Multimodal CNN-PD: A Parkinson's Disease Diagnostics Framework Using Multimodal Convolutional Neural Network

Multimodal CNN-PD: A Parkinson's Disease Diagnostics Framework Using Multimodal Convolutional Neural Network | 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 Multimodal CNN-PD: A Parkinson's Disease Diagnostics Framework Using Multimodal Convolutional Neural Network Umar Muhammad Ibrahim, Kavimbi Chipusu, Taisheng Zeng, Yuguang Ye, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8060316/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract As a common neurodegenerative condition, Parkinson's disease markedly impairs motor abilities, cognitive function, and quality of life. Establishing an early and precise diagnosis, even in its prodromal phase, is a key clinical focus to enable timely treatment and enhance patient management. Deep learning (DL) and machine learning (ML) have demonstrated significant potential in boosting diagnostic accuracy for Parkinson's disease (PD). Nevertheless, the scarcity of large-scale, well-annotated datasets remains a major obstacle, underscoring the critical need for multimodal data integration to enhance model robustness and generalizability. This study proposes MultimodalCNN-PD, a novel multimodal convolutional neural network framework, to improve PD classification accuracy. The model integrates Magnetic Resonance Imaging data with clinical metadata, including motor and cognitive assessments, demographics, and genetic biomarkers. The architecture incorporates Convolutional Block Attention Modules within a ResNet-18 backbone to refine spatial and channel-wise features and introduces a Meta Guided Cross Attention (MGCA) mechanism to align imaging and metadata through multi-head attention. An ensemble-based feature selection strategy further extracts the most discriminative clinical features. The model was robustly evaluated on the Parkinson’s Progression Markers Initiative dataset, employing a subject-level five-fold cross-validation scheme and a held-out test set. It achieved a multiclass classification accuracy of 95.68% in distinguishing Normal Control, prodromal PD, and diagnosed PD, outperforming existing state-of-the-art models. Its strong generalizability was confirmed through external validation on the OASIS-3 dataset, where it attained 94.10% accuracy despite differences in demographics and data acquisition. Ablation studies verified the performance contributions of the CBAM, MGCA, and ensemble feature selection modules. By effectively integrating neuroimaging and clinical metadata, this framework sets a new benchmark for multiclass PD diagnosis and demonstrates considerable potential as a robust, clinically applicable AI tool for early detection and personalized management of neurodegenerative diseases. Health sciences/Biomarkers Biological sciences/Computational biology and bioinformatics Health sciences/Neurology Biological sciences/Neuroscience MultimodalCNN-PD Generalizability Ablation Studies Patient Management AI-driven Diagnostic Tool Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted 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-8060316","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":554034397,"identity":"f5fcaef2-9996-45b7-867f-d4246fd9d297","order_by":0,"name":"Umar Muhammad Ibrahim","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA2UlEQVRIiWNgGAWjYFACxjYgcYCHgb0HKnCAaC08Z4B0AlFaGNggyiRyiNRicO1w2+OKmjsyujPfHpP8+YNBju9GAuPnAnxabie2G5459ozH7HZemjRPAoOx5I0EZukZ+LW0STawHQZqyTGTBjosccONBDZmHoJa/gG13DxjJvkjgaGeOC2NbUAtN3jMJIAOSzAgpEUS5JfGPqCWMznG1jxpEoYzzzxslsanhe92+rOHDd8O25sdP2N484eNjTzf8eSDn/FpQQcSQMzYQIKGUTAKRsEoGAXYAADbVE7bzVdFVgAAAABJRU5ErkJggg==","orcid":"","institution":"Huazhong University of Science and Technology","correspondingAuthor":true,"prefix":"","firstName":"Umar","middleName":"Muhammad","lastName":"Ibrahim","suffix":""},{"id":554034398,"identity":"c1cae6c0-2660-40c1-a3f8-d6191bee5733","order_by":1,"name":"Kavimbi Chipusu","email":"","orcid":"","institution":"University of Saskatchewan","correspondingAuthor":false,"prefix":"","firstName":"Kavimbi","middleName":"","lastName":"Chipusu","suffix":""},{"id":554034399,"identity":"6b58eb03-a700-4612-9303-b9346b2e8353","order_by":2,"name":"Taisheng Zeng","email":"","orcid":"","institution":"Quanzhou Normal University","correspondingAuthor":false,"prefix":"","firstName":"Taisheng","middleName":"","lastName":"Zeng","suffix":""},{"id":554034400,"identity":"57a85e9c-a927-4739-9b62-1e358830cac1","order_by":3,"name":"Yuguang Ye","email":"","orcid":"","institution":"Quanzhou Normal University","correspondingAuthor":false,"prefix":"","firstName":"Yuguang","middleName":"","lastName":"Ye","suffix":""},{"id":554034401,"identity":"d005db0b-b96d-4e5f-84ec-7ead96289db3","order_by":4,"name":"Bijiao Ding","email":"","orcid":"","institution":"Huaqiao University Affiliated Strait Hospital","correspondingAuthor":false,"prefix":"","firstName":"Bijiao","middleName":"","lastName":"Ding","suffix":""},{"id":554034402,"identity":"306d7437-f110-4a27-9190-ec80bd72fafd","order_by":5,"name":"Yifeng Huang","email":"","orcid":"","institution":"Huaqiao University Affiliated Strait Hospital","correspondingAuthor":false,"prefix":"","firstName":"Yifeng","middleName":"","lastName":"Huang","suffix":""},{"id":554034403,"identity":"020df6ce-6f67-4775-b41b-4734ccd2e80b","order_by":6,"name":"Jianlong