{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T16:46:22Z","timestamp":1762015582881},"reference-count":21,"publisher":"Oxford University Press (OUP)","issue":"e1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,4,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Objective To identify patients in a human immunodeficiency virus (HIV) study cohort who have fallen by applying supervised machine learning methods to radiology reports of the cohort.<\/jats:p><jats:p>Methods We used the Veterans Aging Cohort Study Virtual Cohort (VACS-VC), an electronic health record-based cohort of 146\u2009530 veterans for whom radiology reports were available ( N =2\u2009977\u2009739). We created a reference standard of radiology reports, represented each report by a feature set of words and Unified Medical Language System concepts, and then developed several support vector machine (SVM) classifiers for falls. We compared mutual information (MI) ranking and embedded feature selection approaches. The SVM classifier with MI feature selection was chosen to classify all radiology reports in VACS-VC.<\/jats:p><jats:p>Results Our SVM classifier with MI feature selection achieved an area under the curve score of 97.04 on the test set. When applied to all the radiology reports in VACS-VC, 80\u2009416 of these reports were classified as positive for a fall. Of these, 11\u2009484 were associated with a fall-related external cause of injury code (E-code) and 68\u2009932 were not, corresponding to 29\u2009280 patients with potential fall-related injuries who could not have been found using E-codes.<\/jats:p><jats:p>Discussion Feature selection was crucial to improving the classifier\u2019s performance. Feature selection with MI allowed us to select the number of discriminative features to use for classification, in contrast to the embedded feature selection method, in which the number of features is chosen automatically.<\/jats:p><jats:p>Conclusion Machine learning is an effective method of identifying patients who have suffered a fall. The development of this classifier supplements the clinical researcher\u2019s toolkit and reduces dependence on under-coded structured electronic health record data.<\/jats:p>","DOI":"10.1093\/jamia\/ocv155","type":"journal-article","created":{"date-parts":[[2015,11,14]],"date-time":"2015-11-14T02:39:24Z","timestamp":1447468764000},"page":"e113-e117","source":"Crossref","is-referenced-by-count":28,"title":["Classification of radiology reports for falls in an HIV study cohort"],"prefix":"10.1093","volume":"23","author":[{"given":"Jonathan","family":"Bates","sequence":"first","affiliation":[{"name":"Yale School of Medicine, New Haven, CT"},{"name":"VA Connecticut Healthcare System, West Haven, CT"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Samah J","family":"Fodeh","sequence":"additional","affiliation":[{"name":"Yale School of Medicine, New Haven, CT"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cynthia A","family":"Brandt","sequence":"additional","affiliation":[{"name":"Yale School of Medicine, New Haven, CT"},{"name":"VA Connecticut Healthcare System, West Haven, CT"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Julie A","family":"Womack","sequence":"additional","affiliation":[{"name":"Yale School of Nursing, West Haven, CT"},{"name":"VA Connecticut Healthcare System, West Haven, CT"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2015,11,13]]},"reference":[{"key":"2020110612353893300_ocv155-B1"},{"issue":"2","key":"2020110612353893300_ocv155-B2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1371\/journal.pone.0017217","article-title":"Increased risk of fragility fractures among HIV infected compared to uninfected male veterans","volume":"6","author":"Womack","year":"2011","journal-title":"PLoS ONE."},{"issue":"17","key":"2020110612353893300_ocv155-B3","doi-asserted-by":"crossref","first-page":"2679","DOI":"10.1097\/QAD.0b013e32833f6294","article-title":"Fracture incidence in HIV-infected women: results from the Women\u2019s Interagency HIV Study","volume":"24","author":"Yin","year":"2010","journal-title":"AIDS."},{"issue":"5","key":"2020110612353893300_ocv155-B4","first-page":"906","article-title":"Finding falls in ambulatory care clinical documents using statistical text mining","volume":"20","author":"McCart","year":"2013","journal-title":"JAMIA."},{"key":"2020110612353893300_ocv155-B5","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1007\/s10799-009-0061-6","article-title":"Identifying fall-related injuries: text mining the electronic medical record","volume":"10","author":"Tremblay","year":"2009","journal-title":"Inf Technol Manag."