Automated Speech-Fluency Explanations for Schizophrenia Diagnosis

Automated Speech-Fluency Explanations for Schizophrenia Diagnosis | 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 Automated Speech-Fluency Explanations for Schizophrenia Diagnosis Rok Rajher, Mila Marinković, Polona Rus Prelog, Jure Žabkar This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7440282/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 22 Dec, 2025 Read the published version in Scientific Reports → Version 1 posted 11 You are reading this latest preprint version Abstract Schizophrenia is a chronic and severe mental disorder that still relies on time-intensive, clinician-administered assessments. Although several automated approaches have been proposed to support diagnosis, these systems often lack the level of explainability necessary for informed clinical decision-making. In this study, we present a fully automated and explainable pipeline for detecting schizophrenia from audio recordings of verbal fluency tests, collected from 126 Slovene-speaking participants (68 healthy controls, 58 individuals diagnosed with schizophrenia), leveraging recent advancements in automatic speech recognition (ASR) and large language model (LLM) systems. We evaluated three ASR models—Truebar, Whisper, and Soniox—for transcription quality, and selected the best-performing system for further processing. We semantically enriched the transcriptions using the generative capabilities of LLMs and extracted both verbal and non-verbal features grounded in established diagnostic criteria. We assessed the relevance of these features using a Bayesian statistical framework and trained multiple classical machine learning models for automatic classification. Our best-performing model, an Explainable Boosting Machine, achieved a classification accuracy of 0.82 and an AUC of 0.90. We further generated visual explanations for the model's predictions, establishing the first fully automated and explainable schizophrenia detection framework developed for the Slovene language. Our approach prioritizes explainability through model-transparent outputs, while still achieving performance comparable to existing automated systems for speech-based schizophrenia detection. Biological sciences/Computational biology and bioinformatics Health sciences/Diseases Health sciences/Health care Physical sciences/Mathematics and computing Health sciences/Medical research automated schizophrenia detection automated speech recognition verbal fluency Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 22 Dec, 2025 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 30 Sep, 2025 Reviews received at journal 28 Sep, 2025 Reviews received at journal 13 Sep, 2025 Reviewers agreed at journal 07 Sep, 2025 Reviewers agreed at journal 04 Sep, 2025 Reviewers agreed at journal 03 Sep, 2025 Reviewers invited by journal 02 Sep, 2025 Editor invited by journal 29 Aug, 2025 Editor assigned by journal 27 Aug, 2025 Submission checks completed at journal 26 Aug, 2025 First submitted to journal 23 Aug, 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-7440282","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":510796778,"identity":"a48a4f1f-027e-44fa-9664-f881987f5c70","order_by":0,"name":"Rok Rajher","email":"","orcid":"","institution":"University of Ljubljana","correspondingAuthor":false,"prefix":"","firstName":"Rok","middleName":"","lastName":"Rajher","suffix":""},{"id":510796779,"identity":"9885d05d-76d5-4da8-a033-3a4d57eaa5c6","order_by":1,"name":"Mila Marinković","email":"","orcid":"","institution":"University of Ljubljana","correspondingAuthor":false,"prefix":"","firstName":"Mila","middleName":"","lastName":"Marinković","suffix":""},{"id":510796780,"identity":"bb64cdba-5dfc-4a4d-9004-e8f9a45c5e1c","order_by":2,"name":"Polona Rus Prelog","email":"","orcid":"","institution":"University Psychiatric Clinic Ljubljana","correspondingAuthor":false,"prefix":"","firstName":"Polona","middleName":"Rus","lastName":"Prelog","suffix":""},{"id":510796781,"identity":"7d8e9037-b74d-4e46-bb2f-c31423548014","order_by":3,"name":"Jure Žabkar","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABAUlEQVRIiWNgGAWjYBACxgYInSABZD+oYJCAiD3gYWBgI0ILs8EZmJYEPFpgAKSFTeIMnItHKfOM3IcPGP7Y5Um2n31WcXCPBYPB7WagLTIM9ny4HDYj3diAgSe5WJon3ezGgWcSDAZ3DoIdltiGU0samwSDBHPiPIY0ttsfDgC13Ehs/wHUkoDT+zPS2H8wGNQnzuN/xlZwAKIFbIs9Hi1AqYTDibMlgAxkLYw4HdbzjFki4cDxYskZQAZQC48kRIsETr8YtqcxfvjwpzpP4jyQceBAnRzfjfQHDB97bOzlG3BoAYknIAnwQC2XwGEHA4M8DvEfOHWMglEwCkbByAMAFMFTZb9ZYoEAAAAASUVORK5CYII=","orcid":"","institution":"University of Ljubljana","correspondingAuthor":true,"prefix":"","firstName":"Jure","middleName":"","lastName":"Žabkar","suffix":""}],"badges":[],"createdAt":"2025-08-23 09:38:25","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7440282/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7440282/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-33129-w","type":"published","date":"2025-12-22T15:57:21+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":99172260,"identity":"a2672185-d418-4470-881b-bc154de7c0fd","added_by":"auto","created_at":"2025-12-29 16:06:29","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1260644,"visible":true,"origin":"","legend":"","description":"","filename":"NPJDigitalMedicineAutomaticGenerationofExplanationsinDiagnosingSchizophrenia1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7440282/v1_covered_f8666b5a-4792-41b1-99cd-5fa0173212d6.