An Interpretable and Auditable Pipeline for Robust Multi-Cohort Detection of Parkinson’s Disease from Voice Data with Data Leakage Prevention

An Interpretable and Auditable Pipeline for Robust Multi-Cohort Detection of Parkinson’s Disease from Voice Data with Data Leakage Prevention | 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 An Interpretable and Auditable Pipeline for Robust Multi-Cohort Detection of Parkinson’s Disease from Voice Data with Data Leakage Prevention Luana Dantas Pontes Espínola Casado, Ingrid Gabrielly Câmara Lira, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9430849/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 Parkinson’s disease (PD) is a progressive neurodegenerative disorder characterized by early vocal changes thatserve as crucial prodromal biomarkers. This work presents an interpretable and auditable machine learningpipeline for robust PD detection through voice analysis, integrating three heterogeneous public datasets into aunified cohort of 996 recordings from 332 independent subjects. To strictly mitigate subject-level data leakage—astructural flaw endemic to the PD voice literature—the pipeline applies a Leave-One-Subject-Out (LOSO)validation protocol and confines SMOTE-based class balancing exclusively to training folds. A soft-votingensemble of Logistic Regression, Support Vector Machine, and Random Forest achieves a subject-level Area Underthe ROC Curve (AUC) of 0.8836, with a sensitivity of 88.60% and specificity of 70.19%. A label permutationtest, in which the AUC collapses to 0.556, mathematically confirms the absence of trivial target leakage. Featureimportance analysis reveals that Mel-Frequency Cepstral Coefficients (MFCCs) and the Harmonics-to-NoiseRatio (HNR) are the dominant predictors, consistent with the known pathophysiology of hypokinetic dysarthria.This study establishes a reproducible, realistic benchmark and a rigorously audited methodological foundationfor voice-based AI triage systems in telemedicine. Health sciences/Biomarkers Biological sciences/Computational biology and bioinformatics Health sciences/Diseases Health sciences/Neurology Biological sciences/Neuroscience Parkinson’s disease vocal biomarkers machine learning data leakage prevention ensemble classifiers LOSO validation Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 18 May, 2026 Reviewers agreed at journal 15 May, 2026 Reviewers agreed at journal 15 May, 2026 Reviews received at journal 14 May, 2026 Reviewers agreed at journal 14 May, 2026 Reviewers invited by journal 13 May, 2026 Editor assigned by journal 12 May, 2026 Editor invited by journal 12 May, 2026 Submission checks completed at journal 28 Apr, 2026 First submitted to journal 28 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-9430849","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":640225571,"identity":"ad45464d-98d8-4b98-a875-571b947abb68","order_by":0,"name":"Luana Dantas Pontes Espínola Casado","email":"data:image/png;base64,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","orcid":"","institution":"Universidade Federal Rural do Semi-Árido","correspondingAuthor":true,"prefix":"","firstName":"Luana","middleName":"Dantas Pontes Espínola","lastName":"Casado","suffix":""},{"id":640225575,"identity":"747a1149-ecaf-43cf-bce4-45ba661d4627","order_by":1,"name":"Ingrid Gabrielly Câmara Lira","email":"","orcid":"","institution":"Universidade Federal Rural do Semi-Árido","correspondingAuthor":false,"prefix":"","firstName":"Ingrid","middleName":"Gabrielly Câmara","lastName":"Lira","suffix":""},{"id":640225578,"identity":"fab19f1c-6a25-427c-8df2-3e8cd874300e","order_by":2,"name":"Angélica Félix de Castro","email":"","orcid":"","institution":"Universidade Federal Rural do Semi-Árido","correspondingAuthor":false,"prefix":"","firstName":"Angélica","middleName":"Félix","lastName":"de Castro","suffix":""},{"id":640225581,"identity":"acce4557-fce0-444c-aaa9-9600553f9940","order_by":3,"name":"Maximiliano Araujo da Silva Lopes","email":"","orcid":"","institution":"Universidade do Estado do Rio Grande do Norte","correspondingAuthor":false,"prefix":"","firstName":"Maximiliano","middleName":"Araujo da Silva","lastName":"Lopes","suffix":""}],"badges":[],"createdAt":"2026-04-15 20:23:06","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9430849/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9430849/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":109405666,"identity":"92cb74f4-d01f-4bc0-8ae6-74b290e2e382","added_by":"auto","created_at":"2026-05-17 13:19:37","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":885647,"visible":true,"origin":"","legend":"","description":"","filename":"submissiontoScientificReportsSVMPipelineforParkinsonsDisease15.