},{"key":"2020110612353893300_ocv155-B6"},{"key":"2020110612353893300_ocv155-B7","first-page":"300","article-title":"Automatic Classification of Free-Text Radiology Reports to Identify Limb Fractures using Machine Learning and the SNOMED CT Ontology","volume":"2013","author":"Zuccon","year":"2013","journal-title":"AMIA Jt Summits Transl Sci Proc."},{"issue":"5","key":"2020110612353893300_ocv155-B8","first-page":"893","article-title":"Supervised machine learning and active learning in classification of radiology reports","volume":"21","author":"Nguyen","year":"2014","journal-title":"JAMIA."},{"issue":"6","key":"2020110612353893300_ocv155-B9","first-page":"696","article-title":"Identifying wrist fracture patients with high accuracy by automatic categorization of X-ray reports","volume":"13","author":"de Bruijn","year":"2006","journal-title":"JAMIA."},{"issue":"2","key":"2020110612353893300_ocv155-B10","first-page":"221","article-title":"A review of approaches to identifying patient phenotype cohorts using electronic health records","volume":"21","author":"Shivade","year":"2014","journal-title":"JAMIA."},{"issue":"5","key":"2020110612353893300_ocv155-B11","first-page":"760","article-title":"What can natural language processing do for clinical decision support? J Biomed Inform","volume":"42","author":"Demner-Fushman","journal-title":"2009"},{"key":"2020110612353893300_ocv155-B12","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1007\/978-1-4939-0847-9_16","article-title":"Natural language processing in biomedicine: a unified system architecture overview","volume":"1168","author":"Doan","year":"2014","journal-title":"Methods Mol Biol."},{"issue":"5","key":"2020110612353893300_ocv155-B13","first-page":"614","article-title":"The Yale cTAKES extensions for document classification: architecture and application","volume":"18","author":"Garla","year":"2011","journal-title":"JAMIA."},{"issue":"5","key":"2020110612353893300_ocv155-B14","first-page":"507","article-title":"Mayo clinical text analysis and knowledge extraction system (cTAKES): architecture, component evaluation and applications","volume":"17","author":"Savova","year":"2010","journal-title":"JAMIA."},{"key":"2020110612353893300_ocv155-B15"},{"key":"2020110612353893300_ocv155-B16","doi-asserted-by":"crossref","article-title":"A user\u2019s guide to support vector machines","author":"Ben-Hur","DOI":"10.1007\/978-1-60327-241-4_13"},{"issue":"3","key":"2020110612353893300_ocv155-B17","doi-asserted-by":"crossref","first-page":"27:1","DOI":"10.1145\/1961189.1961199","article-title":"LIBSVM: a library for support vector machines","volume":"2","author":"Chang","year":"2011","journal-title":"ACM Trans Intell Syst Technol."},{"key":"2020110612353893300_ocv155-B18","first-page":"1157","article-title":"An introduction to variable and feature selection","volume":"3","author":"Guyon","year":"2003","journal-title":"J Mach Learn Res."},{"key":"2020110612353893300_ocv155-B19","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1007\/BF00994018","article-title":"Support-vector networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Machine Learn."},{"issue":"1","key":"2020110612353893300_ocv155-B20","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1186\/1471-2105-12-138","article-title":"Elastic SCAD as a novel penalization method for SVM classification tasks in high-dimensional data","volume":"12","author":"Becker","year":"2011","journal-title":"BMC Bioinformatics."},{"key":"2020110612353893300_ocv155-B21","article-title":"penalizedSVM: feature Selection SVM using penalty functions","author":"Becker"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/23\/e1\/e113\/34148782\/ocv155.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/23\/e1\/e113\/34148782\/ocv155.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,26]],"date-time":"2022-05-26T03:48:46Z","timestamp":1653536926000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/23\/e1\/e113\/2379897"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,11,13]]},"references-count":21,"journal-issue":{"issue":"e1","published-online":{"date-parts":[[2015,11,13]]},"published-print":{"date-parts":[[2016,4,1]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocv155","relation":{},"ISSN":["1527-974X","1067-5027"],"issn-type":[{"value":"1527-974X","type":"electronic"},{"value":"1067-5027","type":"print"}],"subject":[],"published-other":{"date-parts":[[2016,4]]},"published":{"date-parts":[[2015,11,13]]}}}