Generalizability, Interpretability, and Clinical Readiness of Deep Learning Methods for Alzheimer’s Disease: A Systematic Literature Review

Generalizability, Interpretability, and Clinical Readiness of Deep Learning Methods for Alzheimer’s Disease: A Systematic Literature Review | 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 Systematic Review Generalizability, Interpretability, and Clinical Readiness of Deep Learning Methods for Alzheimer’s Disease: A Systematic Literature Review Sohni Malik, Tanya Kumari, Sanjana Bamnawat, Sonali This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8071648/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 Early and correct identification of Alzheimer's disease is essential for prompt intervention and medical care. Recent advancements use machine learning and deep learning techniques on neuroimaging, genetic, and clinical data to identify Alzheimer’s disease from cognitively normal patients and predict progression from moderate cognitive impairment. This systematic literature review examines studies published between 2019 and 2025 that utilized major datasets, including the Alzheimer’s Disease Neuroimaging Initiative, as well as inputs such as T1-weighted magnetic resonance imaging, electroencephalography, and multimodal neuroimaging data. The reviewed approaches encompass voxel-wise three-dimensional convolutional neural networks, hybrid convolutional neural network–transformer architectures, attention-based multimodal fusion frameworks, and conventional machine learning models such as Random Forest, Extreme Gradient Boosting, and Generalized Linear Models. Common preprocessing techniques include intensity correction, spatial normalization, skull stripping, and data augmentation through rotations, flips, and generative adversarial network–based oversampling. The primary evaluation metrics reported are accuracy, sensitivity, specificity, F1-score, and area under the receiver operating characteristic curve. Interpretability techniques such as Grad-CAM, Layer-Wise Relevance Propagation, and saliency maps were increasingly adopted to visualize discriminative brain regions. Models integrating hybrid architectures and multimodal information demonstrate enhanced robustness, external validation remains limited. Persistent challenges include class imbalance, subject-level data leakage, small dataset sizes, and poor cross-cohort generalizability. Future research should emphasize larger, multi-center datasets, standardized evaluation protocols, and interpretable models that are clinically meaningful and translatable. Alzheimer’s Disease Deep Learning Machine Learning Image Processing Interpretability Neuroimaging Systematic Review Full Text Additional Declarations The authors declare no competing interests. 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-8071648","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Systematic Review","associatedPublications":[],"authors":[{"id":542322638,"identity":"d526322a-32ef-4897-b56a-afeca716f5b7","order_by":0,"name":"Sohni Malik","email":"data:image/png;base64,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","orcid":"","institution":"IGDTUW","correspondingAuthor":true,"prefix":"","firstName":"Sohni","middleName":"","lastName":"Malik","suffix":""},{"id":542322639,"identity":"d1a59928-0f9e-4c7b-a37b-51d4d546a7a0","order_by":1,"name":"Tanya Kumari","email":"","orcid":"","institution":"IGDTUW","correspondingAuthor":false,"prefix":"","firstName":"Tanya","middleName":"","lastName":"Kumari","suffix":""},{"id":542322640,"identity":"7ced6a1e-f373-4ba3-bc98-cea889c5dc80","order_by":2,"name":"Sanjana Bamnawat","email":"","orcid":"","institution":"IGDTUW","correspondingAuthor":false,"prefix":"","firstName":"Sanjana","middleName":"","lastName":"Bamnawat","suffix":""},{"id":542322641,"identity":"f524c684-460b-4b6e-95bd-a548fa7a1565","order_by":3,"name":"Sonali","email":"","orcid":"","institution":"IGDTUW","correspondingAuthor":false,"prefix":"","firstName":"","middleName":"","lastName":"Sonali","suffix":""}],"badges":[],"createdAt":"2025-11-10 01:09:18","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-8071648/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8071648/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":95671980,"identity":"4e7371bc-cbb7-4444-9f4b-2811a9834c0d","added_by":"auto","created_at":"2025-11-11 