Multi-biological Classification for the Diagnosis of Schizophrenia Using Multi-classifier, Multi-feature Selection and Multi-cross Validation: an Integrated Machine Learning Framework Study

Multi-biological Classification for the Diagnosis of Schizophrenia Using Multi-classifier, Multi-feature Selection and Multi-cross Validation: an Integrated Machine Learning Framework Study | 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 Multi-biological Classification for the Diagnosis of Schizophrenia Using Multi-classifier, Multi-feature Selection and Multi-cross Validation: an Integrated Machine Learning Framework Study Peng-fei Ke, Dong-sheng Xiong, Jia-hui Li, Shi-jia Li, Jie Song, and 8 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-181829/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 19 Jul, 2021 Read the published version in Scientific Reports → Version 1 posted 10 You are reading this latest preprint version Abstract Finding effective and objective biomarkers to inform the diagnosis of schizophrenia is of great importance yet remains challenging. However, there is relatively little work on multi-biological data for the diagnosis of schizophrenia. This was a cross-sectional study in which we extracted multiple features from three types of biological data including gut microbiota data, blood data, and electroencephalogram data. Then, an integrated framework of machine learning, consisting of five classifiers, three feature selection algorithms, and four cross-validation methods was used to discriminate patients with schizophrenia from healthy controls. Our results showed that the performance of the classifier using multi-biological data was better than that of the classifiers using single biological data, with 91.7% accuracy and 96.5% AUC. The most discriminative features (top 5%) for the classification include gut microbiota features ( Lactobacillus , Haemophilus , and Prevotella), blood features (superoxide dismutase, monocyte-lymphocyte ratio, and neutrophil), and electroencephalogram features (nodal local efficiency, nodal efficiency, and nodal shortest path length in the temporal and frontal-parietal areas).The proposed integrated framework may be help in understanding the pathophysiology of schizophrenia and developing biomarkers for schizophrenia using multi-biological data. Biomedical Engineering Multi-biological classification diagnosis of schizophrenia machine learning framework multi-classifier multi-feature selection multi-cross validation Figures Figure 1 Figure 2 Figure 3 Figure 4 Full Text Additional Declarations No competing interests reported. Supplementary Files Supplementsc.docx Cite Share Download PDF Status: Published Journal Publication published 19 Jul, 2021 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Major revision 16 Apr, 2021 Reviews received at journal 26 Feb, 2021 Reviews received at journal 24 Feb, 2021 Reviewers agreed at journal 05 Feb, 2021 Reviewers agreed at journal 02 Feb, 2021 Reviewers invited by journal 02 Feb, 2021 Editor assigned by journal 02 Feb, 2021 Editor invited by journal 31 Jan, 2021 Submission checks completed at journal 30 Jan, 2021 First submitted to journal 29 Jan, 2021 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-181829","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":9710046,"identity":"9368fc6a-e652-4327-b33f-a936758b2e4f","order_by":0,"name":"Peng-fei Ke","email":"","orcid":"","institution":"South China University of Technology","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Peng-fei","middleName":"","lastName":"Ke","suffix":""},{"id":9710047,"identity":"ee6ef0e0-46d3-485a-b594-254c262bdb01","order_by":1,"name":"Dong-sheng Xiong","email":"","orcid":"","institution":"South China University of Technology","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Dong-sheng","middleName":"","lastName":"Xiong","suffix":""},{"id":9710048,"identity":"3cbf8ebc-45a7-4d1b-bcbc-8e68bec37b95","order_by":2,"name":"Jia-hui Li","email":"","orcid":"","institution":"South China University of Technology","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Jia-hui","middleName":"","lastName":"Li","suffix":""},{"id":9710049,"identity":"c5b6af0f-e610-474d-a640-86a660d77322","order_by":3,"name":"Shi-jia Li","email":"","orcid":"","institution":"South China University of Technology","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Shi-jia","middleName":"","lastName":"Li","suffix":""},{"id":9710050,"identity":"362ee26a-557b-40c6-a534-b4ad61dcb6ae","order_by":4,"name":"Jie Song","email":"","orcid":"","institution":"South China University of Technology","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Jie","middleName":"","lastName":"Song","suffix":""},{"id":9710051,"identity":"2925de1f-79dd-4338-8399-3a6ab2a5b50a","order_by":5,"name":"Xiao-yi Chen","email":"","orcid":"","institution":"South China University of Technology","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Xiao-yi","middleName":"","lastName":"Chen","suffix":""},{"id":9710052,"identity":"ecc2e060-8cdc-48f6-aa7a-12d539057464","order_by":6,"name":"Jing Zhou","email":"","orcid":"","institution":"South China University of Technology","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Jing","middleName":"","lastName":"Zhou","suffix":""},{"id":9710053,"identity":"03473b0e-8e9d-49a8-8e58-0002dae1e36a","order_by":7,"name":"Gui-xiang Li","email":"","orcid":"","institution":"Guangdong