Contactless Human Oxygen Saturation Detection Using RGB Camera in an Induced Hypoxemia Study with Varied Skin Types

Contactless Human Oxygen Saturation Detection Using RGB Camera in an Induced Hypoxemia Study with Varied Skin Types | 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 Contactless Human Oxygen Saturation Detection Using RGB Camera in an Induced Hypoxemia Study with Varied Skin Types Li Zhu, Migyeong Gwak, Korosh Vatanparvar, Qijia Shao, Sharanya Desai, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9053537/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 Contactless monitoring of blood oxygen saturation (SpO2) using consumer-grade cameras could enable continuous monitoring in clinical settings where contact sensors are impractical, yet existing methods require optical filters, skin contact, or are restricted to narrow saturation ranges. We developed a physics-based framework that extracts ratio-of-ratios (RoR) features from facial video and predicts SpO2 via a RF regression model, evaluated through leave-one-subject-out cross-validation (LOSOCV) on 19 participants (Fitzpatrick types II–VI) during controlled induced hypoxemia (SpO2: 70–100%) with an unmodified commercial RGB camera at approximately 0.6-meter (2-foot) distance under ambient lighting. LOSOCV yielded ARMS of 6.62% (95% CI: 5.60–7.93%; PCC = 0.595), reducible to 3.87% through per-subject calibration. Slope-constrained one-point calibration using a single concurrent pulse oximeter reading achieved ARMS of 4.20%. Within clinically defined SpO2 bins, ARMS ranged from 2.58% to 2.73%, with error concentrating at range boundaries rather than within clinically actionable bands. For hypoxemia screening at the 90% threshold, the area under the receiver operating characteristic curve (AUC-ROC) was 0.797 (95% CI: 0.669–0.870) with sensitivity 0.636 and specificity 0.846. Performance for Fitzpatrick type VI was substantially degraded (ARMS = 9.71%), consistent with melanin-induced signal attenuation in the visible spectrum. These results demonstrate the feasibility of contactless SpO2 estimation from unmodified RGB cameras and identify skin pigmentation as the primary barrier to equitable performance. Health sciences/Biomarkers Health sciences/Diseases Physical sciences/Engineering Health sciences/Health care Health sciences/Medical research Physical sciences/Optics and photonics Full Text Additional Declarations Competing interest reported. The authors declare no competing non-financial interests. Authors affiliated with Samsung Research America received salary. Data collection and research were funded by Samsung Research America (Mountain View, CA 94043, USA). Supplementary Files supplementaryinformation.pdf 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-9053537","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":602336804,"identity":"b04f832b-3cfb-4504-92be-ddb91677d422","order_by":0,"name":"Li Zhu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA4ElEQVRIiWNgGAWjYDACCQbGAwlAEggYHwAJHj4itDCAtfAwMDAbgLSwEaUFRAO1sIHtIqhFfnaPwYGHbRby9uy9zyq/5tjJsDEwP3x0A48WxjlnDA4ktkkY9vAcN7stuy0Z6DA2Y+McPFqYJXIMDiSckUjgkUhjuy25jRmohYdNGp8WNmQtxZLb6glr4QFrqYBoYfy47TBhLRISaQUgLYY9Z44xSzNuO87DxkzAL/Izkjc+/GFQJ8/e3sb48ee2ant+9uaHj/FpQQHMPGCSWOUgwPiDFNWjYBSMglEwYgAAF6s+adjyiigAAAAASUVORK5CYII=","orcid":"","institution":"Samsung Research America","correspondingAuthor":true,"prefix":"","firstName":"Li","middleName":"","lastName":"Zhu","suffix":""},{"id":602336805,"identity":"182859ba-ed2f-4589-a528-ffd455516a48","order_by":1,"name":"Migyeong Gwak","email":"","orcid":"","institution":"Samsung Research America","correspondingAuthor":false,"prefix":"","firstName":"Migyeong","middleName":"","lastName":"Gwak","suffix":""},{"id":602336806,"identity":"c9966893-a3e1-4f85-97ed-1ff947dc2f21","order_by":2,"name":"Korosh Vatanparvar","email":"","orcid":"","institution":"Samsung Research America","correspondingAuthor":false,"prefix":"","firstName":"Korosh","middleName":"","lastName":"Vatanparvar","suffix":""},{"id":602336807,"identity":"9ac55b2a-eee9-436f-93bd-55458de38b08","order_by":3,"name":"Qijia Shao","email":"","orcid":"","institution":"Samsung Research America","correspondingAuthor":false,"prefix":"","firstName":"Qijia","middleName":"","lastName":"Shao","suffix":""},{"id":602336808,"identity":"b91bd0d1-2baa-47f8-bae3-9b922768daca","order_by":4,"name":"Sharanya Desai","email":"","orcid":"","institution":"Samsung Research America","correspondingAuthor":false,"prefix":"","firstName":"Sharanya","middleName":"","lastName":"Desai","suffix":""},{"id":602336809,"identity":"79d20357-b11c-45ec-baa5-4f79e5e11b04","order_by":5,"name":"Jungmok Bae","email":"","orcid":"","institution":"Samsung Research