NeuraSpeech: A Secure Machine Learning-Blockchain Framework for Speech-Based Amyotrophic Lateral Sclerosis Detection | 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 NeuraSpeech: A Secure Machine Learning-Blockchain Framework for Speech-Based Amyotrophic Lateral Sclerosis Detection Ayoub LOUJA, Abdellah JAMALI, Najib NAJA This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7093942/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 12 You are reading this latest preprint version Abstract Amyotrophic Lateral Sclerosis (ALS) is a neurodegenerative disease that involves the degeneration of motor neurons, resulting in muscle weakness and progressive paralysis. Early diagnosis of ALS remains difficult due to its multifaceted pathophysiology and varied symptoms. This research introduces NeuraSpeech, a new hybrid model that integrates state-of-the-art machine learning algorithms and blockchain technology for ALS detection using speech analysis and secure data exchange. We introduce a multi-modal feature extraction method that combines conventional acoustic features, deep learning representations, non-linear dynamics measures, and multi-resolution analysis. A two-stage feature fusion and selection process selects an optimal subset of 22 features with high discriminative power. Our ensemble classification system integrates conventional machine learning models and deep neural networks using weighted voting. The method attains 97.2% accuracy with ±1.0% standard deviation, showing robust performance across patients. The integration of Hyperledger Fabric on blockchain offers data integrity, privacy, and secure sharing of diagnostic reports among healthcare institutions with 28-55 TPS throughput and 0.9-1.9 seconds latency. Methodological process and results are presented in this paper, showing the ability of NeuraSpeech to improve early diagnosis of ALS while maintaining security and privacy of patient information. Amyotrophic Lateral Sclerosis Machine Learning Blockchain Feature Selection Deep Learning Healthcare Data Security Hyperledger Fabric Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 20 Aug, 2025 Reviews received at journal 14 Aug, 2025 Reviewers agreed at journal 14 Aug, 2025 Reviews received at journal 14 Aug, 2025 Reviews received at journal 29 Jul, 2025 Reviewers agreed at journal 21 Jul, 2025 Reviewers agreed at journal 17 Jul, 2025 Reviewers agreed at journal 15 Jul, 2025 Reviewers invited by journal 15 Jul, 2025 Editor assigned by journal 12 Jul, 2025 Submission checks completed at journal 11 Jul, 2025 First submitted to journal 10 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-7093942","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":486048390,"identity":"796a8206-1d80-4796-96ba-fc45b8ff6235","order_by":0,"name":"Ayoub LOUJA","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA8klEQVRIiWNgGAWjYFAC5gYGBh4ok6ECRIJE8AJGZC1nQCQjMVpgFjK2oYlgA/wSiY2PeWTsGPhnJB+TLpxXG83fDtTyo2IbTi2SMxKbjXl4khkkbqSlSc/cdjx3xmHGBsaeM7dxajG4kdgmzcPDzMBwI8dMmnfbsdwGoBagCwlqqWeQB2uZcyx3PpFaDgMZIC0NNbkbCGmR7HnYbDiH5ziP4ZlnydYzjh3I3QjUchCfX/jZkw8+eNtTLSd3PPng7YKautx55w8ffPCjArcWMGDsAUamQAKIeRgscAC/ehD4AbIPrK6OsOJRMApGwSgYcQAA/ftWVM+/STsAAAAASUVORK5CYII=","orcid":"","institution":"Université Hassan 1er","correspondingAuthor":true,"prefix":"","firstName":"Ayoub","middleName":"","lastName":"LOUJA","suffix":""},{"id":486048391,"identity":"02319973-9b6a-4e30-9aff-6307a86d1b40","order_by":1,"name":"Abdellah JAMALI","email":"","orcid":"","institution":"Université Hassan 1er","correspondingAuthor":false,"prefix":"","firstName":"Abdellah","middleName":"","lastName":"JAMALI","suffix":""},{"id":486048392,"identity":"7d6a5379-03a5-4443-b1af-9a8d744a2811","order_by":2,"name":"Najib NAJA","email":"","orcid":"","institution":"Institut National des Postes et Télécommunications","correspondingAuthor":false,"prefix":"","firstName":"Najib","middleName":"","lastName":"NAJA","suffix":""}],"badges":[],"createdAt":"2025-07-10 14:23:10","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7093942/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7093942/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":86992277,"identity":"f8bc11a9-fe31-43db-ba56-4c12bdf1f8fd","added_by":"auto","created_at":"2025-07-18 04:42:41","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2467963,"visible":true,"origin":"","legend":"","description":"","filename":"SpringerNeuraSpeech.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7093942/v1_covered_e8688f6e-e83c-4cba-b4d5-1da2962bad86.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"NeuraSpeech: A Secure Machine Learning-Blockchain Framework for Speech-Based Amyotrophic Lateral Sclerosis Detection","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"
