Zhixin: An Instruction-Tuned Large Language Model for Mental Disorder Diagnosis

preprint OA: closed
Full text JSON View at publisher

Abstract

Abstract Automatic diagnosis of mental disorder from chief complaints is an appealing but challenging task. Large Language Models (LLMs) have shown rich knowledge and strong reasoning ability in medical domain. However, mental disorder diagnosis based on chief complaints requires highly specialised knowledge. Lack of corresponding resources hinders LLMs performance on this task. To address this problem, we collect 6,780 complaint-diagnosis pairs spanning 29 different types of mental disorders from a specialized hospital as the dataset. Meanwhile we conduct detailed data cleansing and manual proofreading to protect the privacy. On this basis, we propose the model named \textsc{Zhixin}, a LLM for mental disorder diagnosis fine-tuned on the proposed dataset. The experimental results show that \textsc{Zhixin} outperforms the state-of-the-art approaches in terms of automatic evaluation. It surpasses 3-shot DeepSeek-R1 by 18.54$\%$ on \textit{Overall Accuracy}. Meanwhile, human evaluation results show that the generated response from \textsc{Zhixin} ensures the \textit{Accuracy}, \textit{Safety} and \textit{Professionalism}, which are critical to the diagnosis of mental disorder. In-depth analysis of category-wise performance sheds light on the future research direction, suggesting the focus on relatively rare metal disorders.
Full text 25,513 characters · extracted from preprint-html · click to expand
Zhixin: An Instruction-Tuned Large Language Model for Mental Disorder 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 Zhixin: An Instruction-Tuned Large Language Model for Mental Disorder Diagnosis Xiujie Zhao, Shutian Liu, Fengdong Sun, Yanrong Dong, Yubo Wang, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8149707/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 14 You are reading this latest preprint version Abstract Automatic diagnosis of mental disorder from chief complaints is an appealing but challenging task. Large Language Models (LLMs) have shown rich knowledge and strong reasoning ability in medical domain. However, mental disorder diagnosis based on chief complaints requires highly specialised knowledge. Lack of corresponding resources hinders LLMs performance on this task. To address this problem, we collect 6,780 complaint-diagnosis pairs spanning 29 different types of mental disorders from a specialized hospital as the dataset. Meanwhile we conduct detailed data cleansing and manual proofreading to protect the privacy. On this basis, we propose the model named \textsc{Zhixin}, a LLM for mental disorder diagnosis fine-tuned on the proposed dataset. The experimental results show that \textsc{Zhixin} outperforms the state-of-the-art approaches in terms of automatic evaluation. It surpasses 3-shot DeepSeek-R1 by 18.54$%$ on \textit{Overall Accuracy}. Meanwhile, human evaluation results show that the generated response from \textsc{Zhixin} ensures the \textit{Accuracy}, \textit{Safety} and \textit{Professionalism}, which are critical to the diagnosis of mental disorder. In-depth analysis of category-wise performance sheds light on the future research direction, suggesting the focus on relatively rare metal disorders. Health sciences/Health care Physical sciences/Mathematics and computing Biological sciences/Psychology Social science/Psychology Large Language Models Mental Disorder Instruction Fine-tuning Intelligent Auxiliary Diagnosis Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 04 May, 2026 Reviews received at journal 28 Apr, 2026 Reviewers agreed at journal 07 Apr, 2026 Reviews received at journal 24 Mar, 2026 Reviewers agreed at journal 26 Feb, 2026 Reviewers agreed at journal 26 Feb, 2026 Reviews received at journal 03 Feb, 2026 Reviewers agreed at journal 18 Dec, 2025 Reviewers agreed at journal 18 Dec, 2025 Reviewers invited by journal 01 Dec, 2025 Editor assigned by journal 01 Dec, 2025 Editor invited by journal 26 Nov, 2025 Submission checks completed at journal 25 Nov, 2025 First submitted to journal 25 Nov, 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-8149707","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":554598042,"identity":"c3500f89-b7af-4844-bcec-3b38d01cd327","order_by":0,"name":"Xiujie Zhao","email":"","orcid":"","institution":"Dalian Neusoft University of