Predicting Alzheimer’s Disease Progression Through LSTM-Based Ensemble Learning: An Integrated Clinical Data Analysis Approach

Predicting Alzheimer’s Disease Progression Through LSTM-Based Ensemble Learning: An Integrated Clinical Data Analysis Approach | 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 Predicting Alzheimer’s Disease Progression Through LSTM-Based Ensemble Learning: An Integrated Clinical Data Analysis Approach Sunita jeevangi, Dr. Mahantesh C Elemmi This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9154535/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 global healthcare system faces mounting challenges from Alzheimer’s disease (AD), a debilitating neurodegen-erative condition affecting millions worldwide. This research introduces an innovative computational framework utilizing Long Short-Term Memory (LSTM) architectures combined with ensemble learning techniques to forecast AD diagnosis from multi-dimensional clinical datasets. Our investigation analyzed 2,149 patient records encompassing 34 distinct clinical parameters, including cognitive performance metrics through Mini-Mental State Examination (MMSE), functional capability assessments, behavioral patterns, and comorbidity indicators. The developed LSTM ensemble framework demonstrated exceptional predictive capabilities, attaining 95.35classification accuracy, 94.59ity, and an area under the receiver operating characteristic curve (AUC-ROC) of 0.9411. These results substantially surpass conventional machine learning benchmarks. Analysis of feature contributions identified cognitive assessment scores, functional evaluation metrics, and chronological age as predominant pre-dictive indicators. Our findings underscore the potential of integrated deep learning methodologies for enhanced early-stage AD identification, offering significant implications for clinical decision-support frameworks and individualized therapeutic strategies in neurodegenerative disorder management Biological sciences/Computational biology and bioinformatics Health sciences/Diseases Health sciences/Health care Physical sciences/Mathematics and computing Health sciences/Medical research Alzheimer’s Disease Detection Deep Learning Networks LSTM Architecture Ensemble Classification Clinical Prediction Models Neurodegenerative Disease Forecasting Computational Healthcare Full Text Additional Declarations No competing interests reported. Supplementary Files lstmalzheimersimplementation.py scientificjournalcode.docx Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 11 May, 2026 Reviews received at journal 09 May, 2026 Reviews received at journal 03 May, 2026 Reviewers agreed at journal 03 May, 2026 Reviewers agreed at journal 30 Apr, 2026 Reviewers invited by journal 30 Apr, 2026 Editor assigned by journal 30 Apr, 2026 Editor invited by journal 02 Apr, 2026 Submission checks completed at journal 31 Mar, 2026 First submitted to journal 31 Mar, 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-9154535","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":635053901,"identity":"67dc451d-f8c4-4acd-924c-c36d52d5891b","order_by":0,"name":"Sunita jeevangi","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABDElEQVRIiWNgGAWjYJCCAwwMbFCmgQ2QYGw8QFDLAYSWNJCWBoJaGJBUHEYXwATyM3IPHv5QwyfHL5H87OGXgvN2a9sPA22psYnGpcXgRl7CgQPH2IwlZ6SZG8sY3E7ediYRqOVYWm4DLi0SOQYHDrCxJW44c8BMWgKoxewAUAtjw2GcWuRngLT8Y6vff+b4N6CWc8lm5x/i18JwA6jlYBtbggF7j5nkB4MDdmY3CNhicOaNwYGzfWyGM473lEkzGCQnmN0A2pKAxy/y7TnGHyq+HZPnb2bfJvnjj5292fn0hw8+1NjgdhgEHAOTzDwMDIlglQn4lYNADZhk/MHAYE9Y8SgYBaNgFIw0AAAvGmeRAgsFpwAAAABJRU5ErkJggg==","orcid":"","institution":"RV institute of Technology and Management bangalore,vtu,india","correspondingAuthor":true,"prefix":"","firstName":"Sunita","middleName":"","lastName":"jeevangi","suffix":""},{"id":635053903,"identity":"2e1d4196-d351-4b4e-af1f-f8f8edffa2b3","order_by":1,"name":"Dr. Mahantesh C Elemmi","email":"","orcid":"","institution":"Navkis collge of engineering hassan","correspondingAuthor":false,"prefix":"Dr.","firstName":"Mahantesh","middleName":"C","lastName":"Elemmi","suffix":""}],"badges":[],"createdAt":"2026-03-18 04:39:47","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9154535/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9154535/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108976649,"identity":"e03b9274-cd87-452b-a1d7-0a8616d46152","added_by":"auto","created_at":"2026-05-11 11:27:13","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":191436,"visible":true,"origin":"","legend":"","description":"","filename":"paper210.