A Global Atlas of Digital Dermatology to Map Innovation and Disparities

A Global Atlas of Digital Dermatology to Map Innovation and Disparities | 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 A Global Atlas of Digital Dermatology to Map Innovation and Disparities Fabian Gröger, Simone Lionetti, Philippe Gottfrois, Alvaro Gonzalez-Jimenez, and 5 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8530334/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted You are reading this latest preprint version Abstract The adoption of artificial intelligence in dermatology promises democratized access to healthcare, but model reliability depends on the quality and comprehensiveness of the data fueling these models. Despite rapid growth in publicly available dermatology images, the field lacks quantitative key performance indicators to measure whether new datasets expand clinical coverage or merely replicate what is already known. Here we present SkinMap, a multi-modal framework for the first comprehensive audit of the field's entire data basis. We unify the publicly available dermatology datasets into a single, queryable semantic atlas comprising more than 1.1 million images of skin conditions and quantify (i) informational novelty over time, (ii) dataset redundancy, and (iii) representation gaps across demographics and diagnoses. Despite exponential growth in dataset sizes, informational novelty across time has somewhat plateaued: Some clusters, such as common neoplasms on fair skin, are densely populated, while underrepresented skin types and many rare diseases remain unaddressed. We further identify structural gaps in coverage: Darker skin tones (Fitzpatrick V-VI) constitute only 5.8% of images and pediatric patients only 3.0%, while many rare diseases and phenotype combinations remain sparsely represented. SkinMap provides infrastructure to measure blind spots and steer strategic data acquisition toward undercovered regions of clinical space. Biological sciences/Biological techniques/Imaging Biological sciences/Computational biology and bioinformatics/Machine learning Biological sciences/Computational biology and bioinformatics/Data integration Health sciences/Signs and symptoms/Skin manifestations Artificial intelligence Dermatology Health equity Data diversity Full Text Additional Declarations Yes there is potential Competing Interest. A.A.N. is a shareholder of Derma2Go AG and Derma.One GmbH. All other authors declare no competing interests. Cite Share Download PDF Status: Under Review 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-8530334","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":571603011,"identity":"9eeb8136-6927-4f63-bfa2-75cffc88df1e","order_by":0,"name":"Fabian Gröger","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABCUlEQVRIiWNgGAWjYBAC9gYehgNIfBsGBmYeMCsBlxaeA6ha0ojTggwOg8QIaGE/e/DAzx0Mdtvbmw+/+LjnfOJ2dt6DH38w2OXh1MKTl3Cw9wxD8pwzx9IsZzy7nbizmS9ZmochuRiXFnuGHIMDvG0MyRISOWbGPAduJ244zGMgzcBwILEBly38bwwO/gVryf9m/OfAOZAW458/8GmRyDE4DLTFDmgL82OGAwdAWswkePBqeZdwWLZNIkGC55gZY8+BZOMNh/nSrHkMkvE4LPfwx7dtNvYS7M2PP/w4YCe74fzZwzd/VNjh1AIFEiAFbBIIAQP86kHAHoiZPxBWNwpGwSgYBSMRAADGsFxnsma+vQAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0002-9699-688X","institution":"University of Basel","correspondingAuthor":true,"prefix":"","firstName":"Fabian","middleName":"","lastName":"Gröger","suffix":""},{"id":571603012,"identity":"6234a68e-254e-46d4-ace3-7852dc8e7a0b","order_by":1,"name":"Simone Lionetti","email":"","orcid":"","institution":"Lucerne University of Applied Sciences and Arts","correspondingAuthor":false,"prefix":"","firstName":"Simone","middleName":"","lastName":"Lionetti","suffix":""},{"id":571603013,"identity":"5957bf4c-0721-4797-b76a-c748a56da098","order_by":2,"name":"Philippe Gottfrois","email":"","orcid":"","institution":"University of Basel","correspondingAuthor":false,"prefix":"","firstName":"Philippe","middleName":"","lastName":"Gottfrois","suffix":""},{"id":571603014,"identity":"55b2c7e5-96d0-4868-9b49-b55a1dcb9140","order_by":3,"name":"Alvaro Gonzalez-Jimenez","email":"","orcid":"","institution":"University Hospital of Basel","correspondingAuthor":false,"prefix":"","firstName":"Alvaro","middleName":"","lastName":"Gonzalez-Jimenez","suffix":""},{"id":571603015,"identity":"ac368bc2-b527-46f1-bed0-5391c0ac9a06","order_by":4,"name":"Lea Habermacher","email":"","orcid":"","institution":"University Hospital of Basel","correspondingAuthor":false,"prefix":"","firstName":"Lea","middleName":"","lastName":"Habermacher","suffix":""},{"id":571603016,"identity":"979521cd-9cc6-42ea-a0e1-eec6bdb682b9","order_by":5,"name":"Ludovic Amruthalingam","email":"","orcid":"","institution":"Lucerne University of Applied Sciences and Arts","correspondingAuthor":false,"prefix":"","firstName":"Ludovic","middleName":"","lastName":"Amruthalingam","suffix":""},{"id":571603017,"identity":"b8286d73-b5b0-49ba-b304-5ce77952cb78","order_by":6,"name":"Matthew Groh","email":"","orcid":"","institution":"Northwestern