Information","correspondingAuthor":false,"prefix":"","firstName":"Xiujie","middleName":"","lastName":"Zhao","suffix":""},{"id":554598043,"identity":"a1914a41-4b1c-4d89-95c9-76d29e32ca0e","order_by":1,"name":"Shutian Liu","email":"","orcid":"","institution":"Dalian Neusoft University of Information","correspondingAuthor":false,"prefix":"","firstName":"Shutian","middleName":"","lastName":"Liu","suffix":""},{"id":554598044,"identity":"ebfd55eb-8dc9-49b2-bb42-ef4bb57cc7cd","order_by":2,"name":"Fengdong Sun","email":"","orcid":"","institution":"Dalian Neusoft University of Information","correspondingAuthor":false,"prefix":"","firstName":"Fengdong","middleName":"","lastName":"Sun","suffix":""},{"id":554598045,"identity":"88458e46-a3a8-45dc-aefe-f4fbe60c761c","order_by":3,"name":"Yanrong Dong","email":"","orcid":"","institution":"Dalian Neusoft University of Information","correspondingAuthor":false,"prefix":"","firstName":"Yanrong","middleName":"","lastName":"Dong","suffix":""},{"id":554598046,"identity":"c448859f-d913-402f-adbc-f455b21ceeb5","order_by":4,"name":"Yubo Wang","email":"","orcid":"","institution":"Dalian Neusoft University of Information","correspondingAuthor":false,"prefix":"","firstName":"Yubo","middleName":"","lastName":"Wang","suffix":""},{"id":554598047,"identity":"f17a07e7-e713-47d9-b57b-1e54f514832b","order_by":5,"name":"Changyun Ge","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA8UlEQVRIiWNgGAWjYLCCBBCSgLDl2NibDxCjxQCuxZiP51gCMfYgtCTOk8hRwKtWfnbzMYmHO/7k8Us3H/zMU3EnvY0hh4HhR8U23MbfOZYmkXjGoFhyzrFkaZ4zz3LbGM4eYOw5cxu3FokcsxuJbQaJG27kGEjObDuc28bYl8DM2IZbi/wMqJb9N/I//5z573A6GzOPAV4tDDdgtkjksEl8bDicwMZGQIvBjbT0H4ltxokzbqSZWXw4dtiwjYct4SA+v8jPSD5s+LNNLrF/RvLjGwk1h+Xl5z8++OBHBR6HYQUHSFQ/CkbBKBgFowANAADn0Fx3DpQ9YAAAAABJRU5ErkJggg==","orcid":"","institution":"Fuyang University of Technology","correspondingAuthor":true,"prefix":"","firstName":"Changyun","middleName":"","lastName":"Ge","suffix":""}],"badges":[],"createdAt":"2025-11-19 01:38:21","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8149707/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8149707/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":97527664,"identity":"e7954599-c74e-44b7-b678-24e3bdbf6f1e","added_by":"auto","created_at":"2025-12-05 12:40:56","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":7583,"visible":true,"origin":"","legend":"","description":"","filename":"683bf8262e3541559532060450048a30.json","url":"https://assets-eu.researchsquare.com/files/rs-8149707/v1/be11981c48d87f3568c8a4b6.json"},{"id":97527668,"identity":"9a8e756c-7cc1-4781-81cf-084ba1bd103e","added_by":"auto","created_at":"2025-12-05 12:40:56","extension":"jpg","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":180243,"visible":true,"origin":"","legend":"","description":"","filename":"F1.jpg","url":"https://assets-eu.researchsquare.com/files/rs-8149707/v1/b9e15c6e767575a2e3e7ed60.jpg"},{"id":97527672,"identity":"a25bdbc4-309a-402a-9430-4062e5cf0e30","added_by":"auto","created_at":"2025-12-05 12:40:56","extension":"pdf","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":98433,"visible":true,"origin":"","legend":"","description":"","filename":"ReviewerResponse.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8149707/v1/b247587888ee8ec6c095f6f5.pdf"},{"id":97671139,"identity":"0a2b47cb-563f-4ce4-b0f0-ef0ba5677e89","added_by":"auto","created_at":"2025-12-08 09:31:59","extension":"pdf","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1012403,"visible":true,"origin":"","legend":"","description":"","filename":"ZhixinAnInstructionTunedLargeLanguageModelforMentalDisorderDiagnosis.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8149707/v1/2adbd617258d4a0e9b3357a5.pdf"},{"id":97670120,"identity":"a648c428-3cc8-429b-a1fa-ce0663b1940d","added_by":"auto","created_at":"2025-12-08 09:29:43","extension":"jpg","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":245553,"visible":true,"origin":"","legend":"","description":"","filename":"f1scorescomparison.jpg","url":"https://assets-eu.researchsquare.com/files/rs-8149707/v1/2b1fa55abe3a18df66051dc7.jpg"},{"id":97527665,"identity":"d22203f1-f34a-4faa-b327-6ed90b11adba","added_by":"auto","created_at":"2025-12-05 12:40:56","extension":"jpg","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":75935,"visible":true,"origin":"","legend":"","description":"","filename":"human.jpg","url":"https://assets-eu.researchsquare.com/files/rs-8149707/v1/177b6b33989c17a87fc1e8f5.jpg"},{"id":97527673,"identity":"9c985395-c4a0-4615-8657-ba2c77c532cc","added_by":"auto","created_at":"2025-12-05 