf00d","order_by":8,"name":"Giovanni Bellomo","email":"","orcid":"","institution":"Link Campus University","correspondingAuthor":false,"prefix":"","firstName":"Giovanni","middleName":"","lastName":"Bellomo","suffix":""},{"id":627985532,"identity":"0ea40af4-61ea-4cf1-a5cc-0eb4127b2f0d","order_by":9,"name":"Luca Gammaitoni","email":"","orcid":"","institution":"University of Perugia","correspondingAuthor":false,"prefix":"","firstName":"Luca","middleName":"","lastName":"Gammaitoni","suffix":""}],"badges":[],"createdAt":"2026-03-25 11:53:46","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9222674/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9222674/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":107872249,"identity":"61298c85-c3eb-47b7-b7eb-141b5357867a","added_by":"auto","created_at":"2026-04-27 07:56:26","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1791232,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9222674/v1_covered_00dc5db8-a1c3-47ee-8a77-e48d383d9207.pdf"},{"id":107857109,"identity":"e938520a-e205-4ec8-8ebe-0c74c95abb43","added_by":"auto","created_at":"2026-04-27 04:10:32","extension":"png","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":295797,"visible":true,"origin":"","legend":"","description":"","filename":"graficocorrelazionefeature.png","url":"https://assets-eu.researchsquare.com/files/rs-9222674/v1/91652ea2bcf3ff6646b499e9.png"},{"id":107870342,"identity":"3085b986-38e3-47d7-98ea-9c730cd55ed7","added_by":"auto","created_at":"2026-04-27 07:39:26","extension":"png","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":120157,"visible":true,"origin":"","legend":"","description":"","filename":"graficobootstrapR2.png","url":"https://assets-eu.researchsquare.com/files/rs-9222674/v1/31f2fcd0df5308edd5bd9d10.png"}],"financialInterests":"Competing interest reported. G.B. received honoraria from Fujirebio and completed paid consultancies for the Parkinson’s Foundation; he received travel/educational grants from Fujirebio and the Alzheimer’s Association. L.P. served as a member of Advisory Boards for Fujirebio, IBL, Roche and Merck. L.Ga. has participated in advisory boards for and received writing or speaker honoraria and travel grants from Biogen, Eisai, Euroimmun, Fujirebio, Lilly, Novartis, Roche and Siemens Healthineers. E.G.T., D.C., F.P.P., G.N., I.N., L.Gm. and D.Ch. have nothing to disclose.","formattedTitle":"\u003cp\u003eMachine Learning–Based Prediction of Future MMSE Scores in Alzheimer’s Disease Using Plasma pTau217 and CSF pTau181/tTau Ratio in a Real-World Cohort\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"Alzheimer’s Disease, Biomarkers, CSF, plasma, Machine Learning, Amyloid, Phosphorylated Tau","lastPublishedDoi":"10.21203/rs.3.rs-9222674/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9222674/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe prediction of cognitive decline in patients with Alzheimer’s disease (AD) is a compelling clinical challenge for treatment planning in the forthcoming era of disease modifying therapies. Fluid biomarkers of AD have proven their prognostic value, with various degrees of reliability, yet their integration into quantitative predictive models for future cognitive scores remains scarcely explored. In this study, we developed an ElasticNet model to predict MMSE scores at follow-up in a real-world cohort of 100 patients with cerebrospinal fluid (CSF) confirmed AD (CSF A+/T+), in all its clinical stages. A systematic feature selection procedure evaluated all available CSF and plasma biomarkers (CSF Aβ42/40, pTau181, tTau and plasma Aβ42/40, pTau181, pTau217, NfL and derived ratios) individually and in combinations of two and in panel models. Plasma pTau217 and CSF pTau181/tTau were identified as the optimal biomarker combination, achieving a strong cross-validated performance (R2 = 0.760; 95% CI: 0.681–0.845). Plasma pTau217 was the strongest biological predictor (permutation p = 0.002), while CSF pTau181/tTau ratio provided a smaller but significant independent contribution (p = 0.010). Our results prove that integrating plasma and CSF biomarkers into a machine learning model allows for proper quantitative estimation of cognitive decline trajectories in patients with biologically confirmed AD.\u003c/p\u003e","manuscriptTitle":"Machine Learning–Based Prediction of Future MMSE Scores in Alzheimer’s Disease Using Plasma pTau217 and CSF pTau181/tTau Ratio in a Real-World Cohort","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-27 04:10:29","doi":"10.21203/rs.3.rs-9222674/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-04-27T08:41:02+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-22T18:29:48+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-21T19:18:42+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"177147750088007611148628983356537060554","date":"2026-04-21T16:23:58+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"225741967587236633079736571032156175045","date":"2026-04-21T14:52:21+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-21T14:20:31+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-04-21T14:09:06+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-04-14T10:10:32+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-04-10T14:05:50+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2026-04-10T12:36:22+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":"49c30d60-c850-4a7a-a28c-db615aac4679","owner":[],"postedDate":"April 27th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":67044984,"name":"Health sciences/Biomarkers"},{"id":67044985,"name":"Health sciences/Neurology"},{"id":67044986,"name":"Biological sciences/Neuroscience"}],"tags":[],"updatedAt":"2026-05-06T11:08:20+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-27 04:10:29","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9222674","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9222674","identity":"rs-9222674","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}