Construction of multimodal dataset for early depression detection and performance evaluation of depression detection model

Construction of multimodal dataset for early depression detection and performance evaluation of depression detection model | 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 Construction of multimodal dataset for early depression detection and performance evaluation of depression detection model Kotaro Kashihara, Toshiki Takanabe, Keita Kiuchi, Hidehiro Umehara, and 6 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6344200/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 5 You are reading this latest preprint version Abstract Depression is a serious social issue, and early detection is crucial for improving mental health care. This study constructed a Japanese multimodal dataset for early depression detection, collecting text, audio, video, and heart rate data from 30-minute interviews with professional counselors. Psychological questionnaires were also administered before and after interviews. Feature extraction and correlation analysis with questionnaire results confirmed the dataset's reliability, aligning with existing psychological research. The dataset was then used to train DepMamba, a latest depression detection model, comparing three training methods. Fine-tuning the constructed dataset after pre-training on DAIC-WOZ significantly improved recall, enhancing depression detection performance. However, data limitations and label imbalances highlight the need for future dataset expansion and objective annotation. This research advances depression detection technology and supports the practical application of mental health care. Multimodal Depression detection Dataset Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviewers agreed at journal 25 May, 2025 Reviewers invited by journal 23 May, 2025 Editor assigned by journal 23 May, 2025 Submission checks completed at journal 02 Apr, 2025 First submitted to journal 31 Mar, 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-6344200","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":461568117,"identity":"22ba729f-0fd8-4a4a-811d-c78354c9131f","order_by":0,"name":"Kotaro Kashihara","email":"data:image/png;base64,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","orcid":"","institution":"Tokushima University","correspondingAuthor":true,"prefix":"","firstName":"Kotaro","middleName":"","lastName":"Kashihara","suffix":""},{"id":461568118,"identity":"f7697abc-6560-41b2-b2b6-cbd16152319e","order_by":1,"name":"Toshiki Takanabe","email":"","orcid":"","institution":"Tokushima University","correspondingAuthor":false,"prefix":"","firstName":"Toshiki","middleName":"","lastName":"Takanabe","suffix":""},{"id":461568119,"identity":"51dc23fb-b382-4fed-a152-7cdfc61d94e7","order_by":2,"name":"Keita Kiuchi","email":"","orcid":"","institution":"Japan Organization of Occupational Health and Society","correspondingAuthor":false,"prefix":"","firstName":"Keita","middleName":"","lastName":"Kiuchi","suffix":""},{"id":461568120,"identity":"9a3fbb99-728f-4aba-ac58-6e0055da11b3","order_by":3,"name":"Hidehiro Umehara","email":"","orcid":"","institution":"Tokushima University","correspondingAuthor":false,"prefix":"","firstName":"Hidehiro","middleName":"","lastName":"Umehara","suffix":""},{"id":461568121,"identity":"9ebad30c-8eb3-4aff-92db-669203fa3fe7","order_by":4,"name":"Koushi Irizawa","email":"","orcid":"","institution":"Tokushima University","correspondingAuthor":false,"prefix":"","firstName":"Koushi","middleName":"","lastName":"Irizawa","suffix":""},{"id":461568122,"identity":"8aaff9c3-319c-4e7f-acfb-f3c2e55a6ea3","order_by":5,"name":"Masahito Nakataki","email":"","orcid":"","institution":"Tokushima University","correspondingAuthor":false,"prefix":"","firstName":"Masahito","middleName":"","lastName":"Nakataki","suffix":""},{"id":461568123,"identity":"c1a8902e-c061-4f7a-89c5-7665eb95eec9","order_by":6,"name":"Shunsuke Numata","email":"","orcid":"","institution":"Tokushima University","correspondingAuthor":false,"prefix":"","firstName":"Shunsuke","middleName":"","lastName":"Numata","suffix":""},{"id":461568124,"identity":"7eb5d307-7efe-40e3-adea-6cfacb775cbd","order_by":7,"name":"Xin Kang","email":"","orcid":"","institution":"Tokushima University","correspondingAuthor":false,"prefix":"","firstName":"Xin","middleName":"","lastName":"Kang","suffix":""},{"id":461568125,"identity":"2b8da2bf-952e-4a71-99a0-8e402fc5c2ec","order_by":8,"name":"Minoru Yoshida","email":"","orcid":"","institution":"Tokushima University","correspondingAuthor":false,"prefix":"","firstName":"Minoru","middleName":"","lastName":"Yoshida","suffix":""},{"id":461568126,"identity":"d4701c45-57a0-4541-be35-0e35eed9d06d","order_by":9,"name":"Kazuyuki Matsumoto","email":"","orcid":"","institution":"Tokushima University","correspondingAuthor":false,"prefix":"","firstName":"Kazuyuki","middleName":"","lastName":"Matsumoto","suffix":""}],"badges":[],"createdAt":"2025-03-31 11:08:23","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6344200/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6344200/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":83445979,"identity":"61f55802-9a7a-4702-85d5-dd46f425a30e","added_by":"auto","created_at":"2025-05-26 11:09:04","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2864367,"visible":true,"origin":"","legend":"","description":"","filename":"kotarokashiharalre.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6344200/v1_covered_9ef889d5-4817-4213-bb0b-77653110569e.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Construction of multimodal dataset for early depression detection and performance evaluation of depression detection model","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":"language-resources-and-evaluation","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"lrev","sideBox":"Learn more about [Language Resources and Evaluation](http://link.springer.com/journal/10579)","snPcode":"10579","submissionUrl":"https://submission.nature.com/new-submission/10579/3","title":"Language Resources and Evaluation","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Multimodal, Depression detection, Dataset","lastPublishedDoi":"10.21203/rs.3.rs-6344200/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6344200/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eDepression is a serious social issue, and early detection is crucial for improving mental health care. This study constructed a Japanese multimodal dataset for early depression detection, collecting text, audio, video, and heart rate data from 30-minute interviews with professional counselors. Psychological questionnaires were also administered before and after interviews. Feature extraction and correlation analysis with questionnaire results confirmed the dataset's reliability, aligning with existing psychological research. The dataset was then used to train DepMamba, a latest depression detection model, comparing three training methods. Fine-tuning the constructed dataset after pre-training on DAIC-WOZ significantly improved recall, enhancing depression detection performance. However, data limitations and label imbalances highlight the need for future dataset expansion and objective annotation. This research advances depression detection technology and supports the practical application of mental health care.\u003c/p\u003e","manuscriptTitle":"Construction of multimodal dataset for early depression detection and performance evaluation of depression detection model","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-05-26 11:00:58","doi":"10.21203/rs.3.rs-6344200/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewerAgreed","content":"11040471264815732250396938357764582840","date":"2025-05-25T15:48:04+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-05-23T15:41:30+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-05-23T15:24:16+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-04-02T23:38:32+00:00","index":"","fulltext":""},{"type":"submitted","content":"Language Resources and Evaluation","date":"2025-03-31T11:03:59+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"language-resources-and-evaluation","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"lrev","sideBox":"Learn more about [Language Resources and Evaluation](http://link.springer.com/journal/10579)","snPcode":"10579","submissionUrl":"https://submission.nature.com/new-submission/10579/3","title":"Language Resources and Evaluation","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"a557978c-c713-4298-b845-864437d0de4f","owner":[],"postedDate":"May 26th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2025-05-26T11:00:58+00:00","versionOfRecord":[],"versionCreatedAt":"2025-05-26 11:00:58","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6344200","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6344200","identity":"rs-6344200","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}