12:40:56","extension":"jpg","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":131833,"visible":true,"origin":"","legend":"","description":"","filename":"humanevaluationcomparison.jpg","url":"https://assets-eu.researchsquare.com/files/rs-8149707/v1/73d59e98885588035fb8fa42.jpg"},{"id":97670804,"identity":"8957ce2c-9874-48f0-8aea-915c94adc784","added_by":"auto","created_at":"2025-12-08 09:31:22","extension":"ldf","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":49107,"visible":true,"origin":"","legend":"","description":"","filename":"jabbrvltwaall.ldf","url":"https://assets-eu.researchsquare.com/files/rs-8149707/v1/007d603dcca1bc4281bbf0ca.ldf"},{"id":97527675,"identity":"75c5f0d4-c003-496a-b45a-a0ac0381e302","added_by":"auto","created_at":"2025-12-05 12:40:56","extension":"ldf","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":268657,"visible":true,"origin":"","legend":"","description":"","filename":"jabbrvltwaen.ldf","url":"https://assets-eu.researchsquare.com/files/rs-8149707/v1/83fb66dbe6ea022ced248687.ldf"},{"id":97672285,"identity":"c20c23e3-3dee-4bac-ad50-9da2816bae0a","added_by":"auto","created_at":"2025-12-08 09:35:03","extension":"sty","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":15480,"visible":true,"origin":"","legend":"","description":"","filename":"jabbrv.sty","url":"https://assets-eu.researchsquare.com/files/rs-8149707/v1/7350028e77060037941ad6c0.sty"},{"id":97672272,"identity":"6e9755c9-afd2-4e3a-b295-e1358db4ddee","added_by":"auto","created_at":"2025-12-08 09:35:00","extension":"aux","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":10580,"visible":true,"origin":"","legend":"","description":"","filename":"main.aux","url":"https://assets-eu.researchsquare.com/files/rs-8149707/v1/5c016479f5ac83028fab8604.aux"},{"id":97670101,"identity":"d0ae2a6a-f753-45bd-8b86-ca395e00de94","added_by":"auto","created_at":"2025-12-08 09:29:41","extension":"bbl","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":13119,"visible":true,"origin":"","legend":"","description":"","filename":"main.bbl","url":"https://assets-eu.researchsquare.com/files/rs-8149707/v1/0d05cc4178174e6499427672.bbl"},{"id":97671250,"identity":"d3592172-01bd-4505-bf10-26c909c96ea5","added_by":"auto","created_at":"2025-12-08 09:32:18","extension":"blg","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":911,"visible":true,"origin":"","legend":"","description":"","filename":"main.blg","url":"https://assets-eu.researchsquare.com/files/rs-8149707/v1/1797ca7d055f727f325e35b5.blg"},{"id":97670139,"identity":"41e85db8-e026-4d4a-b5f1-bd8da8d347d6","added_by":"auto","created_at":"2025-12-08 09:29:46","extension":"fdb_latexmk","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":42244,"visible":true,"origin":"","legend":"","description":"","filename":"main.fdblatexmk","url":"https://assets-eu.researchsquare.com/files/rs-8149707/v1/27e89d908f6713ddec7b6fc2.fdb_latexmk"},{"id":97527690,"identity":"e2ed873c-f0ae-441d-b588-d1c8aab5d693","added_by":"auto","created_at":"2025-12-05 12:40:57","extension":"fls","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":42895,"visible":true,"origin":"","legend":"","description":"","filename":"main.fls","url":"https://assets-eu.researchsquare.com/files/rs-8149707/v1/ada21764971d59354ec181a6.fls"},{"id":97670143,"identity":"fa03dc72-ff00-46e4-abd1-0b6e9855f237","added_by":"auto","created_at":"2025-12-08 09:29:46","extension":"log","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":60174,"visible":true,"origin":"","legend":"","description":"","filename":"main.log","url":"https://assets-eu.researchsquare.com/files/rs-8149707/v1/19b1cb6e2bc873a479ac38b3.log"},{"id":97527682,"identity":"bb61cf67-f282-49b5-bb4f-ea8864bf1c8e","added_by":"auto","created_at":"2025-12-05 12:40:57","extension":"out","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":3746,"visible":true,"origin":"","legend":"","description":"","filename":"main.out","url":"https://assets-eu.researchsquare.com/files/rs-8149707/v1/42cc891dba39e79771199696.out"},{"id":97672225,"identity":"cbff9baf-20c9-42b6-966c-50dd592e90b2","added_by":"auto","created_at":"2025-12-08 09:34:51","extension":"pdf","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1015029,"visible":true,"origin":"","legend":"","description":"","filename":"main.