{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T15:49:51Z","timestamp":1785512991151,"version":"3.56.0"},"reference-count":41,"publisher":"Public Library of Science (PLoS)","issue":"5","license":[{"start":{"date-parts":[[2016,5,2]],"date-time":"2016-05-02T00:00:00Z","timestamp":1462147200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100012068","name":"Health and Care Research Wales","doi-asserted-by":"crossref","award":["CA02"],"award-info":[{"award-number":["CA02"]}],"id":[{"id":"10.13039\/100012068","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100000265","name":"Medical Research Council","doi-asserted-by":"publisher","award":["MR\/K006525\/1"],"award-info":[{"award-number":["MR\/K006525\/1"]}],"id":[{"id":"10.13039\/501100000265","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000265","name":"Medical Research Council","doi-asserted-by":"publisher","award":["G0902272"],"award-info":[{"award-number":["G0902272"]}],"id":[{"id":"10.13039\/501100000265","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"DOI":"10.1371\/journal.pone.0154515","type":"journal-article","created":{"date-parts":[[2016,5,2]],"date-time":"2016-05-02T17:27:32Z","timestamp":1462210052000},"page":"e0154515","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":71,"title":["Defining Disease Phenotypes in Primary Care Electronic Health Records by a Machine Learning Approach: A Case Study in Identifying Rheumatoid Arthritis"],"prefix":"10.1371","volume":"11","author":[{"given":"Shang-Ming","family":"Zhou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fabiola","family":"Fernandez-Gutierrez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan","family":"Kennedy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roxanne","family":"Cooksey","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mark","family":"Atkinson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Spiros","family":"Denaxas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefan","family":"Siebert","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"William G.","family":"Dixon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Terence W.","family":"O\u2019Neill","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ernest","family":"Choy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cathie","family":"Sudlow","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"name":"UK Biobank Follow-up and Outcomes Group","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sinead","family":"Brophy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2016,5,2]]},"reference":[{"key":"ref1","doi-asserted-by":"crossref","first-page":"793","DOI":"10.1093\/rheumatology\/41.7.793","article-title":"The prevalence of rheumatoid arthritis in the United Kingdom: new estimates for a new century","volume":"41","author":"D Symmons","year":"2002","journal-title":"Rheumatology (Oxford)"},{"issue":"Suppl 1","key":"ref2","doi-asserted-by":"crossref","first-page":"K41","DOI":"10.1016\/j.vaccine.2013.03.075","article-title":"A systematic review of validated methods for identifying patients with rheumatoid arthritis using administrative or claims data","volume":"31","author":"CP Chung","year":"2013","journal-title":"Vaccine"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"e226","DOI":"10.1136\/amiajnl-2013-001926","article-title":"Electronic health records based phenotyping in next-generation clinical trials: a perspective from the NIH Health Care Systems Collaboratory","volume":"20","author":"RL Richesson","year":"2013","journal-title":"J Am Med Inform Assoc"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"860","DOI":"10.1016\/j.ijmedinf.2014.08.005","article-title":"Comparison of electronic health record system functionalities to support the patient recruitment process in clinical trials","volume":"83","author":"B Schreiweis","year":"2014","journal-title":"Int J Med Inform"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1177\/1740774510363013","article-title":"Routine data from hospital information systems can support patient recruitment for clinical studies","volume":"7","author":"M Dugas","year":"2010","journal-title":"Clin Trials"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1016\/S0933-3657(03)00040-X","article-title":"Using OncoDoc as a computer-based eligibility screening system to improve accrual onto breast cancer clinical trials","volume":"29","author":"B S\u00e9roussi","year":"2003","journal-title":"Artif Intell Med"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1136\/amiajnl-2013-001935","article-title":"A review of approaches to identifying patient phenotype