Pattern Recognition Model for Identification of Healthy and Coronavirus Infected Samples Based on Optical Spectroscopy

Pattern Recognition Model for Identification of Healthy and Coronavirus Infected Samples Based on Optical Spectroscopy | 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 Pattern Recognition Model for Identification of Healthy and Coronavirus Infected Samples Based on Optical Spectroscopy Muhammad Izzuddin Rumaling, Fuei Pien Chee, Abdullah Bade, Floressy Juhim This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4690520/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 This study proposes optical spectroscopy that utilizes the interaction of light with matter to identify healthy and virus-infected samples. The spectral differences between healthy and infected samples demonstrate the effectiveness of optical spectroscopy in differentiating infected samples from the healthy ones. However, optical spectral data contain numerous peaks which require additional expertise and time for interpretation. Thus, pattern recognition model is employed in conjunction with optical spectroscopy to enable practitioners to interpret results quickly. This study developed and evaluated the performance of several pattern recognition models in detecting SARS-CoV-2 in viral transport media (VTM). 75 healthy and 75 SARS-CoV-2 infected swab samples in separate vials of VTM were acquired and measured for ultraviolet absorbance, infrared absorbance and Raman spectral data. Four supervised classification algorithms, namely k-nearest neighbour (KNN), linear discriminant analysis (LDA), support vector machine (SVM) and artificial neural network (ANN), were developed with and without implementation of principal component analysis (PCA). A total of 8 pattern recognition models were developed using a training set and evaluated for performance. The results showed that the performance model predicts the class of testing set with generally higher performance when using Raman spectral data. Out of all the models predicting using Raman spectra, both LDA and SVM have the highest performance (accuracy, sensitivity and specificity of 100%). The application of PCA before the classification algorithm did not improve the performance of the models. The model developed in this study has demonstrated high performance in detecting SARS-CoV-2 infected samples, comparable to conventional detection methods. Biological sciences/Biophysics Health sciences/Diseases Physical sciences/Optics and photonics Physical sciences/Physics Coronavirus Principal component analysis (PCA) Supervised classification algorithm Performance indicators Optical spectroscopy Pattern recognition model 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-4690520","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":330023564,"identity":"a46ae7b9-b498-46de-8ec9-e5e01e71c735","order_by":0,"name":"Muhammad Izzuddin Rumaling","email":"","orcid":"","institution":"Universiti of Malaysia Sabah","correspondingAuthor":false,"prefix":"","firstName":"Muhammad","middleName":"Izzuddin","lastName":"Rumaling","suffix":""},{"id":330023565,"identity":"08706f93-cd49-4f5d-aea2-c757cb12aa6e","order_by":1,"name":"Fuei Pien Chee","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA2ElEQVRIiWNgGAWjYBAC9gYGNiAlIccP4TMT1sJzAKzFxliygUQtaYkGB4jWIt387MGHisMJxjeykz8wVFgnNoidMcCvReaYueGMM4fzzG7kbpNgOJOe2CCdg1+LvUQOmzRv2+FikBYGxrbDhLXwgLT8/Xc4cfOM3M0fGP8Rq4WxIS1xg0TuBgnGBmK0yBwzk+w5ZmMscebtNomEY+nGbdJpBfi1AENM4kcNMCrbgQ77UGMt2y+dvAGvFgYJZE4CELMxcOB3GKoWCGB/gF/LKBgFo2AUjDQAAJpTRcF7EkQ9AAAAAElFTkSuQmCC","orcid":"","institution":"Universiti of Malaysia Sabah","correspondingAuthor":true,"prefix":"","firstName":"Fuei","middleName":"Pien","lastName":"Chee","suffix":""},{"id":330023566,"identity":"422d4aad-b35a-4b75-a64a-fac810720e24","order_by":2,"name":"Abdullah Bade","email":"","orcid":"","institution":"Universiti of Malaysia Sabah","correspondingAuthor":false,"prefix":"","firstName":"Abdullah","middleName":"","lastName":"Bade","suffix":""},{"id":330023567,"identity":"24341f46-5500-4ee3-8476-7471a4e9a206","order_by":3,"name":"Floressy Juhim","email":"","orcid":"","institution":"Universiti of Malaysia Sabah","correspondingAuthor":false,"prefix":"","firstName":"Floressy","middleName":"","lastName":"Juhim","suffix":""}],"badges":[],"createdAt":"2024-07-05 07:47:25","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4690520/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4690520/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":71954821,"identity":"d4145072-516e-41bb-9cdb-9c6c39d49595","added_by":"auto","created_at":"2024-12-20 05:25:29","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":773757,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscriptv1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4690520/v1_covered_560d6a95-5d20-49ca-9d99-853e791a20f9.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Pattern Recognition Model for Identification of Healthy and Coronavirus Infected Samples Based on Optical Spectroscopy","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":"Coronavirus, Principal component analysis (PCA), Supervised classification algorithm, Performance indicators, Optical spectroscopy, Pattern recognition model","lastPublishedDoi":"10.21203/rs.3.rs-4690520/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4690520/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis study proposes optical spectroscopy that utilizes the interaction of light with matter to identify healthy and virus-infected samples. The spectral differences between healthy and infected samples demonstrate the effectiveness of optical spectroscopy in differentiating infected samples from the healthy ones. However, optical spectral data contain numerous peaks which require additional expertise and time for interpretation. Thus, pattern recognition model is employed in conjunction with optical spectroscopy to enable practitioners to interpret results quickly. This study developed and evaluated the performance of several pattern recognition models in detecting SARS-CoV-2 in viral transport media (VTM). 75 healthy and 75 SARS-CoV-2 infected swab samples in separate vials of VTM were acquired and measured for ultraviolet absorbance, infrared absorbance and Raman spectral data. Four supervised classification algorithms, namely k-nearest neighbour (KNN), linear discriminant analysis (LDA), support vector machine (SVM) and artificial neural network (ANN), were developed with and without implementation of principal component analysis (PCA). A total of 8 pattern recognition models were developed using a training set and evaluated for performance. The results showed that the performance model predicts the class of testing set with generally higher performance when using Raman spectral data. Out of all the models predicting using Raman spectra, both LDA and SVM have the highest performance (accuracy, sensitivity and specificity of 100%). The application of PCA before the classification algorithm did not improve the performance of the models. The model developed in this study has demonstrated high performance in detecting SARS-CoV-2 infected samples, comparable to conventional detection methods.\u003c/p\u003e","manuscriptTitle":"Pattern Recognition Model for Identification of Healthy and Coronavirus Infected Samples Based on Optical Spectroscopy","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-07-30 19:00:50","doi":"10.21203/rs.3.rs-4690520/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":"78a1295e-a396-4ef4-b0b1-9027cecab8d4","owner":[],"postedDate":"July 30th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":34931429,"name":"Biological sciences/Biophysics"},{"id":34931430,"name":"Health sciences/Diseases"},{"id":34931431,"name":"Physical sciences/Optics and photonics"},{"id":34931432,"name":"Physical sciences/Physics"}],"tags":[],"updatedAt":"2024-12-20T05:08:59+00:00","versionOfRecord":[],"versionCreatedAt":"2024-07-30 19:00:50","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4690520","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4690520","identity":"rs-4690520","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}