America","correspondingAuthor":false,"prefix":"","firstName":"Jungmok","middleName":"","lastName":"Bae","suffix":""},{"id":602336810,"identity":"124a2578-4970-4e3f-bd27-f33eb2ba29ce","order_by":6,"name":"Jilong Kuang","email":"","orcid":"","institution":"Samsung Research America","correspondingAuthor":false,"prefix":"","firstName":"Jilong","middleName":"","lastName":"Kuang","suffix":""},{"id":602336811,"identity":"0f6ada45-4bb0-4303-bbf9-eb414f84366d","order_by":7,"name":"Alex Gao","email":"","orcid":"","institution":"Samsung Research America","correspondingAuthor":false,"prefix":"","firstName":"Alex","middleName":"","lastName":"Gao","suffix":""}],"badges":[],"createdAt":"2026-03-06 19:38:53","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9053537/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9053537/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":105729043,"identity":"bd9dd4d9-b048-4aac-a008-8fd09d437efe","added_by":"auto","created_at":"2026-03-30 11:13:21","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2885345,"visible":true,"origin":"","legend":"","description":"","filename":"snarticlelz.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9053537/v1_covered_9e76b502-f8aa-42e8-9cae-8601ff7480f3.pdf"},{"id":104586273,"identity":"f7be2085-b6dd-4164-9223-a340c278205c","added_by":"auto","created_at":"2026-03-13 15:54:01","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":1381779,"visible":true,"origin":"","legend":"","description":"","filename":"supplementaryinformation.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9053537/v1/b5695072fa17543561406c6d.pdf"}],"financialInterests":"Competing interest reported. The authors declare no competing non-financial interests. Authors affiliated with Samsung Research America received salary. Data collection and research were funded by Samsung Research America (Mountain View, CA 94043, USA).","formattedTitle":"Contactless Human Oxygen Saturation Detection Using RGB Camera in an Induced Hypoxemia Study with Varied Skin Types","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"","lastPublishedDoi":"10.21203/rs.3.rs-9053537/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9053537/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Contactless monitoring of blood oxygen saturation (SpO2) using consumer-grade cameras could enable continuous monitoring in clinical settings where contact sensors are impractical, yet existing methods require optical filters, skin contact, or are restricted to narrow saturation ranges. We developed a physics-based framework that extracts ratio-of-ratios (RoR) features from facial video and predicts SpO2 via a RF regression model, evaluated through leave-one-subject-out cross-validation (LOSOCV) on 19 participants (Fitzpatrick types II–VI) during controlled induced hypoxemia (SpO2: 70–100%) with an unmodified commercial RGB camera at approximately 0.6-meter (2-foot) distance under ambient lighting. LOSOCV yielded ARMS of 6.62% (95% CI: 5.60–7.93%; PCC = 0.595), reducible to 3.87% through per-subject calibration. Slope-constrained one-point calibration using a single concurrent pulse oximeter reading achieved ARMS of 4.20%. Within clinically defined SpO2 bins, ARMS ranged from 2.58% to 2.73%, with error concentrating at range boundaries rather than within clinically actionable bands. For hypoxemia screening at the 90% threshold, the area under the receiver operating characteristic curve (AUC-ROC) was 0.797 (95% CI: 0.669–0.870) with sensitivity 0.636 and specificity 0.846. Performance for Fitzpatrick type VI was substantially degraded (ARMS = 9.71%), consistent with melanin-induced signal attenuation in the visible spectrum. These results demonstrate the feasibility of contactless SpO2 estimation from unmodified RGB cameras and identify skin pigmentation as the primary barrier to equitable performance.","manuscriptTitle":"Contactless Human Oxygen Saturation Detection Using RGB Camera in an Induced Hypoxemia Study with Varied Skin Types","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-13 15:53:05","doi":"10.21203/rs.3.rs-9053537/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":"f0ec284b-a7b1-40b3-ae02-6ace97612a49","owner":[],"postedDate":"March 13th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":64102349,"name":"Health sciences/Biomarkers"},{"id":64102350,"name":"Health sciences/Diseases"},{"id":64102351,"name":"Physical sciences/Engineering"},{"id":64102352,"name":"Health sciences/Health care"},{"id":64102353,"name":"Health sciences/Medical research"},{"id":64102354,"name":"Physical sciences/Optics and photonics"}],"tags":[],"updatedAt":"2026-03-30T05:25:11+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-13 15:53:05","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9053537","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9053537","identity":"rs-9053537","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}