{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T05:05:00Z","timestamp":1775192700558,"version":"3.50.1"},"reference-count":50,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2016,10,4]],"date-time":"2016-10-04T00:00:00Z","timestamp":1475539200000},"content-version":"vor","delay-in-days":715,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0"}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2015,1,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Background Venous thromboembolisms (VTEs), which include deep vein thrombosis (DVT) and pulmonary embolism (PE), are associated with significant mortality, morbidity, and cost in hospitalized patients. To evaluate the success of preventive measures, accurate and efficient methods for monitoring VTE rates are needed. Therefore, we sought to determine the accuracy of statistical natural language processing (NLP) for identifying DVT and PE from electronic health record data.<\/jats:p>\n               <jats:p>Methods We randomly sampled 2000 narrative radiology reports from patients with a suspected DVT\/PE in Montreal (Canada) between 2008 and 2012. We manually identified DVT\/PE within each report, which served as our reference standard. Using a bag-of-words approach, we trained 10 alternative support vector machine (SVM) models predicting DVT, and 10 predicting PE. SVM training and testing was performed with nested 10-fold cross-validation, and the average accuracy of each model was measured and compared.<\/jats:p>\n               <jats:p>Results On manual review, 324 (16.2%) reports were DVT-positive and 154 (7.7%) were PE-positive. The best DVT model achieved an average sensitivity of 0.80 (95% CI 0.76 to 0.85), specificity of 0.98 (98% CI 0.97 to 0.99), positive predictive value (PPV) of 0.89 (95% CI 0.85 to 0.93), and an area under the curve (AUC) of 0.98 (95% CI 0.97 to 0.99). The best PE model achieved sensitivity of 0.79 (95% CI 0.73 to 0.85), specificity of 0.99 (95% CI 0.98 to 0.99), PPV of 0.84 (95% CI 0.75 to 0.92), and AUC of 0.99 (95% CI 0.98 to 1.00).<\/jats:p>\n               <jats:p>Conclusions Statistical NLP can accurately identify VTE from narrative radiology reports.<\/jats:p>","DOI":"10.1136\/amiajnl-2014-002768","type":"journal-article","created":{"date-parts":[[2014,10,21]],"date-time":"2014-10-21T06:43:56Z","timestamp":1413873836000},"page":"155-165","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":67,"title":["A novel method of adverse event detection can accurately identify venous thromboembolisms (VTEs) from narrative electronic health record data"],"prefix":"10.1093","volume":"22","author":[{"given":"Christian M","family":"Rochefort","sequence":"first","affiliation":[{"name":"Faculty of Medicine, Ingram School of Nursing, McGill University, Montreal, Canada"},{"name":"McGill Clinical and Health Informatics Research Group, McGill University, Montreal, Canada"},{"name":"Department of Epidemiology, Biostatics and Occupational Health, Faculty of Medicine, McGill University, Montreal, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aman D","family":"Verma","sequence":"additional","affiliation":[{"name":"McGill Clinical and Health Informatics Research Group, McGill University, Montreal, Canada"},{"name":"Department of Epidemiology, Biostatics and Occupational Health, Faculty of Medicine, McGill University, Montreal, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tewodros","family":"Eguale","sequence":"additional","affiliation":[{"name":"McGill Clinical and Health Informatics Research Group, McGill University, Montreal, Canada"},{"name":"Brigham and Women's Hospital, Boston, Massachusetts, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Todd C","family":"Lee","sequence":"additional","affiliation":[{"name":"McGill University Health Centre (MUHC), Montreal, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David L","family":"Buckeridge","sequence":"additional","affiliation":[{"name":"McGill Clinical and Health Informatics Research Group, McGill University, Montreal, Canada"},{"name":"Department of Epidemiology, Biostatics and Occupational Health, Faculty of Medicine, McGill