{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T10:58:08Z","timestamp":1779361088780,"version":"3.51.4"},"reference-count":10,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2018,11,22]],"date-time":"2018-11-22T00:00:00Z","timestamp":1542844800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/100006260","name":"Rheumatology Research Foundation","doi-asserted-by":"publisher","award":["R01 HS024412"],"award-info":[{"award-number":["R01 HS024412"]}],"id":[{"id":"10.13039\/100006260","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000069","name":"NIAMS","doi-asserted-by":"publisher","award":["K23 AR063770"],"award-info":[{"award-number":["K23 AR063770"]}],"id":[{"id":"10.13039\/100000069","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Russell\/Engleman Medical Research Center for Arthritis"},{"DOI":"10.13039\/100000133","name":"Agency for Healthcare Research and Quality","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000133","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,1,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title\/>\n                  <jats:p>Accurate and efficient identification of complex chronic conditions in the electronic health record (EHR) is an important but challenging task that has historically relied on tedious clinician review and oversimplification of the disease. Here we adapt methods that allow for automated \u201cnoisy labeling\u201d of positive and negative controls to create a \u201csilver standard\u201d for machine learning to automate identification of systemic lupus erythematosus (SLE). Our final model, which includes both structured data as well as text processing of clinical notes, outperformed all existing algorithms for SLE (AUC 0.97). In addition, we demonstrate how the probabilistic outputs of this model can be adapted to various clinical needs, selecting high thresholds when specificity is the priority and lower thresholds when a more inclusive patient population is desired. Deploying a similar methodology to other complex diseases has the potential to dramatically simplify the landscape of population identification in the EHR.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>MeSH terms<\/jats:title>\n                  <jats:p>Electronic Health Records, Machine Learning, Lupus Erythematosus, Phenotype, Algorithms<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/jamia\/ocy154","type":"journal-article","created":{"date-parts":[[2018,11,13]],"date-time":"2018-11-13T12:42:07Z","timestamp":1542112927000},"page":"61-65","source":"Crossref","is-referenced-by-count":44,"title":["Automated and flexible identification of complex disease: building a model for systemic lupus erythematosus using noisy labeling"],"prefix":"10.1093","volume":"26","author":[{"given":"Sara G","family":"Murray","sequence":"first","affiliation":[{"name":"Department of Medicine, University of California, San Francisco, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anand","family":"Avati","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Stanford University, Stanford, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gabriela","family":"Schmajuk","sequence":"additional","affiliation":[{"name":"Department of Medicine, University of California, San Francisco, California, USA"},{"name":"Department of Medicine, San Francisco VA Medical Center, San Francisco, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinoos","family":"Yazdany","sequence":"additional","affiliation":[{"name":"Department of Medicine, University of California, San Francisco, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2018,11,22]]},"reference":[{"key":"2020110613020132500_ocy154-B1","doi-asserted-by":"crossref","first-page":"K62","DOI":"10.1016\/j.vaccine.2013.06.104","article-title":"A systematic review of validated methods for identifying systemic lupus erythematosus (SLE) using administrative or claims data","volume":"31","author":"Moores","year":"2013","journal-title":"Vaccine"},{"issue":"e1","key":"2020110613020132500_ocy154-B2","doi-asserted-by":"crossref","first-page":"e162","DOI":"10.1136\/amiajnl-2011-000583","article-title":"Portability of an algorithm to identify rheumatoid arthritis in electronic health records","volume":"19","author":"Carroll","year":"2012","journal-title":"J Am Med Inform Assoc"},{"issue":"8","key":"2020110613020132500_ocy154-B3","doi-asserted-by":"crossref","first-page":"1120","DOI":"10.1002\/acr.20184","article-title":"Electronic medical records for discovery research in rheumatoid arthritis","volume":"62","author":"Liao","year":"2010","journal-title":"Arthritis Care Res"},{"issue":"5","key":"2020110613020132500_ocy154-B4","doi-asserted-by":"crossref","first-page":"687","DOI":"10.1002\/acr.22989","article-title":"Developing electronic health record algorithms that accurately identify patients with systemic lupus erythematosus","volume":"69","author":"Barnado","year":"2017","journal-title":"Arthritis Care Res"},{"issue":"6","key":"2020110613020132500_ocy154-B5","doi-asserted-by":"crossref","first-page":"1166","DOI":"10.1093\/jamia\/ocw028","article-title":"Learning statistical models of phenotypes using noisy labeled training data","volume":"23","author":"Agarwal","year":"2016","journal-title":"J Am Med Inform Assoc"},{"issue":"9","key":"2020110613020132500_ocy154-B6","doi-asserted-by":"crossref","first-page":"1725.","DOI":"10.1002\/art.1780400928","article-title":"Updating the American College of Rheumatology revised criteria for the classification of systemic lupus erythematosus","volume":"40","author":"Hochberg","year":"1997","journal-title":"Arthritis Rheum"},{"key":"2020110613020132500_ocy154-B7","article-title":"Automated case identification of lupus from an electronic health record using novel informatics approaches","volume":"67 (Suppl 10)","author":"Murray","year":"2015","journal-title":"Arthritis Rheumatol"},{"issue":"8","key":"2020110613020132500_ocy154-B8","doi-asserted-by":"crossref","first-page":"1612","DOI":"10.3899\/jrheum.101149","article-title":"The accuracy of administrative data diagnoses of systemic autoimmune rheumatic diseases","volume":"38","author":"Bernatsky","year":"2011","journal-title":"J Rheumatol"},{"key":"2020110613020132500_ocy154-B9","doi-asserted-by":"crossref","first-page":"h1885","DOI":"10.1136\/bmj.h1885","article-title":"Development of phenotype algorithms using electronic medical records and incorporating natural language processing","volume":"350","author":"Liao","year":"2015","journal-title":"BMJ"},{"issue":"2","key":"2020110613020132500_ocy154-B10","doi-asserted-by":"crossref","first-page":"539","DOI":"10.1109\/TSMCB.2008.2007853","article-title":"Exploratory undersampling for class-imbalance learning","volume":"39","author":"Liu","year":"2009","journal-title":"IEEE Trans Syst Man Cybern B Cybern"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/26\/1\/61\/34151245\/ocy154.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/26\/1\/61\/34151245\/ocy154.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,6]],"date-time":"2020-11-06T18:52:39Z","timestamp":1604688759000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/26\/1\/61\/5199370"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11,22]]},"references-count":10,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2018,11,22]]},"published-print":{"date-parts":[[2019,1,1]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocy154","relation":{},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2019,1]]},"published":{"date-parts":[[2018,11,22]]}}}