{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T01:09:35Z","timestamp":1784077775093,"version":"3.55.0"},"reference-count":44,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2016,10,4]],"date-time":"2016-10-04T00:00:00Z","timestamp":1475539200000},"content-version":"vor","delay-in-days":607,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"National Institutes of Health\/National Library of Medicine","award":["R01LM010817"],"award-info":[{"award-number":["R01LM010817"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,5,1]]},"abstract":"<jats:title>ABSTRACT<\/jats:title><jats:p>Objective: For many literature review tasks, including systematic review (SR) and other aspects of evidence-based medicine, it is important to know whether an article describes a randomized controlled trial (RCT). Current manual annotation is not complete or flexible enough for the SR process. In this work, highly accurate machine learning predictive models were built that include confidence predictions of whether an article is an RCT.<\/jats:p><jats:p>Materials and Methods: The LibSVM classifier was used with forward selection of potential feature sets on a large human-related subset of MEDLINE to create a classification model requiring only the citation, abstract, and MeSH terms for each article.<\/jats:p><jats:p>Results: The model achieved an area under the receiver operating characteristic curve of 0.973 and mean squared error of 0.013 on the held out year 2011 data. Accurate confidence estimates were confirmed on a manually reviewed set of test articles. A second model not requiring MeSH terms was also created, and performs almost as well.<\/jats:p><jats:p>Discussion: Both models accurately rank and predict article RCT confidence. Using the model and the manually reviewed samples, it is estimated that about 8000 (3%) additional RCTs can be identified in MEDLINE, and that 5% of articles tagged as RCTs in Medline may not be identified.<\/jats:p><jats:p>Conclusion: Retagging human-related studies with a continuously valued RCT confidence is potentially more useful for article ranking and review than a simple yes\/no prediction. The automated RCT tagging tool should offer significant savings of time and effort during the process of writing SRs, and is a key component of a multistep text mining pipeline that we are building to streamline SR workflow. In addition, the model may be useful for identifying errors in MEDLINE publication types. The RCT confidence predictions described here have been made available to users as a web service with a user query form front end at: http:\/\/arrowsmith.psych.uic.edu\/cgi-bin\/arrowsmith_uic\/RCT_Tagger.cgi.<\/jats:p>","DOI":"10.1093\/jamia\/ocu025","type":"journal-article","created":{"date-parts":[[2015,2,6]],"date-time":"2015-02-06T03:58:49Z","timestamp":1423195129000},"page":"707-717","source":"Crossref","is-referenced-by-count":54,"title":["Automated confidence ranked classification of randomized controlled trial articles: an aid to evidence-based medicine"],"prefix":"10.1093","volume":"22","author":[{"given":"Aaron M","family":"Cohen","sequence":"first","affiliation":[{"name":"Department of Medical Informatics and Clinical Epidemiology, Oregon Health & Science University, Portland, OR 97239 USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Neil R","family":"Smalheiser","sequence":"additional","affiliation":[{"name":"Department of Psychiatry, University of Illinois at Chicago, Chicago, IL 60612 USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marian S","family":"McDonagh","sequence":"additional","affiliation":[{"name":"Department of Medical Informatics and Clinical Epidemiology, Oregon Health & Science University, Portland, OR 97239 USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Clement","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Illinois at Chicago, Chicago, IL 60612 USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Clive E","family":"Adams","sequence":"additional","affiliation":[{"name":"Division of Psychiatry, University of Nottingham, Nottingham, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John M","family":"Davis","sequence":"additional","affiliation":[{"name":"Department of Psychiatry, University of Illinois at Chicago, Chicago, IL 60612 USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Philip S","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Illinois at Chicago, Chicago, IL 60612 USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2015,2,5]]},"reference":[{"issue":"7023","key":"2020110612593287600_ocu025-B1","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1136\/bmj.312.7023.71","article-title":"Evidence based medicine: what it is and what it isn\u2019t","volume":"312","author":"Sackett","year":"1996","journal-title":"BMJ."