Bridging the Gap in Dermatology: AI-Driven Model for Real-Time Skin Disease Diagnosis

Bridging the Gap in Dermatology: AI-Driven Model for Real-Time Skin Disease 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 Research Article Bridging the Gap in Dermatology: AI-Driven Model for Real-Time Skin Disease Diagnosis Dayam Nadeem, . Neha, Nida Saifi, Asiya Irshad This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9569126/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 4 You are reading this latest preprint version Abstract Skin problems are a significant health concern in recent days. Delayed or inaccurate diagnosis may result in precipitate clinical consequences. Conventional diagnostic methods predominately entail on specialist visual assessment. In limited resource environments such evaluations are limited by subjectivity and rely on the availability of dermatologist. This paper proposes an optimised automated AI-driven model for skin disease classification to bridge this gap. A deep learning model based on DenseNet121 with transfer learning was trained on a multi-class dermoscopic image dataset comprising nine common skin conditions. The proposed model achieved a classification accuracy of 95.33% with a test loss of 0.1149, reflecting strong performance in dermatological image analysis. To enable practical deployment, the trained model was optimized and converted into TensorFlow Lite (TFLite), allowing fully offline, on-device inference without any internet connectivity. By simply capturing an image of the affected skin region, users can obtain instant disease predictions along with confidence scores and precautionary guidance. The lightweight model was integrated into a m-health application developed using Kotlin and Jetpack Compose, ensuring real-time and efficient execution directly on the user’s device. The proposed system offers a scalable, energy-efficient, and accessible diagnostic solution, effectively bridging advanced deep learning techniques with offline healthcare applications. The designed model is particularly suitable for deployment in resource-constrained environments, supporting early detection and timely intervention without reliance on network infrastructure. Skin Disease Classification Deep Learning Multi-class Dermoscopic Image DenseNet121 Dermatology AI m-Health Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviewers invited by journal 07 May, 2026 Editor assigned by journal 07 May, 2026 Submission checks completed at journal 02 May, 2026 First submitted to journal 29 Apr, 2026 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-9569126","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":641487767,"identity":"518e8784-5a6e-4f20-8e15-32b701137d13","order_by":0,"name":"Dayam Nadeem","email":"","orcid":"","institution":"Jamia Hamdard","correspondingAuthor":false,"prefix":"","firstName":"Dayam","middleName":"","lastName":"Nadeem","suffix":""},{"id":641487769,"identity":"47697e52-5186-4076-934c-8a23b5646539","order_by":1,"name":". Neha","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA+ElEQVRIiWNgGAWjYFACHgaGD0DMBmIASQaGAyBRA/xaGGeQrIWZB2YdQgseYM7ee/CzjYxdNB/72YOfbpTZ5fMdYH74gaHgDk4tlj3nkqVzeJJz23jygIxzyZYzD7AZSzAYPMOpxeBGjgFQC3NuGwOQkdvGbGBwgMEMKH4Yt5b7b4x/W/DU57bxAxm5bfVALezf8Gu5wWMmzcBzOLdNIscMaMthoBYeAracyTGz7OE5DtTyxsw659xxA8nDPMUSCfi0HD9jfONnT3Xu/P4c49s5ZdUGfMfbN3748Ae3FjBg7EHmMQNxAn4NQPCDoIpRMApGwSgYyQAAl4xQX9Ix5kYAAAAASUVORK5CYII=","orcid":"","institution":"Jamia Hamdard","correspondingAuthor":true,"prefix":"","firstName":".","middleName":"","lastName":"Neha","suffix":""},{"id":641487770,"identity":"4783f757-b31b-43df-8a87-701a9a09c3d7","order_by":2,"name":"Nida Saifi","email":"","orcid":"","institution":"Jamia Hamdard","correspondingAuthor":false,"prefix":"","firstName":"Nida","middleName":"","lastName":"Saifi","suffix":""},{"id":641487771,"identity":"dca289ee-93ad-4c1a-8fbb-036508dc791c","order_by":3,"name":"Asiya Irshad","email":"","orcid":"","institution":"Jamia Hamdard","correspondingAuthor":false,"prefix":"","firstName":"Asiya","middleName":"","lastName":"Irshad","suffix":""}],"badges":[],"createdAt":"2026-04-29 18:38:18","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9569126/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9569126/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":109800230,"identity":"912c50df-fc09-4ec7-8ed8-69452297b258","added_by":"auto","created_at":"2026-05-22 15:36:57","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":779557,"visible":true,"origin":"","legend":"","description":"","filename":"BridgingtheGapinDermatology.