{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T11:53:04Z","timestamp":1775217184863,"version":"3.50.1"},"reference-count":30,"publisher":"Oxford University Press (OUP)","issue":"5","content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2014,9,1]]},"DOI":"10.1136\/amiajnl-2014-002694","type":"journal-article","created":{"date-parts":[[2014,5,1]],"date-time":"2014-05-01T09:30:16Z","timestamp":1398936616000},"page":"871-875","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":67,"title":["N-gram support vector machines for scalable procedure and diagnosis classification, with applications to clinical free text data from the intensive care unit"],"prefix":"10.1093","volume":"21","author":[{"given":"Ben J","family":"Marafino","sequence":"first","affiliation":[]},{"given":"Jason M","family":"Davies","sequence":"additional","affiliation":[]},{"given":"Naomi S","family":"Bardach","sequence":"additional","affiliation":[]},{"given":"Mitzi L","family":"Dean","sequence":"additional","affiliation":[]},{"given":"R Adams","family":"Dudley","sequence":"additional","affiliation":[]}],"member":"286","published-online":{"date-parts":[[2014,4,30]]},"reference":[{"key":"key\n\t\t\t\t20171009031625_R1","doi-asserted-by":"crossref","first-page":"1254","DOI":"10.1097\/01.CCM.0000128577.31689.4C","article-title":"Critical care medicine in the United States 1985\u20132000: an analysis of bed numbers, use, and costs","volume":"32","year":"2004","journal-title":"Crit Care Med"},{"key":"key\n\t\t\t\t20171009031625_R2","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1378\/chest.08-2591","article-title":"Mortality probability model III and simplified acute physiology score II: assessing their value in predicting length of stay and comparison to APACHE IV","volume":"136","year":"2009","journal-title":"Chest"},{"key":"key\n\t\t\t\t20171009031625_R3","doi-asserted-by":"crossref","first-page":"429","DOI":"10.1097\/CCM.0b013e318206b3af","article-title":"The effect of race and ethnicity on outcomes among patients in the intensive care unit: a comprehensive study involving socioeconomic status and resuscitation preferences","volume":"39","year":"2011","journal-title":"Crit Care Med"},{"key":"key\n\t\t\t\t20171009031625_R4","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1016\/j.jcrc.2010.06.010","article-title":"Predictors of early post-discharge mortality in critically ill patients: a retrospective cohort study from the California Intensive Care Outcomes project","volume":"26","year":"2011","journal-title":"J Crit Care"},{"key":"key\n\t\t\t\t20171009031625_R5","doi-asserted-by":"crossref","first-page":"1319","DOI":"10.1378\/chest.07-3061","article-title":"Variation in ICU risk-adjusted mortality: impact of methods of assessment and potential confounders","volume":"133","year":"2008","journal-title":"Chest"},{"key":"key\n\t\t\t\t20171009031625_R6","doi-asserted-by":"crossref","first-page":"e2","DOI":"10.1542\/peds.104.1.e2","article-title":"Rehospitalization in the first two weeks after discharge from the neonatal intensive care unit","volume":"104","year":"1999","journal-title":"Pediatrics"},{"key":"key\n\t\t\t\t20171009031625_R7","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1186\/cc7092","article-title":"Clinical review: critical care management of spontaneous intracerebral hemorrhage","volume":"12","year":"2008","journal-title":"Crit Care"},{"key":"key\n\t\t\t\t20171009031625_R8","doi-asserted-by":"crossref","first-page":"1555","DOI":"10.4187\/respcare.01387","article-title":"Approaches to conventional mechanical ventilation of the patient with acute respiratory distress syndrome","volume":"56","year":"2011","journal-title":"Respir Care"},{"key":"key\n\t\t\t\t20171009031625_R9","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1007\/BF00994018","article-title":"Support-vector networks","volume":"20","year":"1995","journal-title":"Mach Learn"},{"key":"key\n\t\t\t\t20171009031625_R10","volume-title":"Statistical learning theory","year":"1998"},{"key":"key\n\t\t\t\t20171009031625_R11","doi-asserted-by":"crossref","first-page":"869","DOI":"10.1016\/j.jbi.2013.06.014","article-title":"Semi-supervised clinical text classification with Laplacian SVMs: an application to cancer case management","volume":"46","year":"2013","journal-title":"J Biomed Inform"},{"key":"key\n\t\t\t\t20171009031625_R12","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1136\/amiajnl-2013-002090","volume":"21","year":"2014","journal-title":"J Am Med Inform Assoc"},{"key":"key\n\t\t\t\t20171009031625_R13","doi-asserted-by":"crossref","first-page":"887","DOI":"10.1136\/amiajnl-2012-001576","article-title":"Use of a support vector machine for categorizing free-text notes: assessment of