University","correspondingAuthor":false,"prefix":"","firstName":"Matthew","middleName":"","lastName":"Groh","suffix":""},{"id":571603018,"identity":"0545b2a2-e209-42d2-a3cb-0acc1207eca8","order_by":7,"name":"Marc Pouly","email":"","orcid":"https://orcid.org/0000-0002-9520-4799","institution":"Lucerne University of Applied Sciences and Arts","correspondingAuthor":false,"prefix":"","firstName":"Marc","middleName":"","lastName":"Pouly","suffix":""},{"id":571603019,"identity":"7bc7db0d-382d-4097-b58f-9b8654b481b7","order_by":8,"name":"Alexander Navarini","email":"","orcid":"","institution":"University and University Hospital of Basel","correspondingAuthor":false,"prefix":"","firstName":"Alexander","middleName":"","lastName":"Navarini","suffix":""}],"badges":[],"createdAt":"2026-01-06 11:01:48","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8530334/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8530334/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":101296851,"identity":"f022bd00-f692-49a0-998f-fa3a927d3eda","added_by":"auto","created_at":"2026-01-28 09:21:52","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":5931704,"visible":true,"origin":"","legend":"Article File","description":"","filename":"NatureMedicineSkinMapPaper.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8530334/v1_covered_6d3083e2-b434-4c4b-887a-109fc58d16ed.pdf"}],"financialInterests":"\u003cb\u003eYes\u003c/b\u003e there is potential Competing Interest.\nA.A.N. is a shareholder of Derma2Go AG and Derma.One GmbH. \r\nAll other authors declare no competing interests.","formattedTitle":"A Global Atlas of Digital Dermatology to Map Innovation and Disparities","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":"nature-portfolio","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"","title":"Nature Portfolio","twitterHandle":"","acdcEnabled":false,"dfaEnabled":false,"editorialSystem":"ejp","reportingPortfolio":"","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Artificial intelligence, Dermatology, Health equity, Data diversity","lastPublishedDoi":"10.21203/rs.3.rs-8530334/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8530334/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The adoption of artificial intelligence in dermatology promises democratized access to healthcare, but model reliability depends on the quality and comprehensiveness of the data fueling these models. Despite rapid growth in publicly available dermatology images, the field lacks quantitative key performance indicators to measure whether new datasets expand clinical coverage or merely replicate what is already known. Here we present SkinMap, a multi-modal framework for the first comprehensive audit of the field's entire data basis. We unify the publicly available dermatology datasets into a single, queryable semantic atlas comprising more than 1.1 million images of skin conditions and quantify (i) informational novelty over time, (ii) dataset redundancy, and (iii) representation gaps across demographics and diagnoses. Despite exponential growth in dataset sizes, informational novelty across time has somewhat plateaued: Some clusters, such as common neoplasms on fair skin, are densely populated, while underrepresented skin types and many rare diseases remain unaddressed. We further identify structural gaps in coverage: Darker skin tones (Fitzpatrick V-VI) constitute only 5.8% of images and pediatric patients only 3.0%, while many rare diseases and phenotype combinations remain sparsely represented. SkinMap provides infrastructure to measure blind spots and steer strategic data acquisition toward undercovered regions of clinical space.","manuscriptTitle":"A Global Atlas of Digital Dermatology to Map Innovation and Disparities","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-01-23 08:06:42","doi":"10.21203/rs.3.rs-8530334/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-communications","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"NCOMMS","sideBox":"Learn more about [Nature Communications](http://www.nature.com/ncomms/)","snPcode":"","submissionUrl":"https://mts-ncomms.nature.com/","title":"Nature Communications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Communications","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"5179ea43-4a3d-4c2b-935b-59f96ee87229","owner":[],"postedDate":"January 23rd, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":60828635,"name":"Biological sciences/Biological techniques/Imaging"},{"id":60828636,"name":"Biological sciences/Computational biology and bioinformatics/Machine learning"},{"id":60828637,"name":"Biological sciences/Computational biology and bioinformatics/Data integration"},{"id":60828638,"name":"Health sciences/Signs and symptoms/Skin manifestations"}],"tags":[],"updatedAt":"2026-01-23T08:06:42+00:00","versionOfRecord":[],"versionCreatedAt":"2026-01-23 08:06:42","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8530334","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8530334","identity":"rs-8530334","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}