},{"issue":"1","key":"2020110612593287600_ocu025-B2","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1186\/1472-6963-2-3","article-title":"What kind of evidence is it that evidence-based medicine advocates want health care providers and consumers to pay attention to?","volume":"2","author":"Haynes","year":"2002","journal-title":"BMC Health Serv Res."},{"key":"2020110612593287600_ocu025-B3","doi-asserted-by":"crossref","first-page":"d7501","DOI":"10.1136\/bmj.d7501","article-title":"Understanding why evidence from randomised clinical trials may not be retrieved from Medline: comparison of indexed and non-indexed records","volume":"344","author":"Wieland","year":"2012","journal-title":"BMJ."},{"key":"2020110612593287600_ocu025-B4","article-title":"A large-scale analysis of the reasons given for excluding articles that are retrieved by literature search during systematic review","author":"Edinger","year":"2013","journal-title":"AMIA Annu Symp Proc."},{"key":"2020110612593287600_ocu025-B5","first-page":"376","article-title":"Evidence-based medicine, the essential role of systematic reviews, and the need for automated text mining tools","author":"Cohen","year":"2010","journal-title":"Proceedings of the 1st ACM International Health Informatics Symposium November, 2010; Arlington, Virginia USA."},{"issue":"4","key":"2020110612593287600_ocu025-B6","doi-asserted-by":"crossref","first-page":"397","DOI":"10.1111\/j.1744-1609.2012.00290.x","article-title":"What is a rapid review? A methodological exploration of rapid reviews in Health Technology Assessments","volume":"10","author":"Harker","year":"2012","journal-title":"Int J Evid Based Healthc."},{"key":"2020110612593287600_ocu025-B7","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1186\/2046-4053-1-10","article-title":"Evidence summaries: the evolution of a rapid review approach","volume":"1","author":"Khangura","year":"2012","journal-title":"Syst Rev."},{"key":"2020110612593287600_ocu025-B8","first-page":"121","article-title":"Optimizing feature representation for automated systematic review work prioritization","volume":"2008","author":"Cohen","year":"2008","journal-title":"AMIA Annu Symp Proc."},{"key":"2020110612593287600_ocu025-B9","volume-title":"Updating Comparative Effectiveness Reviews: Current Efforts in AHRQ\u2019s Effective Health Care Program. Methods Guide for Effectiveness and Comparative Effectiveness Reviews [Internet]","author":"Tsertsvadze","year":"2008"},{"key":"2020110612593287600_ocu025-B10","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1186\/1471-2288-12-140","article-title":"Methods for the drug effectiveness review project","volume":"12","author":"McDonagh","year":"2012","journal-title":"BMC Med Res Methodol."},{"issue":"2","key":"2020110612593287600_ocu025-B11","first-page":"176","article-title":"Indexing consistency in MEDLINE","volume":"71","author":"Funk","year":"1983","journal-title":"Bull Med Libr Assoc."},{"key":"2020110612593287600_ocu025-B12","first-page":"137","article-title":"Text categorization with support vector machines: learning with many relevant features. In: Proceedings of the 10th European Conference on Machine Learning, April, 1998; Chemnitz, Germany","author":"Joachims","year":"1998"},{"key":"2020110612593287600_ocu025-B13","first-page":"1871","article-title":"LIBLINEAR: A library for large linear classification","volume":"9","author":"Fan","year":"2008","journal-title":"J Mach Learn Res."},{"key":"2020110612593287600_ocu025-B14","article-title":"A simple method for estimating conditional probabilities for svms","volume-title":"Technical Report\/Universit\u00e4t Dortmund, SFB 475 Komplexit\u00e4tsreduktion in Multivariaten Datenstrukturen","author":"R\u00fcping","year":"2004"},{"key":"2020110612593287600_ocu025-B15","first-page":"161","article-title":"An effective general purpose approach for automated biomedical document classification","volume":"2006","author":"Cohen","year":"2006","journal-title":"AMIA Annu Symp Proc."