17:32:14","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":252752,"visible":true,"origin":"","legend":"","description":"","filename":"SLR.docx","url":"https://assets-eu.researchsquare.com/files/rs-8071648/v1/5b30d44734def5d95f046791.docx"},{"id":95671979,"identity":"f80130c3-dd4e-4c4c-9f5f-cc3a1cbfe98c","added_by":"auto","created_at":"2025-11-11 17:32:14","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":342,"visible":true,"origin":"","legend":"","description":"","filename":"rs8071648.json","url":"https://assets-eu.researchsquare.com/files/rs-8071648/v1/48cc4340829b383d48802bd3.json"},{"id":95799085,"identity":"380eb167-3462-4d9a-8300-197eaf5e6ea2","added_by":"auto","created_at":"2025-11-13 08:18:44","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":119051,"visible":true,"origin":"","legend":"","description":"","filename":"rs80716480enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-8071648/v1/dba05d1c6953e402840de23d.xml"},{"id":95671988,"identity":"15fd939d-9ab4-443d-a4ec-f4f615037c47","added_by":"auto","created_at":"2025-11-11 17:32:14","extension":"jpeg","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":322809,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8071648/v1/f29f0ed01abaa621cd51ee16.jpeg"},{"id":95798009,"identity":"38e00192-f93d-4e8b-9176-a8d11fcebe04","added_by":"auto","created_at":"2025-11-13 08:13:35","extension":"png","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":16293,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8071648/v1/c29d72f363a269b74bc8d27a.png"},{"id":95671983,"identity":"bb1e4d1f-bbf1-4325-ba6b-1f7b5d94b9fe","added_by":"auto","created_at":"2025-11-11 17:32:14","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":24561,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8071648/v1/a008b31bfc6a734e60b35169.png"},{"id":95798756,"identity":"83e5b794-3b05-4b90-9787-0b5dac7f84ec","added_by":"auto","created_at":"2025-11-13 08:17:45","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":80052,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-8071648/v1/825fb608ed6be2ca554164e7.png"},{"id":95671984,"identity":"fe216f1f-94ec-4e9b-8567-483a4e6e8ee9","added_by":"auto","created_at":"2025-11-11 17:32:14","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":27169,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-8071648/v1/4b94445c2e7669b6174c836c.png"},{"id":95798699,"identity":"259d6508-bce5-4483-aa55-af85b5699570","added_by":"auto","created_at":"2025-11-13 08:17:39","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":19758,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-8071648/v1/0851ce338bd6a28bc2e2b215.png"},{"id":95799942,"identity":"97226833-fd68-45f9-901a-4c37cb1b7d8b","added_by":"auto","created_at":"2025-11-13 08:21:10","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":10576,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-8071648/v1/b8a01c0e71396ae26687f04b.png"},{"id":95671989,"identity":"ac89aab5-d67d-41be-b6d5-aff60c039866","added_by":"auto","created_at":"2025-11-11 17:32:14","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":74421,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8071648/v1/b39c1bda679e6967e525df1b.png"},{"id":95671994,"identity":"d7b2155d-868d-4613-b32e-d45b6e03c7b8","added_by":"auto","created_at":"2025-11-11 17:32:15","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":3875,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8071648/v1/c639384991b6a62a64b262a4.png"},{"id":95671991,"identity":"17fa21d5-098e-4eda-bf20-6643480ac27d","added_by":"auto","created_at":"2025-11-11 17:32:14","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5785,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8071648/v1/feb2b1f183bf28bf7d8104a8.png"},{"id":95797331,"identity":"3b96c93e-2ee5-450d-a9b4-05f50fdcbac2","added_by":"auto","created_at":"2025-11-13 08:03:36","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":19477,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-8071648/v1/2b287d6a8dbd6681588ca893.png"},{"id":95797381,"identity":"f3ce14bf-6cca-4369-ac98-dd93d78f3e47","added_by":"auto","created_at":"2025-11-13 08:04:27","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":7509,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-8071648/v1/85157d1e576462a904ef5778.png"},{"id":95671993,"identity":"0ef7c636-8f86-4d8d-9200-887016e2c7a2","added_by":"auto","created_at":"2025-11-11 17:32:14","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4673,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-8071648/v1/3d8dae4e781a3e6208cbace3.png"},{"id":95671995,"identity":"3e514053-1760-45ec-b143-3b1865c23799","added_by":"auto","created_at":"2025-11-11 