Artificial intelligence based detection of early cognitive impairment using language, speech, and demographic features: Model development and validation

Artificial intelligence based detection of early cognitive impairment using language, speech, and demographic features: Model development and validation | 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 Artificial intelligence based detection of early cognitive impairment using language, speech, and demographic features: Model development and validation Usha Lokala, Prabhakar B. Sharma, Rutvik H. Desai, Valerie L. Shalin, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4595656/v2 This work is licensed under a CC BY 4.0 License Status: Under Review Version 2 posted 3 You are reading this latest preprint version Show more versions Abstract Background Mild cognitive impairment (MCI) is a prevalent condition among older adults and a potential marker for dementia. The current challenge lies in diagnosing MCI among healthy older populations. This diagnosis typically requires extensive labor-intensive neuropsychological evaluation using tools like the Mini-Mental State Examination (MMSE) or the MoCA (Montreal Cognitive Assessment) based on specific diagnostic criteria. Objective This study used knowledge-guided machine learning (ML) algorithms and large language models (LLMs) to build diagnostic models. Our approach generates a clinician-guided classification by augmenting LLMs with external knowledge to predict levels of MCI by using the verbal text from picture description tasks. Methods The models used language features from two picture description tasks, along with demographic features. They aimed to distinguish between three levels of MCI (MCI, possible MCI, and healthy group). The dataset exhibits class imbalance, with relatively fewer MCI and possible-MCI cases compared to healthy participants. This imbalance is addressed using SMOTE and stratified cross-validation. We utilized the cognitive cross-domain attention model (CCDA) to integrate the attention mechanism of diverse types of information into our training process, improving performance. Results We demonstrate the efficacy of machine learning, large language models (LLMs), and knowledge-integrated LLMs built on semantic, syntactic, lexical, fluency, and demographic features to identify different levels of cognitive decline from the analysis of verbal utterances. Our CCDA model detected MCI from the participant input, aided by an external attention mechanism. Statistical analysis was conducted using a significance threshold of α = 0.05. Results that do not meet this threshold are interpreted as indicative trends rather than statistically significant findings. An ablation study (Table 6) showed the impact of the attention mechanism and LLM approach on performance. The proposed CCDA model achieved a mean AUC of 0.81 (95% CI: 0.77–0.85) and an F1 score of 0.73 (95% CI: 0.69–0.76) using stratified 10-fold cross-validation. Conclusion Our knowledge-augmented approach compared favorably to contemporary LLM approaches, indicating the promise of knowledge-augmented learning in detecting MCI. This framework can support early, non-invasive screening for cognitive decline in telehealth and resource-limited settings, assisting clinicians in identifying at-risk individuals for further evaluation. Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 2 posted Reviewers invited by journal 24 Apr, 2026 Submission checks completed at journal 22 Apr, 2026 First submitted to journal 19 Apr, 2026 You are reading this latest preprint version Show more versions 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-4595656","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[{"code":1,"date":"2024-07-10 15:26:14","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-medical-informatics-and-decision-making","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"midm","sideBox":"Learn more about [BMC Medical Informatics and Decision Making](http://bmcmedinformdecismak.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/midm/default.aspx","title":"BMC Medical Informatics and Decision Making","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":631155178,"identity":"4bc1dfdd-430f-11f1-b2c4-06cc9d20a69f","order_by":0,"name":"Usha Lokala","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA3UlEQVRIiWNgGAWjYDACdgZmBoYCBjkQ+8ADiJgBfi3MIC0GDMZgLQmkaElsAHGI0mLOzHzY4IeBXXq/2OGHQFvq5BnYm7dJ4NNi2cyWnNhjkJw7c3aaAVDLYcMGnmNleLUYHOYxPsBjwJy74XYCSAsQSeSYEdRy8I9Bfbr97fQPIIclMMi/IawlmcfgcIKBdA7IFmagLTyEtLAlG8sYHDeccTun4ECCwWHDNp60Ygu8Wo43H5Z8U1Etzz87ffOHDxV18vzshzfewKcF3QQGBjYSlI+CUTAKRsEowAEA+otDCjYt+wsAAAAASUVORK5CYII=","orcid":"","institution":"University of South Carolina","correspondingAuthor":true,"prefix":"","firstName":"Usha","middleName":"","lastName":"Lokala","suffix":""},{"id":631163929,"identity":"58d51f7f-87e3-4d58-9678-f22cea1ec9f8","order_by":1,"name":"Prabhakar B. Sharma","email":"","orcid":"","institution":"Palmetto GBA\"","correspondingAuthor":false,"prefix":"","firstName":"Prabhakar","middleName":"B.","lastName":"Sharma","suffix":""},{"id":631155256,"identity":"5c274ed3-430f-11f1-b2c4-06cc9d20a69f","order_by":2,"name":"Rutvik H. Desai","email":"","orcid":"","institution":"University of South Carolina","correspondingAuthor":false,"prefix":"","firstName":"Rutvik","middleName":"H.","lastName":"Desai","suffix":""},{"id":631155297,"identity":"67e0ad7d-430f-11f1-b2c4-06cc9d20a69f","order_by":3,"name":"Valerie L. Shalin","email":"","orcid":"","institution":"Wright State University","correspondingAuthor":false,"prefix":"","firstName":"Valerie","middleName":"L.","lastName":"Shalin","suffix":""},{"id":631155389,"identity":"7383e479-430f-11f1-b2c4-06cc9d20a69f","order_by":4,"name":"Amit Sheth","email":"","orcid":"","institution":"University of South Carolina","correspondingAuthor":false,"prefix":"","firstName":"Amit","middleName":"","lastName":"Sheth","suffix":""}],"badges":[],"createdAt":"2024-06-17 18:08:19","currentVersionCode":2,"declarations":"","doi":"10.21203/rs.3.rs-4595656/v2","doiUrl":"https://doi.org/10.21203/rs.3.rs-4595656/v2","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108181490,"identity":"f5fcbb4d-07f4-40b5-b6b4-f1e8af26e9e7","added_by":"auto","created_at":"2026-04-30 08:58:41","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":595430,"visible":true,"origin":"","legend":"","description":"","filename":"BMC042126Version.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4595656/v2_covered_ab2c6e3e-650e-49a7-8241-ae7cae8cf15d.