Engineering Technology Research Center for Diagnosis and Rehabilitation of Dementia","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Gui-xiang","middleName":"","lastName":"Li","suffix":""},{"id":9710054,"identity":"ff2bf001-4cef-4d69-a848-2ec3e37216be","order_by":8,"name":"Jun Chen","email":"","orcid":"","institution":"Guangdong Engineering Technology Research Center for Diagnosis and Rehabilitation of Dementia","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Jun","middleName":"","lastName":"Chen","suffix":""},{"id":9710055,"identity":"447ed886-1dea-494b-bbf6-dc1578c885c4","order_by":9,"name":"Xiao-bo Li","email":"","orcid":"","institution":"New Jersey Institute of Technology","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Xiao-bo","middleName":"","lastName":"Li","suffix":""},{"id":9710056,"identity":"fc592944-0772-4cc7-b08b-451c6f429098","order_by":10,"name":"Yu-ping Ning","email":"","orcid":"","institution":"The Affiliated Brain Hospital of Guangzhou Medical University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Yu-ping","middleName":"","lastName":"Ning","suffix":""},{"id":9710057,"identity":"e3a5fc23-9ae2-41e0-ba89-3554e9564fc1","order_by":11,"name":"Feng-chun Wu","email":"","orcid":"","institution":"The Affiliated Brain Hospital of Guangzhou Medical University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Feng-chun","middleName":"","lastName":"Wu","suffix":""},{"id":9710058,"identity":"f2c61e70-73db-4e47-819e-873bc0426deb","order_by":12,"name":"Kai Wu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAv0lEQVRIiWNgGAWjYBACCQbGBgaGCiiPh3gtZ4AsNuK1AAFjGylaJNsPt0nzzquTN7jfwPjgbRuDvDkhLdI8iUAt2w4bbjjGwGw4t43BcGcDAS1yDIltt3m3HUgwOMbAJs3bxpBgcICQFv6HQC1z6kBa2H8TpUVaAmRLAzPYFmaitEjOeNj+c86xw4YzjyU2S845J2G4gZAWifPpjw3e1NTJ8x0+fPDDmzIbeYK2IAFQnELiaRSMglEwCkYBpQAAPh88DwmoQBsAAAAASUVORK5CYII=","orcid":"","institution":"South China University of Technology","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Kai","middleName":"","lastName":"Wu","suffix":""}],"badges":[],"createdAt":"2021-01-29 05:44:08","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-181829/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-181829/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-021-94007-9","type":"published","date":"2021-07-19T15:04:46+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":5867054,"identity":"1cfc348c-4a2c-44b9-b9d5-74ff07848397","added_by":"auto","created_at":"2021-02-11 15:51:52","extension":"jpg","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":143035,"visible":true,"origin":"","legend":"Flow Chart of Brain Network Construction of EEG Signal. Abbreviations: EEG, Electroencephalogram; PLV, Phase locking value.","description":"","filename":"Figure1.jpg","url":"https://assets-eu.researchsquare.com/files/rs-181829/v1/a71dc110ae9d879bac8efb0f.jpg"},{"id":5867057,"identity":"ea887659-5840-48db-9c59-95dff1e5f156","added_by":"auto","created_at":"2021-02-11 15:51:52","extension":"jpg","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":124359,"visible":true,"origin":"","legend":"Overview of the Proposed Integrated Machine Learning Framework for Schizophrenia Classification. \nThe proposed integrated machine learning framework for schizophrenia classification consists of 5M methods. (a) Multi-biological data of all subjects were collected including electroencephalogram (EEG) data, fecal data and blood data. (b) Multi-biological features were extracted from multi-biological data. (c) Multi-feature selection algorithms were used to eliminate redundant features, including recursive feature elimination (RFE), principal component analysis (PCA), and analysis of variance (ANOVA) (d) Multi-classifier were used to match heterogeneous biological features including support vector machine (SVM), random forest (RF), linear discriminant analysis (LDA), logistic regression (LR), and k-nearest neighbor (KNN) (e) Multi-cross validation methods including 10-fold, 5-fold, 3-fold, and leave-one-out were used to evaluate the performance of the trained model.","description":"","filename":"Figure2.jpg","url":"https://assets-eu.researchsquare.com/files/rs-181829/v1/575329384b97deea1dacf19c.jpg"},{"id":5867056,"identity":"a2445bb7-f836-4795-91d3-b0dcdc34c3d0","added_by":"auto","created_at":"2021-02-11 15:51:52","extension":"jpg","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":159220,"visible":true,"origin":"","legend":"The Flowchart of Classification Method by Machine Learning. ","description":"","filename":"Figure3.jpg","url":"https://assets-eu.researchsquare.com/files/rs-181829/v1/29f5a8064f6526fb3b5a0d86.jpg"},{"id":5867055,"identity":"9d88065c-c666-4e79-96d3-a1bd0cd10756","added_by":"auto","created_at":"2021-02-11 15:51:52","extension":"jpg","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":40584,"visible":true,"origin":"","legend":"Areas Under the Receiver Operating Characteristic Curves (AUC) of the best model Comparing the Gut Microbiota Features, Blood Features, Electroencephalogram Features and the Combination of GMV, BF and EF as the Input of Machine Learning. \nEach curve in the figure represents the roc curve of the best model using different input features.