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8149707/v1/ba519282fe0ad84e73e4848c.pdf"},{"id":97527683,"identity":"935dcc2f-1596-411d-bb12-119e635f247f","added_by":"auto","created_at":"2025-12-05 12:40:57","extension":"gz","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":202053,"visible":true,"origin":"","legend":"","description":"","filename":"main.synctex.gz","url":"https://assets-eu.researchsquare.com/files/rs-8149707/v1/f2b2df68af10eb0174b091f9.gz"},{"id":97527677,"identity":"0e22ffef-f69d-405e-9279-c168d5ee5d2c","added_by":"auto","created_at":"2025-12-05 12:40:57","extension":"bst","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":36153,"visible":true,"origin":"","legend":"","description":"","filename":"naturemagdoi.bst","url":"https://assets-eu.researchsquare.com/files/rs-8149707/v1/bcb59ad92ee0a3fa6730a60e.bst"},{"id":97670766,"identity":"c655967b-73db-4494-b908-8c9f63e63ca8","added_by":"auto","created_at":"2025-12-08 09:31:18","extension":"jpg","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":93886,"visible":true,"origin":"","legend":"","description":"","filename":"piechart.jpg","url":"https://assets-eu.researchsquare.com/files/rs-8149707/v1/322d73a4722d26d4e0c19b45.jpg"},{"id":97527684,"identity":"f9e50900-51fd-4d59-8adf-3630d24d5e5e","added_by":"auto","created_at":"2025-12-05 12:40:57","extension":"jpg","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":14224,"visible":true,"origin":"","legend":"","description":"","filename":"resultright.jpg","url":"https://assets-eu.researchsquare.com/files/rs-8149707/v1/b99c1dd9fa17a45956c51fb3.jpg"},{"id":97527685,"identity":"3c653ed3-5e06-4bb8-949d-0ba3b3c71f13","added_by":"auto","created_at":"2025-12-05 12:40:57","extension":"jpg","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":14103,"visible":true,"origin":"","legend":"","description":"","filename":"resultwrong.jpg","url":"https://assets-eu.researchsquare.com/files/rs-8149707/v1/6241d471669554ec9e7f50c4.jpg"},{"id":97527687,"identity":"bf9634a5-79ae-4674-924f-3a8d607205ed","added_by":"auto","created_at":"2025-12-05 12:40:57","extension":"jpg","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":379752,"visible":true,"origin":"","legend":"","description":"","filename":"stream.jpg","url":"https://assets-eu.researchsquare.com/files/rs-8149707/v1/95ff2309da2601ca2efb2a80.jpg"},{"id":97527692,"identity":"5efc675f-cf13-4588-a03f-997050b5fc90","added_by":"auto","created_at":"2025-12-05 12:40:57","extension":"jpg","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":19300,"visible":true,"origin":"","legend":"","description":"","filename":"trainloss.jpg","url":"https://assets-eu.researchsquare.com/files/rs-8149707/v1/6e8c881b07e86c33bf0916b0.jpg"},{"id":97527681,"identity":"f854e0ea-61ab-4ebf-82f6-4460ba8646d5","added_by":"auto","created_at":"2025-12-05 12:40:57","extension":"cls","order_by":25,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5824,"visible":true,"origin":"","legend":"","description":"","filename":"wlscirep.cls","url":"https://assets-eu.researchsquare.com/files/rs-8149707/v1/383ee5e7cdcba5b116918c27.cls"},{"id":97670771,"identity":"ec2c9fde-c351-4ad6-a993-cb76e823fc6e","added_by":"auto","created_at":"2025-12-08 09:31:18","extension":"png","order_by":26,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":262666,"visible":true,"origin":"","legend":"","description":"","filename":"wordmap.png","url":"https://assets-eu.researchsquare.com/files/rs-8149707/v1/5a60e9009c02884863ad0194.png"},{"id":97527691,"identity":"b44311c7-0090-4549-9d2f-80a1875f24ef","added_by":"auto","created_at":"2025-12-05 12:40:57","extension":"xml","order_by":27,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":111781,"visible":true,"origin":"","legend":"","description":"","filename":"683bf8262e3541559532060450048a301structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-8149707/v1/dc0704de51c53cd4877d8245.xml"},{"id":97677863,"identity":"702b7455-89b7-464c-b77b-18b58417aa84","added_by":"auto","created_at":"2025-12-08 09:54:49","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":976748,"visible":true,"origin":"","legend":"","description":"","filename":"ZhixinAnInstructionTunedLargeLanguageModelforMentalDisorderDiagnosis.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8149707/v1_covered_ae1e4634-043e-4b98-adbf-05ce02c91cc7.