cohorts using electronic health records","volume":"21","author":"C Shivade","year":"2013","journal-title":"J Am Med Inform Assoc"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1038\/nrg3208","article-title":"Mining electronic health records: towards better research applications and clinical care","volume":"13","author":"PB Jensen","year":"2012","journal-title":"Nat Rev Genet"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0054878","article-title":"Optimising Use of Electronic Health Records to Describe the Presentation of Rheumatoid Arthritis in Primary Care: A Strategy for Developing Code Lists","volume":"8","author":"A Nicholson","year":"2013","journal-title":"PLoS One"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1136\/postgradmedj-2013-132068","article-title":"Prevalence and characteristics in coding, classification and diagnosis of diabetes in primary care","volume":"90","author":"S Seidu","year":"2014","journal-title":"Postgrad Med J"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1136\/archdischild-2012-302237","article-title":"Childhood epilepsy recorded in primary care in the UK","volume":"98","author":"WH Meeraus","year":"2013","journal-title":"Arch Dis Child"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"1314","DOI":"10.1002\/art.24015","article-title":"How accurate are diagnoses for rheumatoid arthritis and juvenile idiopathic arthritis in the general practice research database?","volume":"59","author":"SL Thomas","year":"2008","journal-title":"Arthritis Rheum"},{"key":"ref13","unstructured":"Team\/MSDi H-QOFBR. New GMS Contract QOF Implementation Dataset and Business Rules\u2014Rheumatoid Arthritis Indicator Set (RA) Wales. n.d."},{"key":"ref14","unstructured":"NHS. Read Coded Clinical Terms n.d. Available: <ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"http:\/\/systems.hscic.gov.uk\/data\/uktc\/readcodes\" xlink:type=\"simple\">http:\/\/systems.hscic.gov.uk\/data\/uktc\/readcodes<\/ext-link>. Accessed 1 June 2015."},{"key":"ref15","unstructured":"SNOMED Clinical Terms n.d. Available: <ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"http:\/\/www.nlm.nih.gov\/research\/umls\/Snomed\/snomed_announcement.html\" xlink:type=\"simple\">http:\/\/www.nlm.nih.gov\/research\/umls\/Snomed\/snomed_announcement.html<\/ext-link>. Accessed 28 March 2015."},{"key":"ref16","article-title":"Constructing Compact Takagi-Sugeno Rule Systems: Identification of Complex Interactions in Epidemiological Data","volume":"7","author":"SM Zhou","year":"2012","journal-title":"PLoS One"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"e113592","DOI":"10.1371\/journal.pone.0113592","article-title":"Local modelling techniques for assessing micro-level impacts of risk factors in complex data: understanding health and socioeconomic inequalities in childhood educational attainments","volume":"9","author":"S-M Zhou","year":"2014","journal-title":"PLoS One"},{"key":"ref18","article-title":"Pattern Recognition and Machine Learning","author":"CM Bishop","year":"2006"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1186\/1472-6947-9-3","article-title":"The SAIL databank: linking multiple health and social care datasets","volume":"9","author":"R a Lyons","year":"2009","journal-title":"BMC Med Inform Decis Mak"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"196","DOI":"10.1016\/j.jbi.2014.01.003","article-title":"A case study of the Secure Anonymous Information Linkage (SAIL) Gateway: A privacy-protecting remote access system for health-related research and evaluation","volume":"50","author":"KH Jones","year":"2014","journal-title":"J Biomed Inform"},{"key":"ref21","unstructured":"CELLMA. CELLMA. RioMed Ltd, Eastleigh, Hampshire, UK n.d. Available: <ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"http:\/\/www.riomed.com\" xlink:type=\"simple\">http:\/\/www.riomed.com<\/ext-link>."},{"key":"ref22","unstructured":"SNOMED CT. n.d. Available: <ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"http:\/\/systems.hscic.gov.uk\/data\/uktc\" xlink:type=\"simple\">http:\/\/systems.hscic.gov.uk\/data\/uktc<\/ext-link>."