University, Montreal, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2014,10,20]]},"reference":[{"issue":"(6 Suppl)","key":"2020110613025348200_R1","doi-asserted-by":"crossref","first-page":"381S","DOI":"10.1378\/chest.08-0656","article-title":"Prevention of venous thromboembolism: American College of Chest Physicians Evidence-Based Clinical Practice Guidelines (8th Edition)","volume":"133","author":"Geerts","year":"2008","journal-title":"Chest"},{"key":"2020110613025348200_R2","doi-asserted-by":"crossref","first-page":"951","DOI":"10.1160\/TH09-02-0073","article-title":"Rates of venous thromboembolism occurrence in medical patients among the insured population","volume":"102","author":"Spyropoulos","year":"2009","journal-title":"Thromb Haemost"},{"issue":"(23 Suppl 1)","key":"2020110613025348200_R3","first-page":"I4","article-title":"The epidemiology of venous thromboembolism","volume":"107","author":"White","year":"2003","journal-title":"Circulation"},{"key":"2020110613025348200_R4","doi-asserted-by":"crossref","first-page":"2105","DOI":"10.1001\/archinte.161.17.2105","article-title":"Prevention and treatment of postphlebitic syndrome: results of a 3-part study","volume":"161","author":"Ginsberg","year":"2001","journal-title":"Arch Intern Med"},{"key":"2020110613025348200_R5","doi-asserted-by":"crossref","first-page":"718","DOI":"10.1111\/j.1538-7836.2005.01216.x","article-title":"Predictors of the post-thrombotic syndrome during long-term treatment of proximal deep vein thrombosis","volume":"3","author":"Kahn","year":"2005","journal-title":"J Thromb Haemost"},{"key":"2020110613025348200_R6","doi-asserted-by":"crossref","first-page":"2257","DOI":"10.1056\/NEJMoa032274","article-title":"Incidence of chronic thromboembolic pulmonary hypertension after pulmonary embolism","volume":"350","author":"Pengo","year":"2004","journal-title":"N Engl J Med"},{"key":"2020110613025348200_R7","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1177\/1076029611431956","article-title":"Long-term outcomes in acute pulmonary thromboembolism: the incidence of chronic thromboembolic pulmonary hypertension and associated risk factors","volume":"18","author":"Korkmaz","year":"2012","journal-title":"Clin Appl Thromb Hemost"},{"key":"2020110613025348200_R8","doi-asserted-by":"crossref","first-page":"1868","DOI":"10.1001\/jama.290.14.1868","article-title":"Excess length of stay, charges, and mortality attributable to medical injuries during hospitalization","volume":"290","author":"Zhan","year":"2003","journal-title":"JAMA"},{"key":"2020110613025348200_R9","doi-asserted-by":"crossref","first-page":"943","DOI":"10.1592\/phco.29.8.943","article-title":"Economic burden of venous thromboembolism in hospitalized patients","volume":"29","author":"Dobesh","year":"2009","journal-title":"Pharmacotherapy"},{"issue":"(43)","key":"2020110613025348200_R10","first-page":"i","article-title":"Making health care safer: a critical analysis of patient safety practices","author":"Shojania","year":"2001","journal-title":"Evid Rep Technol Assess (Summer)"},{"key":"2020110613025348200_R11","article-title":"Specifications Manual for National Hospital Inpatient Quality Measures","author":"The Joint Commission","year":"2014"},{"key":"2020110613025348200_R12","first-page":"CD008201","article-title":"Interventions for implementation of thromboprophylaxis in hospitalized medical and surgical patients at risk for venous thromboembolism","volume":"7","author":"Kahn","year":"2013","journal-title":"Cochrane Database Syst Rev"},{"key":"2020110613025348200_R13","first-page":"e11","article-title":"Automated detection of harm in healthcare with information technology: a systematic review","volume":"19","author":"Govindan","year":"2010","journal-title":"Qual Saf Health Care"},{"key":"2020110613025348200_R14","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1016\/j.jbi.2003.08.003","article-title":"Detecting adverse events for patient safety research: a review of current methodologies","volume":"36","author":"Murff","year":"2003","journal-title":"J Biomed Inform"},{"key":"2020110613025348200_R15","doi-asserted-by":"crossref","first-page":"1268","DOI":"10.1086\/597591","article-title":"Automated