High dimensional predictions of suicide risk in 4.2 million US Veterans using ensemble transfer learning

High dimensional predictions of suicide risk in 4.2 million US Veterans using ensemble transfer learning | 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 High dimensional predictions of suicide risk in 4.2 million US Veterans using ensemble transfer learning Sayera Dhaubhadel, Kumkum Ganguly, Ruy M. Ribeiro, Judith Cohn, and 24 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3276492/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 20 Jan, 2024 Read the published version in Scientific Reports → Version 1 posted 8 You are reading this latest preprint version Abstract We present an ensemble transfer learning model to predict suicide from Veterans Affairs (VA) electronic medical records (EMR). A diverseset of base models was trained to predict a binary outcome constructed from reported suicide, suicide attempt, and overdose diagnoseswith varying choices of study design and prediction methodology. Each model used twenty cross-sectional and 190 longitudinal variablesobserved in eight time intervals covering 7.5 years prior to the time of prediction. Ensembles of seven base models were created andfine-tuned with ten additional variables, expected to change with study design and outcome definition, in order to predict suicide andcombined outcome in a prospective cohort. The ensemble models achieved c-statistics of 0.73 on 2-year suicide risk and 0.83 onthe combined outcome when predicting on a prospective cohort of ∼ 4.2M veterans. The ensembles rely heavily on nonlinear basemodels trained using a retrospective nested case-control (Rcc) study cohort and show good calibration across a diversity of subgroups,including risk strata, age, sex, race, and level of healthcare utilization. In addition, a linear Rcc base model provided a rich set of biologicalpredictors, including indicators of suicide, substance use disorder, mental health diagnoses and treatments, hypoxia and vascular damage,and demographics. Biological sciences/Computational biology and bioinformatics/Machine learning Health sciences/Medical research/Outcomes research Full Text Additional Declarations No competing interests reported. Supplementary Files conditions10.pdf pulldata.22.r Model.Stats.xlsx rv10.r NatureReachVetpagesSI.pdf Cite Share Download PDF Status: Published Journal Publication published 20 Jan, 2024 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Major revision 06 Sep, 2023 Reviews received at journal 26 Aug, 2023 Reviewers agreed at journal 25 Aug, 2023 Reviewers invited by journal 24 Aug, 2023 Editor assigned by journal 24 Aug, 2023 Editor invited by journal 24 Aug, 2023 Submission checks completed at journal 24 Aug, 2023 First submitted to journal 18 Aug, 2023 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-3276492","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":228473764,"identity":"3ff60f04-e93c-41e8-9bdd-9508d5d10698","order_by":0,"name":"Sayera Dhaubhadel","email":"","orcid":"","institution":"Los Alamos National Laboratory","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Sayera","middleName":"","lastName":"Dhaubhadel","suffix":""},{"id":228473765,"identity":"f9097b69-bd14-4f0d-b7fb-adad8564ec7b","order_by":1,"name":"Kumkum Ganguly","email":"","orcid":"","institution":"Los Alamos National Laboratory","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Kumkum","middleName":"","lastName":"Ganguly","suffix":""},{"id":228473766,"identity":"cce12424-c7d0-4842-b0a5-871a647118bf","order_by":2,"name":"Ruy M. Ribeiro","email":"","orcid":"","institution":"Los Alamos National Laboratory","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Ruy","middleName":"M.","lastName":"Ribeiro","suffix":""},{"id":228473767,"identity":"b7985f10-d7e6-4167-b07e-a71bc0595c52","order_by":3,"name":"Judith Cohn","email":"","orcid":"","institution":"Los Alamos National Laboratory","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Judith","middleName":"","lastName":"Cohn","suffix":""},{"id":228473768,"identity":"afad9a37-7dab-4c48-9e74-57c6af0f8e34","order_by":4,"name":"James M. Hyman","email":"","orcid":"","institution":"Los Alamos National Laboratory","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"James","middleName":"M.","lastName":"Hyman","suffix":""},{"id":228473769,"identity":"36b79afb-98fc-493f-8abb-bd5947abf239","order_by":5,"name":"Nicolas