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Zhixin: An Instruction-Tuned Large Language Model for Mental Disorder Diagnosis","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":"Large Language Models, Mental Disorder, Instruction Fine-tuning, Intelligent Auxiliary Diagnosis","lastPublishedDoi":"10.21203/rs.3.rs-8149707/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8149707/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Automatic diagnosis of mental disorder from chief complaints is an appealing but challenging task. Large Language Models (LLMs) have shown rich knowledge and strong reasoning ability in medical domain. However, mental disorder diagnosis based on chief complaints requires highly specialised knowledge. Lack of corresponding resources hinders LLMs performance on this task. To address this problem, we collect 6,780 complaint-diagnosis pairs spanning 29 different types of mental disorders from a specialized hospital as the dataset. Meanwhile we conduct detailed data cleansing and manual proofreading to protect the privacy. On this basis, we propose the model named \\textsc{Zhixin}, a LLM for mental disorder diagnosis fine-tuned on the proposed dataset. The experimental results show that \\textsc{Zhixin} outperforms the state-of-the-art approaches in terms of automatic evaluation. It surpasses 3-shot DeepSeek-R1 by 18.54$\\%$ on \\textit{Overall Accuracy}. Meanwhile, human evaluation results show that the generated response from \\textsc{Zhixin} ensures the \\textit{Accuracy}, \\textit{Safety} and \\textit{Professionalism}, which are critical to the diagnosis of mental disorder. In-depth analysis of category-wise performance sheds light on the future research direction, suggesting the focus on relatively rare metal disorders.","manuscriptTitle":"Zhixin: An Instruction-Tuned Large Language Model for Mental Disorder Diagnosis","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-05 12:40:52","doi":"10.21203/rs.3.rs-8149707/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-05-04T08:05:27+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-28T04:39:02+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"218801782168480183715018972016661073960","date":"2026-04-07T13:20:28+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-24T14:18:58+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"167137162860695228793131826143161096471","date":"2026-02-27T00:28:32+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"169328890072967689057215444131915269084","date":"2026-02-26T14:15:28+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-04T02:58:41+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"152947919192522649751592410594390221568","date":"2025-12-19T01:49:12+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"226129754973291133948138843366188084834","date":"2025-12-18T16:27:20+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-12-01T09:46:58+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-12-01T09:44:19+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-11-26T06:29:22+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-11-25T06:44:16+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-11-25T06:41:41+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":"4987d8dd-459a-4ddd-aa4e-7b76ec37e157","owner":[],"postedDate":"December 5th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":59017686,"name":"Health sciences/Health care"},{"id":59017687,"name":"Physical sciences/Mathematics and computing"},{"id":59017688,"name":"Biological sciences/Psychology"},{"id":59017689,"name":"Social science/Psychology"}],"tags":[],"updatedAt":"2026-05-26T14:24:32+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-05 12:40:52","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8149707","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8149707","identity":"rs-8149707","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.

My notes (saved in your browser only)

Ask this paper AI returns verbatim quotes from the full text · source: preprint-html

Answers must be backed by verbatim quotes from this paper's full text. Hallucinated quotes are dropped automatically; if no verbatim passage answers the question, we say so. How this works

Citation neighborhood (no data yet)

We don't have any in-corpus citations linked to this paper yet. This is a recent paper (2025) — citers typically take a year or two to land, and the OpenAlex reference graph may still be filling in.

Source provenance

europepmc
last seen: 2026-05-20T01:45:00.602351+00:00