\nAbbreviations: GMF, gut microbiota features; BF, blood features; EF, electroencephalogram features; CF, combined features.","description":"","filename":"Figure4.jpg","url":"https://assets-eu.researchsquare.com/files/rs-181829/v1/9d0dae8e73b22e4e190588ef.jpg"},{"id":13583425,"identity":"debeaa57-944a-4db1-8bd7-4372b04e80ad","added_by":"auto","created_at":"2021-09-17 04:35:02","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1020688,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript20210122.pdf","url":"https://assets-eu.researchsquare.com/files/rs-181829/v1_covered.pdf"},{"id":5867209,"identity":"b4d2c16b-dd45-49a6-b179-7b1fc29977af","added_by":"auto","created_at":"2021-02-11 15:54:59","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1145921,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript20210122.pdf","url":"https://assets-eu.researchsquare.com/files/rs-181829/v1_stamped.pdf"},{"id":5867444,"identity":"281145b8-2b2f-4c06-8e00-da6faa259e5f","added_by":"auto","created_at":"2021-02-11 15:57:53","extension":"docx","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":79090,"visible":true,"origin":"","legend":"","description":"","filename":"Supplementsc.docx","url":"https://assets-eu.researchsquare.com/files/rs-181829/v1/4133ff9baa0613c52ea64dbf.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"\u003cp\u003eMulti-biological Classification for the Diagnosis of Schizophrenia Using Multi-classifier, Multi-feature Selection and Multi-cross Validation: an Integrated Machine Learning Framework Study\u003c/p\u003e","fulltext":[{"header":"Full Text","content":"\u003cp\u003eThis preprint is available for \u003ca href='/article/rs-181829/latest.pdf' target='_blank'\u003edownload as a PDF\u003c/a\u003e.\u003c/p\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Multi-biological classification, diagnosis of schizophrenia, machine learning framework, multi-classifier, multi-feature selection, multi-cross validation","lastPublishedDoi":"10.21203/rs.3.rs-181829/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-181829/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eFinding effective and objective biomarkers to inform the diagnosis of schizophrenia is of great importance yet remains challenging. However, there is relatively little work on multi-biological data for the diagnosis of schizophrenia. This was a cross-sectional study in which we extracted multiple features from three types of biological data including gut microbiota data, blood data, and electroencephalogram data. Then, an integrated framework of machine learning, consisting of five classifiers, three feature selection algorithms, and four cross-validation methods was used to discriminate patients with schizophrenia from healthy controls. Our results showed that the performance of the classifier using multi-biological data was better than that of the classifiers using single biological data, with 91.7% accuracy and 96.5% AUC. The most discriminative features (top 5%) for the classification include gut microbiota features (\u003cem\u003eLactobacillus\u003c/em\u003e, \u003cem\u003eHaemophilus\u003c/em\u003e, and \u003cem\u003ePrevotella), \u003c/em\u003eblood features (superoxide dismutase, monocyte-lymphocyte ratio, and neutrophil), and electroencephalogram features (nodal local efficiency, nodal efficiency, and nodal shortest path length in the temporal and frontal-parietal areas).The proposed integrated framework may be help in understanding the pathophysiology of schizophrenia and developing biomarkers for schizophrenia using multi-biological data.\u003c/p\u003e","manuscriptTitle":"Multi-biological Classification for the Diagnosis of Schizophrenia Using Multi-classifier, Multi-feature Selection and Multi-cross Validation: an Integrated Machine Learning Framework Study","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2021-02-11 15:51:50","doi":"10.21203/rs.3.rs-181829/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Major revision","date":"2021-04-16T12:46:47+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2021-02-26T06:13:21+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2021-02-24T08:31:56+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"d8626599-e817-4818-ad2b-700078516d4d","date":"2021-02-05T09:34:38+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"52e1a047-169a-48c4-be8a-0eba94ac393d","date":"2021-02-02T08:10:44+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2021-02-02T07:53:39+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2021-02-02T07:29:27+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2021-02-01T04:53:30+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2021-01-30T06:58:28+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2021-01-29T05:32:28+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"0c10d1f7-af68-46bf-b468-d2d30500c679","owner":[],"postedDate":"February 11th, 2021","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":2366208,"name":"Biomedical Engineering"}],"tags":[],"updatedAt":"2021-08-22T15:18:48+00:00","versionOfRecord":{"articleIdentity":"rs-181829","link":"https://doi.org/10.1038/s41598-021-94007-9","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2021-07-19 15:04:46","publishedOnDateReadable":"July 19th, 2021"},"versionCreatedAt":"2021-02-11 15:51:50","video":"","vorDoi":"10.1038/s41598-021-94007-9","vorDoiUrl":"https://doi.org/10.1038/s41598-021-94007-9","workflowStages":[]},"version":"v1","identity":"rs-181829","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-181829","identity":"rs-181829","version":["v1"]},"buildId":"WrCJVZZCHTDjtuVLN7oU0","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}