W. Hengartner","email":"","orcid":"","institution":"Los Alamos National Laboratory","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Nicolas","middleName":"W.","lastName":"Hengartner","suffix":""},{"id":228473770,"identity":"adca06aa-9553-4bf6-bd8b-23a6d35b408d","order_by":6,"name":"Beauty Kolade","email":"","orcid":"","institution":"Los Alamos National Laboratory","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Beauty","middleName":"","lastName":"Kolade","suffix":""},{"id":228473771,"identity":"8b4cb9f4-8d89-4dbc-94ab-e92dc7ac4f2a","order_by":7,"name":"Anna Singley","email":"","orcid":"","institution":"Los Alamos National Laboratory","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Anna","middleName":"","lastName":"Singley","suffix":""},{"id":228473772,"identity":"4f9d22d1-777d-4d42-b37a-9960749c323f","order_by":8,"name":"Tanmoy Bhattacharya","email":"","orcid":"","institution":"Los Alamos National Laboratory","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Tanmoy","middleName":"","lastName":"Bhattacharya","suffix":""},{"id":228473773,"identity":"a40f31e3-1efd-4d33-80bf-6e1dd002694a","order_by":9,"name":"Patrick D. Finley","email":"","orcid":"","institution":"Sandia National Laboratories","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Patrick","middleName":"D.","lastName":"Finley","suffix":""},{"id":228473774,"identity":"cf24b21a-154b-4ea3-a374-67cf8a1fd8cb","order_by":10,"name":"Drew Levin","email":"","orcid":"","institution":"Sandia National Laboratories","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Drew","middleName":"","lastName":"Levin","suffix":""},{"id":228473775,"identity":"e14d9053-b568-4144-adc8-ea6f7b64a65a","order_by":11,"name":"Haedi Thelen","email":"","orcid":"","institution":"Sandia National Laboratories","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Haedi","middleName":"","lastName":"Thelen","suffix":""},{"id":228473776,"identity":"5f24f38f-3362-444f-869e-49f4b58c2818","order_by":12,"name":"Kelly Cho","email":"","orcid":"","institution":"VA Boston Healthcare System","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Kelly","middleName":"","lastName":"Cho","suffix":""},{"id":228473777,"identity":"3aa66507-05e0-4594-bf0a-26a4532e654a","order_by":13,"name":"Lauren Costa","email":"","orcid":"","institution":"VA Boston Healthcare System","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Lauren","middleName":"","lastName":"Costa","suffix":""},{"id":228473778,"identity":"aa233e2b-01fa-4402-899c-6bc6a726b1cb","order_by":14,"name":"Yuk-Lam Ho","email":"","orcid":"","institution":"VA Boston Healthcare System","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Yuk-Lam","middleName":"","lastName":"Ho","suffix":""},{"id":228473779,"identity":"57d4dc09-ee3d-4fb3-aa86-5cd802eaeeab","order_by":15,"name":"Amy C. Justice","email":"","orcid":"","institution":"VA Connecticut Healthcare System","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Amy","middleName":"C.","lastName":"Justice","suffix":""},{"id":228473780,"identity":"16b2093d-ebdb-449f-9271-1d79fff3d457","order_by":16,"name":"John Pestian","email":"","orcid":"","institution":"Cincinnati Children's Hospital Medical Center","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"John","middleName":"","lastName":"Pestian","suffix":""},{"id":228473781,"identity":"71288d84-245d-45e1-9878-5337c27f27ff","order_by":17,"name":"Daniel Santel","email":"","orcid":"","institution":"Cincinnati Children's Hospital Medical Center","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Daniel","middleName":"","lastName":"Santel","suffix":""},{"id":228473782,"identity":"42b9c824-4dc3-495e-a16f-94301f80ad2e","order_by":18,"name":"Rafael Zamora-Resendiz","email":"","orcid":"","institution":"Lawrence Berkeley National Laboratory","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Rafael","middleName":"","lastName":"Zamora-Resendiz","suffix":""},{"id":228473783,"identity":"85c1466b-7042-453b-8a67-34d6dd6f0697","order_by":19,"name":"Silvia Crivelli","email":"","orcid":"","institution":"Lawrence Berkeley National Laboratory","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Silvia","middleName":"","lastName":"Crivelli","suffix":""},{"id":228473784,"identity":"a3dc9327-9d0e-4b6f-af50-23cdfe9a9432","order_by":20,"name":"Suzanne Tamang","email":"","orcid":"","institution":"VA Palo Alto Health Care