Deep Learning for Diabetic Retinopathy Detection: A Review of Multimodal Data Fusion Approaches

Deep Learning for Diabetic Retinopathy Detection: A Review of Multimodal Data Fusion Approaches | 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 Deep Learning for Diabetic Retinopathy Detection: A Review of Multimodal Data Fusion Approaches Kartina Diah Kesuma Wardhani, Shahreen Kasim, Rohayanti Hassan, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7196434/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 Diabetic retinopathy (DR) is a diabetes-induced eye disease that affects the blood vessels of the retina, and a lack of proper DR detection could result in the loss of vision. Although deep learning (DL) has successfully analyzed single-modality medical data, DR diagnosis often requires interpreting diverse information such as retinal imaging and clinical data. Multimodal data fusion has the potential to accommodate robust and complementary information between these sources for more accurate diagnostic decisions. However, DR detection using deep learning-based multimodal fusion is still challenging and underdeveloped. This review investigates recent advances in applying DL techniques to multimodal DR detection , focusing on model architecture, modality combinations, fusion strategies, and performance metrics. Among these architectures, convolutional neural networks (CNNs) are the most popular, and the fusion of fundus images with OCT or 1 EHR data is the most common pairing. Early and joint fusion strategies dominate, while model performance is typically assessed using accuracy, AUC, sensitivity, and F1-score. Despite promising progress, the field still faces challenges including modality heterogeneity, lack of standardized multimodal datasets, and limited model interpretability. Emerging trends point toward hybrid architecture, attention mechanisms, and self-supervised learning as potential solutions. This review highlights current developments and outlines future directions to support the design of scalable, generalizable, and clinically applicable multimodal DL systems for DR detection. Diabetic Retinopathy Retinal Imaging Clinical Data Deep Learning Multimodal Data Fusion Strategy 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-7196434","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":496658227,"identity":"f9a76a06-cc31-4b83-a365-ac05df76de24","order_by":0,"name":"Kartina Diah Kesuma Wardhani","email":"data:image/png;base64,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","orcid":"","institution":"Tun Hussein Onn University of Malaysia","correspondingAuthor":true,"prefix":"","firstName":"Kartina","middleName":"Diah Kesuma","lastName":"Wardhani","suffix":""},{"id":496658228,"identity":"2b06d2dd-fe2b-48ce-bbec-dc128edcf3c0","order_by":1,"name":"Shahreen Kasim","email":"","orcid":"","institution":"Tun Hussein Onn University of Malaysia","correspondingAuthor":false,"prefix":"","firstName":"Shahreen","middleName":"","lastName":"Kasim","suffix":""},{"id":496658229,"identity":"6b8cfec5-4fbe-4ced-b051-48a0e129f8f0","order_by":2,"name":"Rohayanti Hassan","email":"","orcid":"","institution":"University of Technology Malaysia","correspondingAuthor":false,"prefix":"","firstName":"Rohayanti","middleName":"","lastName":"Hassan","suffix":""},{"id":496658230,"identity":"d54591e6-2e6f-46e2-a6e0-a6ae8d14c266","order_by":3,"name":"Rahmat Hidayat","email":"","orcid":"","institution":"Politeknik Negeri Padang","correspondingAuthor":false,"prefix":"","firstName":"Rahmat","middleName":"","lastName":"Hidayat","suffix":""},{"id":496658231,"identity":"b3bff476-f69e-4a16-b40f-7ffcda78d711","order_by":4,"name":"Khaled Mahmud Sujon","email":"","orcid":"","institution":"University of Technology Malaysia","correspondingAuthor":false,"prefix":"","firstName":"Khaled","middleName":"Mahmud","lastName":"Sujon","suffix":""}],"badges":[],"createdAt":"2025-07-23 12:38:22","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7196434/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7196434/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":90279114,"identity":"f7f860f0-739d-492a-9d12-5af3582874cc","added_by":"auto","created_at":"2025-09-01 03:53:43","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1336671,"visible":true,"origin":"","legend":"","description":"","filename":"AIreviewrevised.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7196434/v1_covered_da6cc2ef-71d5-4da6-abe6-e1258e53435a.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Deep Learning for Diabetic Retinopathy Detection: A Review of Multimodal Data Fusion Approaches","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":"Diabetic Retinopathy, Retinal Imaging, Clinical Data, Deep Learning, Multimodal Data, Fusion Strategy","lastPublishedDoi":"10.21203/rs.3.rs-7196434/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7196434/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Diabetic retinopathy (DR) is a diabetes-induced eye disease that affects the blood vessels of the retina, and a lack of proper DR detection could result in the loss of vision. Although deep learning (DL) has successfully analyzed single-modality medical data, DR diagnosis often requires interpreting diverse information such as retinal imaging and clinical data. Multimodal data fusion has the potential to accommodate robust and complementary information between these sources for more accurate diagnostic decisions. However, DR detection using deep learning-based multimodal fusion is still challenging and underdeveloped. This review investigates recent advances in applying DL techniques to multimodal DR detection , focusing on model architecture, modality combinations, fusion strategies, and performance metrics. Among these architectures, convolutional neural networks (CNNs) are the most popular, and the fusion of fundus images with OCT or 1 EHR data is the most common pairing. Early and joint fusion strategies dominate, while model performance is typically assessed using accuracy, AUC, sensitivity, and F1-score. Despite promising progress, the field still faces challenges including modality heterogeneity, lack of standardized multimodal datasets, and limited model interpretability. Emerging trends point toward hybrid architecture, attention mechanisms, and self-supervised learning as potential solutions. This review highlights current developments and outlines future directions to support the design of scalable, generalizable, and clinically applicable multimodal DL systems for DR detection.","manuscriptTitle":"Deep Learning for Diabetic Retinopathy Detection: A Review of Multimodal Data Fusion Approaches","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-07 04:30:35","doi":"10.21203/rs.3.rs-7196434/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":"9b1057c2-cd4e-4db3-91ba-c0fbf142f5ac","owner":[],"postedDate":"August 7th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-09-01T03:53:16+00:00","versionOfRecord":[],"versionCreatedAt":"2025-08-07 04:30:35","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7196434","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7196434","identity":"rs-7196434","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}