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9430849/v1_covered_8466493f-897b-475f-afee-29d245dc8aab.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"An Interpretable and Auditable Pipeline for Robust Multi-Cohort Detection of Parkinson’s Disease from Voice Data with Data Leakage Prevention","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":"Parkinson’s disease, vocal biomarkers, machine learning, data leakage prevention, ensemble classifiers, LOSO validation","lastPublishedDoi":"10.21203/rs.3.rs-9430849/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9430849/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Parkinson’s disease (PD) is a progressive neurodegenerative disorder characterized by early vocal changes thatserve as crucial prodromal biomarkers. This work presents an interpretable and auditable machine learningpipeline for robust PD detection through voice analysis, integrating three heterogeneous public datasets into aunified cohort of 996 recordings from 332 independent subjects. To strictly mitigate subject-level data leakage—astructural flaw endemic to the PD voice literature—the pipeline applies a Leave-One-Subject-Out (LOSO)validation protocol and confines SMOTE-based class balancing exclusively to training folds. A soft-votingensemble of Logistic Regression, Support Vector Machine, and Random Forest achieves a subject-level Area Underthe ROC Curve (AUC) of 0.8836, with a sensitivity of 88.60% and specificity of 70.19%. A label permutationtest, in which the AUC collapses to 0.556, mathematically confirms the absence of trivial target leakage. Featureimportance analysis reveals that Mel-Frequency Cepstral Coefficients (MFCCs) and the Harmonics-to-NoiseRatio (HNR) are the dominant predictors, consistent with the known pathophysiology of hypokinetic dysarthria.This study establishes a reproducible, realistic benchmark and a rigorously audited methodological foundationfor voice-based AI triage systems in telemedicine.","manuscriptTitle":"An Interpretable and Auditable Pipeline for Robust Multi-Cohort Detection of Parkinson’s Disease from Voice Data with Data Leakage Prevention","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-15 09:50:41","doi":"10.21203/rs.3.rs-9430849/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2026-05-18T13:37:30+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"83923199074208285220110706239357152138","date":"2026-05-15T10:30:32+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"281471471931849362949516505674156835407","date":"2026-05-15T09:53:31+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-15T02:30:57+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"201742936692713709557691328696944695649","date":"2026-05-15T01:20:44+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-05-13T09:46:48+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-05-12T08:48:48+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-05-12T04:04:53+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-04-28T16:10:54+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2026-04-28T14:03:07+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":"bf5657c9-1adc-4125-a447-086af855e3cf","owner":[],"postedDate":"May 15th, 2026","published":true,"recentEditorialEvents":[{"type":"editorInvitedReview","content":"","date":"2026-05-18T13:37:30+00:00","index":50,"fulltext":""},{"type":"reviewerAgreed","content":"83923199074208285220110706239357152138","date":"2026-05-15T10:30:32+00:00","index":48,"fulltext":""},{"type":"reviewerAgreed","content":"281471471931849362949516505674156835407","date":"2026-05-15T09:53:31+00:00","index":47,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-15T02:30:57+00:00","index":46,"fulltext":""},{"type":"reviewerAgreed","content":"201742936692713709557691328696944695649","date":"2026-05-15T01:20:44+00:00","index":45,"fulltext":""},{"type":"reviewersInvited","content":"20","date":"2026-05-13T09:46:48+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-05-12T08:48:48+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-05-12T04:04:53+00:00","index":"","fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":68136722,"name":"Health sciences/Biomarkers"},{"id":68136723,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":68136724,"name":"Health sciences/Diseases"},{"id":68136725,"name":"Health sciences/Neurology"},{"id":68136726,"name":"Biological sciences/Neuroscience"}],"tags":[],"updatedAt":"2026-05-15T09:50:41+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-15 09:50:41","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9430849","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9430849","identity":"rs-9430849","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}