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Artificial intelligence based detection of early cognitive impairment using language, speech, and demographic features: Model development and validation","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"bmc-medical-informatics-and-decision-making","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"midm","sideBox":"Learn more about [BMC Medical Informatics and Decision Making](http://bmcmedinformdecismak.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/midm/default.aspx","title":"BMC Medical Informatics and Decision Making","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-4595656/v2","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4595656/v2","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground\u003c/h2\u003e \u003cp\u003eMild cognitive impairment (MCI) is a prevalent condition among older adults and a potential marker for dementia. The current challenge lies in diagnosing MCI among healthy older populations. This diagnosis typically requires extensive labor-intensive neuropsychological evaluation using tools like the Mini-Mental State Examination (MMSE) or the MoCA (Montreal Cognitive Assessment) based on specific diagnostic criteria.\u003c/p\u003e\u003ch2\u003eObjective\u003c/h2\u003e \u003cp\u003eThis study used knowledge-guided machine learning (ML) algorithms and large language models (LLMs) to build diagnostic models. Our approach generates a clinician-guided classification by augmenting LLMs with external knowledge to predict levels of MCI by using the verbal text from picture description tasks.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e \u003cp\u003eThe models used language features from two picture description tasks, along with demographic features. They aimed to distinguish between three levels of MCI (MCI, possible MCI, and healthy group). The dataset exhibits class imbalance, with relatively fewer MCI and possible-MCI cases compared to healthy participants. This imbalance is addressed using SMOTE and stratified cross-validation. We utilized the cognitive cross-domain attention model (CCDA) to integrate the attention mechanism of diverse types of information into our training process, improving performance.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e \u003cp\u003eWe demonstrate the efficacy of machine learning, large language models (LLMs), and knowledge-integrated LLMs built on semantic, syntactic, lexical, fluency, and demographic features to identify different levels of cognitive decline from the analysis of verbal utterances. Our CCDA model detected MCI from the participant input, aided by an external attention mechanism. Statistical analysis was conducted using a significance threshold of α\u0026thinsp;=\u0026thinsp;0.05. Results that do not meet this threshold are interpreted as indicative trends rather than statistically significant findings. An ablation study (Table\u0026nbsp;6) showed the impact of the attention mechanism and LLM approach on performance. The proposed CCDA model achieved a mean AUC of 0.81 (95% CI: 0.77\u0026ndash;0.85) and an F1 score of 0.73 (95% CI: 0.69\u0026ndash;0.76) using stratified 10-fold cross-validation.\u003c/p\u003e\u003ch2\u003eConclusion\u003c/h2\u003e \u003cp\u003eOur knowledge-augmented approach compared favorably to contemporary LLM approaches, indicating the promise of knowledge-augmented learning in detecting MCI. This framework can support early, non-invasive screening for cognitive decline in telehealth and resource-limited settings, assisting clinicians in identifying at-risk individuals for further evaluation.\u003c/p\u003e","manuscriptTitle":"Artificial intelligence based detection of early cognitive impairment using language, speech, and demographic features: Model development and validation","msid":"","msnumber":"","nonDraftVersions":[{"code":2,"date":"2026-04-28 14:44:20","doi":"10.21203/rs.3.rs-4595656/v2","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewersInvited","content":"","date":"2026-04-24T11:38:26+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-04-22T09:06:15+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Medical Informatics and Decision Making","date":"2026-04-19T19:06:16+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-medical-informatics-and-decision-making","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"midm","sideBox":"Learn more about [BMC Medical Informatics and Decision Making](http://bmcmedinformdecismak.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/midm/default.aspx","title":"BMC Medical Informatics and Decision Making","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}},{"code":"","date":"2026-04-07 12:47:17","doi":"","editorialEvents":[{"type":"decision","content":"Revision requested","date":"2026-04-07T12:47:17+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-06T10:02:03+00:00","index":"hide","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-09-23T10:43:35+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-07-27T16:05:43+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"227601755790373462103678045808258130248","date":"2025-07-07T17:48:14+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"179138485504077279063571373231393245168","date":"2025-07-03T13:55:15+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-02T10:16:24+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"187778435149397718955669197376027358706","date":"2025-06-02T10:11:19+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-06-01T20:11:21+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-05-02T13:37:18+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Medical Informatics and Decision Making","date":"2025-05-01T21:15:38+00:00","index":"","fulltext":""},{"type":"notPreprinted","content":""}],"status":"timeline","journal":{"display":true,"email":"[email protected]","identity":"bmc-medical-informatics-and-decision-making","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"midm","sideBox":"Learn more about [BMC Medical Informatics and Decision Making](http://bmcmedinformdecismak.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/midm/default.aspx","title":"BMC Medical Informatics and Decision Making","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"72fe6da3-0d41-484d-b4a3-e7665edcc249","owner":[],"postedDate":"April 28th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-04-24T11:53:20+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-28 14:44:20","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v2","identity":"rs-4595656","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4595656","identity":"rs-4595656","version":["v2"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}