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9154535/v1_covered_8b9231cd-f974-4bff-b53a-3bf2ba320477.pdf"},{"id":108838080,"identity":"6ad4fd50-c586-4491-9fe6-2c899f3e9006","added_by":"auto","created_at":"2026-05-09 00:20:41","extension":"py","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":15237,"visible":true,"origin":"","legend":"","description":"","filename":"lstmalzheimersimplementation.py","url":"https://assets-eu.researchsquare.com/files/rs-9154535/v1/5274ad37081e70cc46245cbe.py"},{"id":108838081,"identity":"4e670af2-b438-432d-9198-f74e3a85bf90","added_by":"auto","created_at":"2026-05-09 00:20:41","extension":"docx","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":36586,"visible":true,"origin":"","legend":"","description":"","filename":"scientificjournalcode.docx","url":"https://assets-eu.researchsquare.com/files/rs-9154535/v1/45623e341920f1f6f893958d.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"Predicting Alzheimer’s Disease Progression Through LSTM-Based Ensemble Learning: An Integrated Clinical Data Analysis Approach","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 Detection, Deep Learning Networks, LSTM Architecture, Ensemble Classification, Clinical Prediction Models, Neurodegenerative Disease Forecasting, Computational Healthcare","lastPublishedDoi":"10.21203/rs.3.rs-9154535/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9154535/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The global healthcare system faces mounting challenges from Alzheimer’s disease (AD), a debilitating neurodegen-erative condition affecting millions worldwide. This research introduces an innovative computational framework utilizing Long Short-Term Memory (LSTM) architectures combined with ensemble learning techniques to forecast AD diagnosis from multi-dimensional clinical datasets. Our investigation analyzed 2,149 patient records encompassing 34 distinct clinical parameters, including cognitive performance metrics through Mini-Mental State Examination (MMSE), functional capability assessments, behavioral patterns, and comorbidity indicators. The developed LSTM ensemble framework demonstrated exceptional predictive capabilities, attaining 95.35classification accuracy, 94.59ity, and an area under the receiver operating characteristic curve (AUC-ROC) of 0.9411. These results substantially surpass conventional machine learning benchmarks. Analysis of feature contributions identified cognitive assessment scores, functional evaluation metrics, and chronological age as predominant pre-dictive indicators. Our findings underscore the potential of integrated deep learning methodologies for enhanced early-stage AD identification, offering significant implications for clinical decision-support frameworks and individualized therapeutic strategies in neurodegenerative disorder management","manuscriptTitle":"Predicting Alzheimer’s Disease Progression Through LSTM-Based Ensemble Learning: An Integrated Clinical Data Analysis Approach","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-09 00:20:37","doi":"10.21203/rs.3.rs-9154535/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-05-11T13:06:50+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-10T01:57:13+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-03T23:52:16+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"277258874225337120900886268829176946747","date":"2026-05-03T23:24:12+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"306655247304010628546778580561313852414","date":"2026-05-01T01:25:32+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-05-01T00:08:25+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-05-01T00:05:33+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-04-02T11:19:09+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-03-31T07:05:01+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2026-03-31T06:56:28+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":"696d1f90-6cc2-48f8-9412-2017fad1412c","owner":[],"postedDate":"May 9th, 2026","published":true,"recentEditorialEvents":[{"type":"decision","content":"Revision requested","date":"2026-05-11T13:06:50+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-10T01:57:13+00:00","index":106,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-03T23:52:16+00:00","index":103,"fulltext":""},{"type":"reviewerAgreed","content":"277258874225337120900886268829176946747","date":"2026-05-03T23:24:12+00:00","index":102,"fulltext":""},{"type":"reviewerAgreed","content":"306655247304010628546778580561313852414","date":"2026-05-01T01:25:32+00:00","index":96,"fulltext":""},{"type":"reviewersInvited","content":"13","date":"2026-05-01T00:08:25+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-05-01T00:05:33+00:00","index":"","fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":67588655,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":67588656,"name":"Health sciences/Diseases"},{"id":67588657,"name":"Health sciences/Health care"},{"id":67588658,"name":"Physical sciences/Mathematics and computing"},{"id":67588659,"name":"Health sciences/Medical research"}],"tags":[],"updatedAt":"2026-05-13T07:40:19+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-09 00:20:37","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9154535","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9154535","identity":"rs-9154535","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}