17:32:15","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2649,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-8071648/v1/66c24cee70be73199a3b442b.png"},{"id":95671996,"identity":"1822603a-7b26-4732-9240-4038415513cc","added_by":"auto","created_at":"2025-11-11 17:32:15","extension":"xml","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":118296,"visible":true,"origin":"","legend":"","description":"","filename":"rs80716480structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-8071648/v1/4fc0ce2ecdc0613ec50536db.xml"},{"id":95671997,"identity":"c3c0cbd8-e6ef-4531-b101-b024bc15410c","added_by":"auto","created_at":"2025-11-11 17:32:15","extension":"html","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":127532,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-8071648/v1/bfc818719f68a23e391af64e.html"},{"id":95804692,"identity":"57170fb6-1a09-40b8-a289-3181f9652f9d","added_by":"auto","created_at":"2025-11-13 08:39:08","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":640062,"visible":true,"origin":"","legend":"","description":"","filename":"SLR.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8071648/v1_covered_2e275922-c507-4249-b841-95fe4eb93296.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003e\u003cstrong\u003eGeneralizability, Interpretability, and Clinical Readiness of Deep Learning Methods for Alzheimer’s Disease: A Systematic Literature Review\u003c/strong\u003e\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Indira Gandhi Delhi Technical University for Women","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":"Alzheimer’s Disease, Deep Learning, Machine Learning, Image Processing, Interpretability, Neuroimaging, Systematic Review","lastPublishedDoi":"10.21203/rs.3.rs-8071648/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8071648/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eEarly and correct identification of Alzheimer's disease is essential for prompt intervention and medical care. Recent advancements use machine learning and deep learning techniques on neuroimaging, genetic, and clinical data to identify Alzheimer\u0026rsquo;s disease from cognitively normal patients and predict progression from moderate cognitive impairment. This systematic literature review examines studies published between 2019 and 2025 that utilized major datasets, including the Alzheimer\u0026rsquo;s Disease Neuroimaging Initiative, as well as inputs such as T1-weighted magnetic resonance imaging, electroencephalography, and multimodal neuroimaging data. The reviewed approaches encompass voxel-wise three-dimensional convolutional neural networks, hybrid convolutional neural network\u0026ndash;transformer architectures, attention-based multimodal fusion frameworks, and conventional machine learning models such as Random Forest, Extreme Gradient Boosting, and Generalized Linear Models. Common preprocessing techniques include intensity correction, spatial normalization, skull stripping, and data augmentation through rotations, flips, and generative adversarial network\u0026ndash;based oversampling. The primary evaluation metrics reported are accuracy, sensitivity, specificity, F1-score, and area under the receiver operating characteristic curve. Interpretability techniques such as Grad-CAM, Layer-Wise Relevance Propagation, and saliency maps were increasingly adopted to visualize discriminative brain regions. Models integrating hybrid architectures and multimodal information demonstrate enhanced robustness, external validation remains limited. Persistent challenges include class imbalance, subject-level data leakage, small dataset sizes, and poor cross-cohort generalizability. Future research should emphasize larger, multi-center datasets, standardized evaluation protocols, and interpretable models that are clinically meaningful and translatable.\u003c/p\u003e","manuscriptTitle":"Generalizability, Interpretability, and Clinical Readiness of Deep Learning Methods for Alzheimer’s Disease: A Systematic Literature Review","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-11 17:32:10","doi":"10.21203/rs.3.rs-8071648/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":"33a9bffd-cf10-4dc1-9a2c-4b003e77ebe6","owner":[],"postedDate":"November 11th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-11-11T17:32:10+00:00","versionOfRecord":[],"versionCreatedAt":"2025-11-11 17:32:10","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8071648","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8071648","identity":"rs-8071648","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}