},{"key":"2020110612593287600_ocu025-B16","first-page":"1022","article-title":"Multi-interval discretization of continuous-valued attributes for classification learning","author":"Fayyad","year":"1993","journal-title":"Proceedings of the Thirteenth International Joint Conference on Artificial Intelligence"},{"key":"2020110612593287600_ocu025-B17","first-page":"CD005440","article-title":"Early versus delayed laparoscopic cholecystectomy for people with acute cholecystitis","volume":"6","author":"Gurusamy","year":"2013","journal-title":"Cochrane Database Syst Rev."},{"key":"2020110612593287600_ocu025-B18","first-page":"CD001867","article-title":"Opioid antagonists for alcohol dependence","volume":"12)","author":"R\u00f6sner","year":"2010","journal-title":"Cochrane Database Syst Rev."},{"key":"2020110612593287600_ocu025-B19","first-page":"CD008189","article-title":"Preconception lifestyle advice for people with subfertility","volume":"4)","author":"Anderson","year":"2010","journal-title":"Cochrane Database Syst Rev."},{"key":"2020110612593287600_ocu025-B20","first-page":"CD000978","article-title":"Interventions for preventing oral mucositis for patients with cancer receiving treatment","volume":"4)","author":"Worthington","year":"2011","journal-title":"Cochrane Database Syst Rev."},{"issue":"1","key":"2020110612593287600_ocu025-B21","doi-asserted-by":"crossref","first-page":"150","DOI":"10.1093\/ije\/31.1.150","article-title":"Development of a highly sensitive search strategy for the retrieval of reports of controlled trials using PubMed","volume":"31","author":"Robinson","year":"2002","journal-title":"Int J Epidemiol."},{"issue":"1","key":"2020110612593287600_ocu025-B22","doi-asserted-by":"crossref","first-page":"A8","DOI":"10.7326\/ACPJC-2005-142-1-A08","article-title":"Finding the gold in MEDLINE: clinical queries","volume":"142","author":"Haynes","year":"2005","journal-title":"ACP J Club."},{"key":"2020110612593287600_ocu025-B23","volume-title":"Haynes RB. MEDLINE clinical queries are robust when searching in recent publishing years","author":"Wilczynski"},{"issue":"1","key":"2020110612593287600_ocu025-B24","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1186\/1472-6947-12-33","article-title":"Studying the potential impact of automated document classification on scheduling a systematic review update","volume":"12","author":"Cohen","year":"2012","journal-title":"BMC Med Inform Decis Mak."},{"issue":"2","key":"2020110612593287600_ocu025-B25","doi-asserted-by":"crossref","first-page":"206","DOI":"10.1197\/jamia.M1929","article-title":"Reducing workload in systematic review preparation using automated citation classification","volume":"13","author":"Cohen","year":"2006","journal-title":"J Am Med Inf Assoc."},{"key":"2020110612593287600_ocu025-B26","first-page":"121","article-title":"A prospective evaluation of an automated classification system to support evidence-based medicine and systematic review","volume":"2010","author":"Cohen","year":"2010","journal-title":"AMIA Annu Symp Proc."},{"issue":"1","key":"2020110612593287600_ocu025-B27","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1016\/j.artmed.2010.10.005","article-title":"Exploiting the systematic review protocol for classification of medical abstracts","volume":"51","author":"Frunza","year":"2011","journal-title":"Artif Intell Med."},{"issue":"4","key":"2020110612593287600_ocu025-B28","doi-asserted-by":"crossref","first-page":"446","DOI":"10.1136\/jamia.2010.004325","article-title":"A new algorithm for reducing the workload of experts in performing systematic reviews","volume":"17","author":"Matwin","year":"2010","journal-title":"J Am Med Inf Assoc."},{"issue":"4","key":"2020110612593287600_ocu025-B29","doi-asserted-by":"crossref","first-page":"446","DOI":"10.1197\/jamia.M2031","article-title":"A comparison of citation metrics to machine learning filters for the identification of high quality MEDLINE documents","volume":"13","author":"Aphinyanaphongs","year":"2006","journal-title":"J Am Med Inf Assoc."},{"issue":"2","key":"2020110612593287600_ocu025-B30","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1197\/jamia.M1641","article-title":"Text categorization models for high-quality article retrieval in internal medicine","volume":"12","author":"Aphinyanaphongs","year":"2005","journal-title":"J Am Med Inf Assoc."},{"key":"2020110612593287600_ocu025-B31","first-page":"151","article-title":"A prototype system to support evidence-based practice","author":"Demner-Fushman","year":"2008","journal-title":"AMIA Annu Symp Proc."},{"issue":"1","key":"2020110612593287600_ocu025-B32","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1197\/jamia.M2996","article-title":"Towards automatic recognition of scientifically rigorous clinical research evidence","volume":"16","author":"Kilicoglu","year":"2009","journal-title":"J Am Med Inf Assoc."