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9569126/v1_covered_45cb5fbc-7900-42fe-a465-262f20577064.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Bridging the Gap in Dermatology: AI-Driven Model for Real-Time Skin Disease 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":"acta-universitatis-sapientiae-mathematica","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Acta Universitatis Sapientiae, Mathematica](https://link.springer.com/journal/44426)","snPcode":"44426","submissionUrl":"https://submission.springernature.com/new-submission/44426/3","title":"Acta Universitatis Sapientiae, Mathematica","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Skin Disease Classification, Deep Learning, Multi-class Dermoscopic Image, DenseNet121, Dermatology AI, m-Health","lastPublishedDoi":"10.21203/rs.3.rs-9569126/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9569126/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eSkin problems are a significant health concern in recent days. Delayed or inaccurate diagnosis may result in precipitate clinical consequences. Conventional diagnostic methods predominately entail on specialist visual assessment. In limited resource environments such evaluations are limited by subjectivity and rely on the availability of dermatologist. This paper proposes an optimised automated AI-driven model for skin disease classification to bridge this gap.\u003c/p\u003e \u003cp\u003eA deep learning model based on DenseNet121 with transfer learning was trained on a multi-class dermoscopic image dataset comprising nine common skin conditions. The proposed model achieved a classification accuracy of 95.33% with a test loss of 0.1149, reflecting strong performance in dermatological image analysis. To enable practical deployment, the trained model was optimized and converted into TensorFlow Lite (TFLite), allowing fully offline, on-device inference without any internet connectivity. By simply capturing an image of the affected skin region, users can obtain instant disease predictions along with confidence scores and precautionary guidance. The lightweight model was integrated into a m-health application developed using Kotlin and Jetpack Compose, ensuring real-time and efficient execution directly on the user\u0026rsquo;s device.\u003c/p\u003e \u003cp\u003eThe proposed system offers a scalable, energy-efficient, and accessible diagnostic solution, effectively bridging advanced deep learning techniques with offline healthcare applications. The designed model is particularly suitable for deployment in resource-constrained environments, supporting early detection and timely intervention without reliance on network infrastructure.\u003c/p\u003e","manuscriptTitle":"Bridging the Gap in Dermatology: AI-Driven Model for Real-Time Skin Disease Diagnosis","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-18 13:02:08","doi":"10.21203/rs.3.rs-9569126/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewersInvited","content":"","date":"2026-05-07T10:04:15+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-05-07T09:06:43+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-05-02T06:20:40+00:00","index":"","fulltext":""},{"type":"submitted","content":"Acta Universitatis Sapientiae, Mathematica","date":"2026-04-29T18:30:57+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"acta-universitatis-sapientiae-mathematica","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Acta Universitatis Sapientiae, Mathematica](https://link.springer.com/journal/44426)","snPcode":"44426","submissionUrl":"https://submission.springernature.com/new-submission/44426/3","title":"Acta Universitatis Sapientiae, Mathematica","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"54560997-1356-4b38-9437-a7f0b1094df5","owner":[],"postedDate":"May 18th, 2026","published":true,"recentEditorialEvents":[{"type":"reviewersInvited","content":"4","date":"2026-05-07T10:04:15+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-05-07T09:06:43+00:00","index":"","fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-18T13:02:08+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-18 13:02:08","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9569126","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9569126","identity":"rs-9569126","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}