surveillance of health care-associated infections","volume":"48","author":"Klompas","year":"2009","journal-title":"Clin Infect Dis"},{"key":"2020110613025348200_R16","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1197\/jamia.M1074","article-title":"Detecting adverse events using information technology","volume":"10","author":"Bates","year":"2003","journal-title":"J Am Med Inform Assoc"},{"key":"2020110613025348200_R17","first-page":"370","article-title":"Clinical validation of the AHRQ postoperative venous thromboembolism patient safety indicator","volume":"35","author":"Henderson","year":"2009","journal-title":"Jt Comm J Qual Patient Saf"},{"key":"2020110613025348200_R18","doi-asserted-by":"crossref","first-page":"1237","DOI":"10.1097\/MLR.0b013e3181b58940","article-title":"How valid is the ICD-9-CM based AHRQ patient safety indicator for postoperative venous thromboembolism?","volume":"47","author":"White","year":"2009","journal-title":"Med Care"},{"key":"2020110613025348200_R19","first-page":"154","article-title":"How often are potential patient safety events present on admission?","volume":"34","author":"Houchens","year":"2008","journal-title":"Jt Comm J Qual Patient Saf"},{"key":"2020110613025348200_R20","doi-asserted-by":"crossref","first-page":"516","DOI":"10.1097\/MLR.0b013e31815f537f","article-title":"Do the AHRQ patient safety indicators flag conditions that are present at the time of hospital admission?","volume":"46","author":"Bahl","year":"2008","journal-title":"Med Care"},{"key":"2020110613025348200_R21","author":"Allen","year":"1995"},{"key":"2020110613025348200_R22","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1016\/B978-012369378-5\/50019-3","article-title":"Natural language processing for biosurveillance","volume-title":"Handbook of biosurveillance","author":"Chapman","year":"2006"},{"key":"2020110613025348200_R23","doi-asserted-by":"crossref","first-page":"448","DOI":"10.1197\/jamia.M1794","article-title":"Automated detection of adverse events using natural language processing of discharge summaries","volume":"12","author":"Melton","year":"2005","journal-title":"J Am Med Inform Assoc"},{"key":"2020110613025348200_R24","first-page":"848","article-title":"Automated identification of postoperative complications within an electronic medical record using natural language processing","volume":"306","author":"Murff","year":"2011","journal-title":"JAMA"},{"key":"2020110613025348200_R25","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1097\/MLR.0b013e31828d1210","article-title":"Exploring the frontier of electronic health record surveillance: the case of postoperative complications","volume":"51","author":"FitzHenry","year":"2013","journal-title":"Med Care"},{"key":"2020110613025348200_R26","doi-asserted-by":"crossref","first-page":"118","DOI":"10.1016\/j.ijmedinf.2012.04.006","article-title":"Detecting temporal expressions in medical narratives","volume":"82","author":"Reeves","year":"2013","journal-title":"Int J Med Inform"},{"key":"2020110613025348200_R27","article-title":"Extracting information from textual documents in the electronic health record: a review of recent research","author":"Meystre","journal-title":"Yearb Med Inform"},{"key":"2020110613025348200_R28","author":"Mitchell","year":"1997"},{"key":"2020110613025348200_R29","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1007\/BF00994018","article-title":"Support vector network","volume":"20","author":"Cortes","year":"1995","journal-title":"Mach Learn"},{"key":"2020110613025348200_R30","author":"Vapnik","year":"1998"},{"key":"2020110613025348200_R31","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1186\/1472-6947-10-16","article-title":"Application of support vector machine modeling for prediction of common diseases: the case of diabetes and pre-diabetes","volume":"10","author":"Yu","year":"2010","journal-title":"BMC Med Inform Decis Mak"},{"key":"2020110613025348200_R32","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1016\/j.cmpb.2009.01.003","article-title":"Support Vectors Machine-based identification of heart valve diseases using heart