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Automated Speech-Fluency Explanations for Schizophrenia Diagnosis","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":"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":"automated schizophrenia detection, automated speech recognition, verbal fluency","lastPublishedDoi":"10.21203/rs.3.rs-7440282/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7440282/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eSchizophrenia is a chronic and severe mental disorder that still relies on time-intensive, clinician-administered assessments. Although several automated approaches have been proposed to support diagnosis, these systems often lack the level of explainability necessary for informed clinical decision-making. In this study, we present a fully automated and explainable pipeline for detecting schizophrenia from audio recordings of verbal fluency tests, collected from 126 Slovene-speaking participants (68 healthy controls, 58 individuals diagnosed with schizophrenia), leveraging recent advancements in automatic speech recognition (ASR) and large language model (LLM) systems.\u003c/p\u003e\n\u003cp\u003eWe evaluated three ASR models—Truebar, Whisper, and Soniox—for transcription quality, and selected the best-performing system for further processing. We semantically enriched the transcriptions using the generative capabilities of LLMs and extracted both verbal and non-verbal features grounded in established diagnostic criteria. We assessed the relevance of these features using a Bayesian statistical framework and trained multiple classical machine learning models for automatic classification.\u003c/p\u003e\n\u003cp\u003eOur best-performing model, an Explainable Boosting Machine, achieved a classification accuracy of 0.82 and an AUC of 0.90. We further generated visual explanations for the model's predictions, establishing the first fully automated and explainable schizophrenia detection framework developed for the Slovene language. Our approach prioritizes explainability through model-transparent outputs, while still achieving performance comparable to existing automated systems for speech-based schizophrenia detection.\u003c/p\u003e","manuscriptTitle":"Automated Speech-Fluency Explanations for Schizophrenia Diagnosis","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-09 13:26:18","doi":"10.21203/rs.3.rs-7440282/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-09-30T07:32:01+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-09-28T13:17:11+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-09-13T18:42:49+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"244612753781069847203616320934487581180","date":"2025-09-08T00:13:40+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"230667348863950342066466744288976286404","date":"2025-09-04T23:54:35+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"119172246508417500418083653684592154446","date":"2025-09-03T13:09:58+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-09-02T23:52:52+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-08-29T07:49:44+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-08-27T09:50:31+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-08-26T09:57:40+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-08-23T09:28:03+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":"5d27f995-64f8-464d-8918-a4c02bb9a8fa","owner":[],"postedDate":"September 9th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":54261083,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":54261084,"name":"Health sciences/Diseases"},{"id":54261085,"name":"Health sciences/Health care"},{"id":54261086,"name":"Physical sciences/Mathematics and computing"},{"id":54261087,"name":"Health sciences/Medical research"}],"tags":[],"updatedAt":"2025-12-29T16:00:01+00:00","versionOfRecord":{"articleIdentity":"rs-7440282","link":"https://doi.org/10.1038/s41598-025-33129-w","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2025-12-22 15:57:21","publishedOnDateReadable":"December 22nd, 2025"},"versionCreatedAt":"2025-09-09 13:26:18","video":"","vorDoi":"10.1038/s41598-025-33129-w","vorDoiUrl":"https://doi.org/10.1038/s41598-025-33129-w","workflowStages":[]},"version":"v1","identity":"rs-7440282","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7440282","identity":"rs-7440282","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}