System","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Suzanne","middleName":"","lastName":"Tamang","suffix":""},{"id":228473785,"identity":"2f018222-8ef5-4310-918f-d2f2ac4c1f52","order_by":21,"name":"Susana Martins","email":"","orcid":"","institution":"VA Palo Alto Health Care System","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Susana","middleName":"","lastName":"Martins","suffix":""},{"id":228473786,"identity":"03e5fa8f-cca0-4d7b-8458-d281b06c0e90","order_by":22,"name":"Jodie Trafton","email":"","orcid":"","institution":"VA Palo Alto Health Care System","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Jodie","middleName":"","lastName":"Trafton","suffix":""},{"id":228473787,"identity":"10378383-71ab-4fac-96b2-18f01b3197c7","order_by":23,"name":"David W. Oslin","email":"","orcid":"","institution":"Philadelphia VA Medical Center","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"David","middleName":"W.","lastName":"Oslin","suffix":""},{"id":228473788,"identity":"f6dcc0a4-c203-432b-b0f8-0490d5077444","order_by":24,"name":"Jean C. Bekham","email":"","orcid":"","institution":"Durham VA Health Care System","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Jean","middleName":"C.","lastName":"Bekham","suffix":""},{"id":228473789,"identity":"4ac530cd-5e5d-4e42-975e-9e307586e301","order_by":25,"name":"Nathan A. Kimbrel","email":"","orcid":"","institution":"Durham VA Health Care System","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Nathan","middleName":"A.","lastName":"Kimbrel","suffix":""},{"id":228473790,"identity":"58be7d69-34f0-411e-b0cc-44f1cbdc63c5","order_by":26,"name":"Million Vetaran Program Suicide Exemplar Work Group","email":"","orcid":"","institution":"","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Million","middleName":"Vetaran Program Suicide Exemplar Work","lastName":"Group","suffix":""},{"id":228473791,"identity":"3dcebae9-b928-4c52-86ba-d091a3dd5bba","order_by":27,"name":"Benjamin H. McMahon","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAt0lEQVRIiWNgGAWjYJACZiCW42NgYDxAkhZjNiBBmpbENqK16LafTvxcUHEnvY397IEDDL9sEhsIaTE7k7tZesaZZ7ltPHkJBxj70ojQcoN3gzRv2+HcNoYcgwOMPYeNCToMqGXzb6CWdDb+N8Rr2QayJYFNAmgLw4/DcoS1nMndZs1z5rBhmwTQlsSGNCK0HD+7+TZPxWF5fv4cwwcf/tjwENSCCsCxQyL4Q7qWUTAKRsEoGP4AANxmPuhy7wZ9AAAAAElFTkSuQmCC","orcid":"","institution":"Los Alamos National Laboratory","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Benjamin","middleName":"H.","lastName":"McMahon","suffix":""}],"badges":[],"createdAt":"2023-08-18 22:29:11","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3276492/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3276492/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-024-51762-9","type":"published","date":"2024-01-20T15:01:43+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":49978816,"identity":"e7a59451-e345-4465-ab8c-324e34adce8c","added_by":"auto","created_at":"2024-01-22 15:09:21","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2356262,"visible":true,"origin":"","legend":"","description":"","filename":"NatureReachVet1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3276492/v1_covered_ba68e65c-b950-4b34-9d31-9877fe85a012.pdf"},{"id":42043851,"identity":"e0a220b2-be34-428e-95e7-3cc6b9cd8aa8","added_by":"auto","created_at":"2023-08-24 00:43:42","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":212238,"visible":true,"origin":"","legend":"","description":"","filename":"conditions10.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3276492/v1/9dc25bfb1a8cbfffebab32b2.pdf"},{"id":42043849,"identity":"b79c9ee7-6e6c-4b12-a995-fa0026311c2d","added_by":"auto","created_at":"2023-08-24 00:43:42","extension":"r","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":48461,"visible":true,"origin":"","legend":"","description":"","filename":"pulldata.22.r","url":"https://assets-eu.researchsquare.com/files/rs-3276492/v1/82eefcaab38042fd5e003cd6.r"},{"id":42043852,"identity":"ddc1dc7c-491c-4a1e-910b-f7edd953909b","added_by":"auto","created_at":"2023-08-24 00:43:42","extension":"xlsx","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":113805,"visible":true,"origin":"","legend":"","description":"","filename":"Model.Stats.