accuracy across two institutions","volume":"20","year":"2013","journal-title":"J Am Med Info Assoc"},{"key":"key\n\t\t\t\t20171009031625_R14","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1197\/jamia.M2442","article-title":"Identifying smokers with a medical extraction system","volume":"15","year":"2008","journal-title":"J Am Med Inform Assoc"},{"key":"key\n\t\t\t\t20171009031625_R15","first-page":"540","article-title":"Overcoming barriers to NLP for clinical text: the role of shared tasks and the need for additional creative solutions","volume":"18","year":"2010","journal-title":"J Am Med Inform Assoc"},{"key":"key\n\t\t\t\t20171009031625_R16","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1006\/jbin.2001.1029","article-title":"A simple algorithm for identifying negated findings and diseases in discharge summaries","volume":"34","year":"2001","journal-title":"J Biomed Inform"},{"key":"key\n\t\t\t\t20171009031625_R17","first-page":"467","article-title":"Class-based n-gram models of natural language","volume":"18","year":"1992","journal-title":"Comput Linguist"},{"key":"key\n\t\t\t\t20171009031625_R18","volume-title":"Foundations of statistical natural language processing","year":"1999"},{"key":"key\n\t\t\t\t20171009031625_R19","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1109\/MIS.2009.36","article-title":"The unreasonable effectiveness of data","volume":"24","year":"2009","journal-title":"IEEE Intell Sys"},{"key":"key\n\t\t\t\t20171009031625_R20","doi-asserted-by":"crossref","first-page":"952","DOI":"10.1097\/CCM.0b013e31820a92c6","article-title":"Multiparameter intelligent monitoring in intensive care II (MIMIC-II): a public-access ICU database","volume":"39","year":"2011","journal-title":"Crit Care Med"},{"key":"key\n\t\t\t\t20171009031625_R21","doi-asserted-by":"crossref","first-page":"e215","DOI":"10.1161\/01.CIR.101.23.e215","article-title":"PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals","volume":"101","year":"2000","journal-title":"Circulation"},{"key":"key\n\t\t\t\t20171009031625_R22","first-page":"5213","article-title":"Heuristics to determine ventilation times of ICU patients from the MIMIC-II database","year":"2010","journal-title":"Conf Proc IEEE Eng Med Biol Soc"},{"key":"key\n\t\t\t\t20171009031625_R23","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1108\/eb046814","article-title":"An algorithm for suffix stripping","volume":"14","year":"1980","journal-title":"Program"},{"key":"key\n\t\t\t\t20171009031625_R24","volume-title":"Introduction to modern information retrieval","year":"1986"},{"key":"key\n\t\t\t\t20171009031625_R25","first-page":"728","article-title":"Document-level classification of CT pulmonary angiography reports based on an extension of the ConText algorithm","volume":"5","year":"2011","journal-title":"J Biomed Inform"},{"key":"key\n\t\t\t\t20171009031625_R26","first-page":"1","article-title":"LIBSVM: a library for support vector machines","volume":"2","year":"2011","journal-title":"ACM Trans Intell Syst Technol"},{"key":"key\n\t\t\t\t20171009031625_R27","first-page":"2825","article-title":"Scikit-learn: machine learning in Python","volume":"12","year":"2011","journal-title":"J Machine Learn Res"},{"key":"key\n\t\t\t\t20171009031625_R28","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1186\/1471-2105-7-91","article-title":"Bias in error estimation when using cross-validation for model selection","volume":"7","year":"2006","journal-title":"BMC Bioinformatics"},{"key":"key\n\t\t\t\t20171009031625_R29","first-page":"2079","article-title":"On over-fitting in model selection and subsequent selection bias in performance evaluation","volume":"11","journal-title":"J Mach Learn Res"},{"key":"key\n\t\t\t\t20171009031625_R30","doi-asserted-by":"crossref","first-page":"805","DOI":"10.1542\/peds.2006-0675","article-title":"Physiologic and pathologic jaundice: the conundrum of defining normal bilirubin levels in the newborn","volume":"118","year":"2006","journal-title":"Pediatrics"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/21\/5\/871\/20710789\/amiajnl-2014-002694.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,10,9]],"date-time":"2017-10-09T07:16:35Z","timestamp":1507533395000},"score":1,"resource":{"primary":{"URL":"http:\/\/academic.oup.com\/jamia\/article\/21\/5\/871\/761055\/Ngram-support-vector-machines-for-scalable"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,4,30]]},"references-count":30,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2014,4,30]]},"published-print":{"date-parts":[[2014,9,1]]}},"URL":"https:\/\/doi.org\/10.1136\/amiajnl-2014-002694","relation":{},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2014,9]]},"published":{"date-parts":[[2014,4,30]]}}}