sounds","volume":"95","author":"Maglogiannis","year":"2009","journal-title":"Comput Methods Programs Biomed"},{"key":"2020110613025348200_R33","article-title":"hines. Methods, theory and algorithms","author":"Thorsten","year":"2002"},{"key":"2020110613025348200_R34","author":"Japkowicz","year":"2011","edition":"1st edn"},{"key":"2020110613025348200_R35","author":"Manning","year":"2003","edition":"1st edn"},{"key":"2020110613025348200_R36","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v025.i05","article-title":"Text mining infrastructure in R","volume":"25","author":"Feinerer","year":"2008","journal-title":"J Stat Software"},{"key":"2020110613025348200_R37","doi-asserted-by":"crossref","first-page":"e47","DOI":"10.1016\/j.ijmedinf.2009.03.010","article-title":"Classifying disease outbreak reports using n-grams and semantic features","volume":"78","author":"Conway","year":"2009","journal-title":"Int J Med Inform"},{"key":"2020110613025348200_R38","author":"Feinerer"},{"key":"2020110613025348200_R39","doi-asserted-by":"crossref","first-page":"2507","DOI":"10.1093\/bioinformatics\/btm344","article-title":"A review of feature selection techniques in bioinformatics","volume":"23","author":"Saeys","year":"2007","journal-title":"Bioinformatics"},{"key":"2020110613025348200_R40","author":"Hastie","year":"2009","edition":"2nd edn"},{"key":"2020110613025348200_R41","first-page":"1","article-title":"Support vector machines in R","volume":"15","author":"Karatzoglou","year":"2012","journal-title":"J Stat Software"},{"key":"2020110613025348200_R42","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1023\/A:1024068626366","article-title":"Inference for the generalization error","volume":"52","author":"Nadeau","year":"2003","journal-title":"Mach Learn"},{"key":"2020110613025348200_R43","doi-asserted-by":"crossref","first-page":"861","DOI":"10.1016\/j.patrec.2005.10.010","article-title":"An introduction to ROC analysis","volume":"27","author":"Fawcett","year":"2006","journal-title":"Pattern Recogn Lett"},{"key":"2020110613025348200_R44","author":"Dimitriadou"},{"key":"2020110613025348200_R45","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","author":"Garla","year":"2013","journal-title":"J Biomed Inform"},{"key":"2020110613025348200_R46","doi-asserted-by":"crossref","first-page":"817","DOI":"10.1136\/amiajnl-2011-000752","article-title":"Pneumonia identification using statistical feature selection","volume":"19","author":"Bejan","year":"2012","journal-title":"J Am Med Inform Assoc"},{"key":"2020110613025348200_R47","doi-asserted-by":"crossref","first-page":"906","DOI":"10.1136\/amiajnl-2012-001334","article-title":"Finding falls in ambulatory care clinical documents using statistical text mining","volume":"20","author":"McCart","year":"2013","journal-title":"J Am Med Inform Assoc"},{"key":"2020110613025348200_R48","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","author":"Wright","year":"2013","journal-title":"J Am Med Inform Assoc"},{"key":"2020110613025348200_R49","author":"Hsu","year":"2010"},{"key":"2020110613025348200_R50","doi-asserted-by":"crossref","first-page":"992","DOI":"10.1016\/j.jbi.2012.04.010","article-title":"Ontology-guided feature engineering for clinical text classification","volume":"45","author":"Garla","year":"2012","journal-title":"J Biomed Inform"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/22\/1\/155\/34145216\/amiajnl-2014-002768.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/22\/1\/155\/34145216\/amiajnl-2014-002768.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,6]],"date-time":"2020-11-06T18:56:20Z","timestamp":1604688980000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/22\/1\/155\/833681"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,10,20]]},"references-count":50,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2014,10,20]]},"published-print":{"date-parts":[[2015,1,1]]}},"URL":"https:\/\/doi.org\/10.1136\/amiajnl-2014-002768","relation":{},"ISSN":["1527-974X","1067-5027"],"issn-type":[{"value":"1527-974X","type":"electronic"},{"value":"1067-5027","type":"print"}],"subject":[],"published-other":{"date-parts":[[2015,1]]},"published":{"date-parts":[[2014,10,20]]}}}