},{"key":"ref23","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"L Breiman","year":"2001","journal-title":"Mach Learn"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1198\/jasa.2009.tm08622","article-title":"High-Dimensional Variable Selection for Survival Data","volume":"105","author":"H Ishwaran","year":"2010","journal-title":"J Am Stat Assoc"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"831","DOI":"10.1093\/bioinformatics\/btq038","article-title":"Maximal conditional chi-square importance in random forests","volume":"26","author":"M Wang","year":"2010","journal-title":"Bioinformatics"},{"key":"ref26","article-title":"C4.5 Programs for Machine Learning","author":"JR Quinlan","year":"1993"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1002\/jae.1278","article-title":"RSTUDIO: A platform-independent IDE for R and sweave","volume":"27","author":"JS Racine","year":"2012","journal-title":"J Appl Econom"},{"key":"ref28","unstructured":"Breiman T, Cutler A, Classification D. Package \u201crandomForest\u201d 2014."},{"key":"ref29","unstructured":"Kuhn M, Weston S, Coulter N. Package \u201cC50\u201d\u2014C5.0 Decision Trees and Rule-Based Models 2014."},{"key":"ref30","first-page":"5","article-title":"Sources, uses, strengths and limitations of data collected in primary care in England","author":"A Majeed","year":"2004","journal-title":"Health Stat Q"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"192","DOI":"10.3399\/bjgp08X277302","article-title":"Identifying undiagnosed diabetes: Cross-sectional survey of 3.6 million patients\u2019 electronic records","volume":"58","author":"TA Holt","year":"2008","journal-title":"Br J Gen Pract"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"1130","DOI":"10.1136\/bmj.326.7399.1130","article-title":"Use of Read codes in diabetes management in a south London primary care group: implications for establishing disease registers","volume":"326","author":"J Gray","year":"2003","journal-title":"BMJ"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1093\/fampra\/cmn047","article-title":"Accuracy and completeness of electronic patient records in primary care","volume":"25","author":"A Majeed","year":"2008","journal-title":"Fam Pract"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"1490","DOI":"10.1002\/acr.21736","article-title":"Identification of rheumatoid arthritis patients using an administrative database: a Veterans Affairs study","volume":"64","author":"B Ng","year":"2012","journal-title":"Arthritis Care Res"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"952","DOI":"10.1002\/art.20827","article-title":"Accuracy of Veterans Administration databases for a diagnosis of rheumatoid arthritis","volume":"51","author":"JA Singh","year":"2004","journal-title":"Arthritis Rheum"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"R32","DOI":"10.1186\/ar3260","article-title":"Validation of rheumatoid arthritis diagnoses in health care utilization data","volume":"13","author":"SY Kim","year":"2011","journal-title":"Arthritis Res Ther"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"e1001779","DOI":"10.1371\/journal.pmed.1001779","article-title":"UK Biobank: An Open Access Resource for Identifying the Causes of a Wide Range of Complex Diseases of Middle and Old Age","volume":"12","author":"C Sudlow","year":"2015","journal-title":"PLOS Med"},{"key":"ref38","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0127914","article-title":"Suitability of UK Biobank retinal images for automatic analysis of morphometric properties of the vasculature","volume":"10","author":"TJ MacGillivray","year":"2015","journal-title":"PLoS One"},{"key":"ref39","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0138677","article-title":"A GWAS study on liver function test using eMERGE network participants","volume":"10","author":"B Namjou","year":"2015","journal-title":"PLoS One"},{"key":"ref40","doi-asserted-by":"crossref","first-page":"e111301","DOI":"10.1371\/journal.pone.0111301","article-title":"Genetic variants associated with serum thyroid stimulating hormone (TSH) levels in European Americans and African Americans from the eMERGE Network","volume":"9","author":"JR Malinowski","year":"2014","journal-title":"PLoS One"},{"key":"ref41","doi-asserted-by":"crossref","first-page":"761","DOI":"10.1038\/gim.2013.72","article-title":"The Electronic Medical Records and Genomics (eMERGE) Network: past, present, and future","volume":"15","author":"O Gottesman","year":"2013","journal-title":"Genet Med"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/dx.plos.org\/10.1371\/journal.pone.0154515","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,5,16]],"date-time":"2020-05-16T20:09:37Z","timestamp":1589659777000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0154515"}},"subtitle":[],"editor":[{"given":"Francesco","family":"Pappalardo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2016,5,2]]},"references-count":41,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2016,5,2]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0154515","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,5,2]]}}}