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-3276492/v1/1739ef281bbe8c93978ba314.xlsx"},{"id":42043850,"identity":"e2281f6d-fa1f-4a8d-a103-021f8cb72f14","added_by":"auto","created_at":"2023-08-24 00:43:42","extension":"r","order_by":3,"title":"","display":"","copyAsset":false,"role":"supplement","size":149210,"visible":true,"origin":"","legend":"","description":"","filename":"rv10.r","url":"https://assets-eu.researchsquare.com/files/rs-3276492/v1/1cb2de38967ac6e1c3cdbcaf.r"},{"id":42043853,"identity":"94bb0ab9-e341-47cf-9612-6c87233dd4fb","added_by":"auto","created_at":"2023-08-24 00:43:42","extension":"pdf","order_by":5,"title":"","display":"","copyAsset":false,"role":"supplement","size":4161633,"visible":true,"origin":"","legend":"","description":"","filename":"NatureReachVetpagesSI.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3276492/v1/e991f1ffc80339f79ecdf419.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"High dimensional predictions of suicide risk in 4.2 million US Veterans using ensemble transfer learning","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"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":"","lastPublishedDoi":"10.21203/rs.3.rs-3276492/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3276492/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"We present an ensemble transfer learning model to predict suicide from Veterans Affairs (VA) electronic medical records (EMR). A diverseset of base models was trained to predict a binary outcome constructed from reported suicide, suicide attempt, and overdose diagnoseswith varying choices of study design and prediction methodology. Each model used twenty cross-sectional and 190 longitudinal variablesobserved in eight time intervals covering 7.5 years prior to the time of prediction. Ensembles of seven base models were created andfine-tuned with ten additional variables, expected to change with study design and outcome definition, in order to predict suicide andcombined outcome in a prospective cohort. The ensemble models achieved c-statistics of 0.73 on 2-year suicide risk and 0.83 onthe combined outcome when predicting on a prospective cohort of ∼ 4.2M veterans. The ensembles rely heavily on nonlinear basemodels trained using a retrospective nested case-control (Rcc) study cohort and show good calibration across a diversity of subgroups,including risk strata, age, sex, race, and level of healthcare utilization. In addition, a linear Rcc base model provided a rich set of biologicalpredictors, including indicators of suicide, substance use disorder, mental health diagnoses and treatments, hypoxia and vascular damage,and demographics.","manuscriptTitle":"High dimensional predictions of suicide risk in 4.2 million US Veterans using ensemble transfer learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2023-08-24 00:43:37","doi":"10.21203/rs.3.rs-3276492/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Major revision","date":"2023-09-06T04:36:32+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2023-08-26T20:46:36+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"1e3d0861-d50c-47c7-8434-b6e027e523f7","date":"2023-08-25T13:58:21+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2023-08-25T00:06:23+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2023-08-25T00:04:31+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2023-08-24T12:50:23+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2023-08-24T12:45:13+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2023-08-18T22:27:57+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":"25731246-01c3-47d9-9eb9-a3e51410fe9c","owner":[],"postedDate":"August 24th, 2023","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":24240003,"name":"Biological sciences/Computational biology and bioinformatics/Machine learning"},{"id":24240004,"name":"Health sciences/Medical research/Outcomes research"}],"tags":[],"updatedAt":"2024-01-22T15:05:35+00:00","versionOfRecord":{"articleIdentity":"rs-3276492","link":"https://doi.org/10.1038/s41598-024-51762-9","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2024-01-20 15:01:43","publishedOnDateReadable":"January 20th, 2024"},"versionCreatedAt":"2023-08-24 00:43:37","video":"","vorDoi":"10.1038/s41598-024-51762-9","vorDoiUrl":"https://doi.org/10.1038/s41598-024-51762-9","workflowStages":[]},"version":"v1","identity":"rs-3276492","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3276492","identity":"rs-3276492","version":["v1"]},"buildId":"FbvkV6FR0MCFSLy54lSbu","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}