[email protected]","identity":"multimedia-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mmsj","sideBox":"Learn more about [Multimedia Systems](http://link.springer.com/journal/530)","snPcode":"530","submissionUrl":"https://submission.nature.com/new-submission/530/3","title":"Multimedia Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Amyotrophic Lateral Sclerosis, Machine Learning, Blockchain, Feature Selection, Deep Learning, Healthcare Data Security, Hyperledger Fabric","lastPublishedDoi":"10.21203/rs.3.rs-7093942/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7093942/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAmyotrophic Lateral Sclerosis (ALS) is a neurodegenerative disease that involves the degeneration of motor neurons, resulting in muscle weakness and progressive paralysis. Early diagnosis of ALS remains difficult due to its multifaceted pathophysiology and varied symptoms. This research introduces NeuraSpeech, a new hybrid model that integrates state-of-the-art machine learning algorithms and blockchain technology for ALS detection using speech analysis and secure data exchange. We introduce a multi-modal feature extraction method that combines conventional acoustic features, deep learning representations, non-linear dynamics measures, and multi-resolution analysis. A two-stage feature fusion and selection process selects an optimal subset of 22 features with high discriminative power. Our ensemble classification system integrates conventional machine learning models and deep neural networks using weighted voting. The method attains 97.2% accuracy with \u0026plusmn;1.0% standard deviation, showing robust performance across patients. The integration of Hyperledger Fabric on blockchain offers data integrity, privacy, and secure sharing of diagnostic reports among healthcare institutions with 28-55 TPS throughput and 0.9-1.9 seconds latency. Methodological process and results are presented in this paper, showing the ability of NeuraSpeech to improve early diagnosis of ALS while maintaining security and privacy of patient information.\u003c/p\u003e","manuscriptTitle":"NeuraSpeech: A Secure Machine Learning-Blockchain Framework for Speech-Based Amyotrophic Lateral Sclerosis Detection","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-07-18 04:26:28","doi":"10.21203/rs.3.rs-7093942/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-08-20T09:34:03+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-08-14T16:45:16+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"72524871766173884084086064604594189185","date":"2025-08-14T15:38:37+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-08-14T05:23:58+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-07-29T09:07:07+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"79301113358076568533111958110312975313","date":"2025-07-21T10:50:56+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"315239485448546868660179848446397003090","date":"2025-07-18T02:59:15+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"19301937722435686500900949232598454178","date":"2025-07-16T02:52:52+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-07-15T14:01:59+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-07-12T08:20:40+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-07-11T05:03:20+00:00","index":"","fulltext":""},{"type":"submitted","content":"Multimedia Systems","date":"2025-07-10T14:08:34+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"
[email protected]","identity":"multimedia-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mmsj","sideBox":"Learn more about [Multimedia Systems](http://link.springer.com/journal/530)","snPcode":"530","submissionUrl":"https://submission.nature.com/new-submission/530/3","title":"Multimedia Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"ca1d2bb4-759e-42ce-84fb-0929dec9f47d","owner":[],"postedDate":"July 18th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-02-25T01:24:32+00:00","versionOfRecord":[],"versionCreatedAt":"2025-07-18 04:26:28","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7093942","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7093942","identity":"rs-7093942","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}
Text is read by the "Ask this paper" AI Q&A widget below.
Extraction quality varies by source — PMC NXML preserves structure
cleanly, OA-HTML may include some navigation residue, and OA-PDF can
have broken hyphenation. The publisher copy
(via DOI)
is the canonical version.