Huang","email":"","orcid":"","institution":"Quanzhou Normal University","correspondingAuthor":false,"prefix":"","firstName":"Jianlong","middleName":"","lastName":"Huang","suffix":""}],"badges":[],"createdAt":"2025-11-07 22:23:16","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8060316/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8060316/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":97321320,"identity":"bb6ac3df-5d38-4c58-8fe6-50b9698e1016","added_by":"auto","created_at":"2025-12-03 07:54:48","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1412000,"visible":true,"origin":"","legend":"","description":"","filename":"20251117ManuscriptCNNPD.docx","url":"https://assets-eu.researchsquare.com/files/rs-8060316/v1/0e10e4c3d28f1827dc3477c1.docx"},{"id":97321319,"identity":"c3815e52-0f8e-4d05-ab28-b40c70acd605","added_by":"auto","created_at":"2025-12-03 07:54:48","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":9147,"visible":true,"origin":"","legend":"","description":"","filename":"0b24391da55f4f45aec5137cc1f69521.json","url":"https://assets-eu.researchsquare.com/files/rs-8060316/v1/32905664bbbf573949306d36.json"},{"id":103305035,"identity":"3ba44660-42c3-42a1-af35-0f4ea7b3ff4f","added_by":"auto","created_at":"2026-02-24 08:58:03","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":963611,"visible":true,"origin":"","legend":"","description":"","filename":"20251117ManuscriptCNNPD.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8060316/v1_covered_71fae6af-33c2-4f94-b6aa-df22fe88707e.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Multimodal CNN-PD: A Parkinson's Disease Diagnostics Framework Using Multimodal Convolutional Neural Network","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"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":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"MultimodalCNN-PD, Generalizability, Ablation Studies, Patient Management, AI-driven Diagnostic Tool","lastPublishedDoi":"10.21203/rs.3.rs-8060316/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8060316/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"As a common neurodegenerative condition, Parkinson's disease markedly impairs motor abilities, cognitive function, and quality of life. Establishing an early and precise diagnosis, even in its prodromal phase, is a key clinical focus to enable timely treatment and enhance patient management. Deep learning (DL) and machine learning (ML) have demonstrated significant potential in boosting diagnostic accuracy for Parkinson's disease (PD). Nevertheless, the scarcity of large-scale, well-annotated datasets remains a major obstacle, underscoring the critical need for multimodal data integration to enhance model robustness and generalizability. This study proposes MultimodalCNN-PD, a novel multimodal convolutional neural network framework, to improve PD classification accuracy. The model integrates Magnetic Resonance Imaging data with clinical metadata, including motor and cognitive assessments, demographics, and genetic biomarkers. The architecture incorporates Convolutional Block Attention Modules within a ResNet-18 backbone to refine spatial and channel-wise features and introduces a Meta Guided Cross Attention (MGCA) mechanism to align imaging and metadata through multi-head attention. An ensemble-based feature selection strategy further extracts the most discriminative clinical features. The model was robustly evaluated on the Parkinson’s Progression Markers Initiative dataset, employing a subject-level five-fold cross-validation scheme and a held-out test set. It achieved a multiclass classification accuracy of 95.68% in distinguishing Normal Control, prodromal PD, and diagnosed PD, outperforming existing state-of-the-art models. Its strong generalizability was confirmed through external validation on the OASIS-3 dataset, where it attained 94.10% accuracy despite differences in demographics and data acquisition. Ablation studies verified the performance contributions of the CBAM, MGCA, and ensemble feature selection modules. By effectively integrating neuroimaging and clinical metadata, this framework sets a new benchmark for multiclass PD diagnosis and demonstrates considerable potential as a robust, clinically applicable AI tool for early detection and personalized management of neurodegenerative diseases.","manuscriptTitle":"Multimodal CNN-PD: A Parkinson's Disease Diagnostics Framework Using Multimodal Convolutional Neural Network","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-03 07:54:43","doi":"10.21203/rs.3.rs-8060316/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"047b5142-013f-4ba7-8a6f-4a4825fdfb3f","owner":[],"postedDate":"December 3rd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":58954774,"name":"Health sciences/Biomarkers"},{"id":58954775,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":58954776,"name":"Health sciences/Neurology"},{"id":58954777,"name":"Biological sciences/Neuroscience"}],"tags":[],"updatedAt":"2026-02-24T08:56:15+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-03 07:54:43","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8060316","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8060316","identity":"rs-8060316","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}