},{"issue":"3","key":"2020110612593287600_ocu025-B33","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1016\/j.artmed.2012.05.002","article-title":"Screening nonrandomized studies for medical systematic reviews: a comparative study of classifiers","volume":"55","author":"Bekhuis","year":"2012","journal-title":"Artif Intell Med."},{"issue":"1","key":"2020110612593287600_ocu025-B34","doi-asserted-by":"crossref","first-page":"e86277","DOI":"10.1371\/journal.pone.0086277","article-title":"Feature engineering and a proposed decision-support system for systematic reviewers of medical evidence","volume":"9","author":"Bekhuis","year":"2014","journal-title":"PLoS ONE."},{"issue":"23","key":"2020110612593287600_ocu025-B35","doi-asserted-by":"crossref","first-page":"3174","DOI":"10.1093\/bioinformatics\/btp548","article-title":"Automatically classifying sentences in full-text biomedical articles into Introduction, Methods, Results and Discussion","volume":"25","author":"Agarwal","year":"2009","journal-title":"Bioinformatics."},{"issue":"1","key":"2020110612593287600_ocu025-B36","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1186\/1472-6947-9-10","article-title":"Sentence retrieval for abstracts of randomized controlled trials","volume":"9","author":"Chung","year":"2009","journal-title":"BMC Med Inform Decis Mak."},{"key":"2020110612593287600_ocu025-B37","article-title":"Automatic summarization of MEDLINE citations for evidence-based medical treatment: a topic-oriented evaluation","author":"Fiszman","year":"2008","journal-title":"J Biomed Inf [Internet]."},{"issue":"14","key":"2020110612593287600_ocu025-B38","doi-asserted-by":"crossref","first-page":"1888","DOI":"10.1002\/asi.20486","article-title":"Collaborative information synthesis II: recommendations for information systems to support synthesis activities","volume":"57","author":"Blake","year":"2006","journal-title":"J Am Soc Inf Sci Technol."},{"key":"2020110612593287600_ocu025-B39","first-page":"MR000023","article-title":"When and how to update systematic reviews","volume":"1)","author":"Moher","year":"2008","journal-title":"Cochrane Database Syst Rev."},{"issue":"8","key":"2020110612593287600_ocu025-B40","doi-asserted-by":"crossref","first-page":"755","DOI":"10.1016\/j.jclinepi.2007.10.003","article-title":"Surveillance search techniques identified the need to update systematic reviews","volume":"61","author":"Sampson","year":"2008","journal-title":"J Clin Epidemiol."},{"issue":"10","key":"2020110612593287600_ocu025-B41","doi-asserted-by":"crossref","first-page":"1435","DOI":"10.1177\/1049732312452938","article-title":"Beyond PICO The SPIDER Tool for Qualitative Evidence Synthesis","volume":"22","author":"Cooke","year":"2012","journal-title":"Qual Health Res."},{"issue":"1","key":"2020110612593287600_ocu025-B42","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/2047-2501-2-1","article-title":"Design and implementation of meta, a meta search engine for biomedical literature retrieval intended for systematic reviewers","volume":"2","author":"Smalheiser","year":"2014","journal-title":"Health Inf Sci Syst."},{"key":"2020110612593287600_ocu025-B43","doi-asserted-by":"crossref","first-page":"bat086","DOI":"10.1093\/database\/bat086","article-title":"Rule-based deduplication of article records from bibliographic databases","volume":"2014","author":"Jiang","year":"2014","journal-title":"Database."},{"key":"2020110612593287600_ocu025-B44","article-title":"Aggregator: a machine learning approach to identifying MEDLINE articles that derive from the same underlying clinical trial","author":"Shao","year":"2014","journal-title":"Methods."}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/22\/3\/707\/34145652\/ocu025.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/22\/3\/707\/34145652\/ocu025.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,28]],"date-time":"2022-04-28T18:56:22Z","timestamp":1651172182000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/22\/3\/707\/775487"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,2,5]]},"references-count":44,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2015,2,5]]},"published-print":{"date-parts":[[2015,5,1]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocu025","relation":{},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2015,5]]},"published":{"date-parts":[[2015,2,5]]}}}