{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,23]],"date-time":"2024-08-23T18:30:31Z","timestamp":1724437831476},"reference-count":43,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2017,8,31]],"date-time":"2017-08-31T00:00:00Z","timestamp":1504137600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["UL1TR001422, P50-HG007738, and 1R01MH106577-01A1"],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,1,1]]},"abstract":"Abstract<\/jats:title>We propose Segment Convolutional Neural Networks (Seg-CNNs) for classifying relations from clinical notes. Seg-CNNs use only word-embedding features without manual feature engineering. Unlike typical CNN models, relations between 2 concepts are identified by simultaneously learning separate representations for text segments in a sentence: preceding, concept1, middle, concept2, and succeeding. We evaluate Seg-CNN on the i2b2\/VA relation classification challenge dataset. We show that Seg-CNN achieves a state-of-the-art micro-average F-measure of 0.742 for overall evaluation, 0.686 for classifying medical problem\u2013treatment relations, 0.820 for medical problem\u2013test relations, and 0.702 for medical problem\u2013medical problem relations. We demonstrate the benefits of learning segment-level representations. We show that medical domain word embeddings help improve relation classification. Seg-CNNs can be trained quickly for the i2b2\/VA dataset on a graphics processing unit (GPU) platform. These results support the use of CNNs computed over segments of text for classifying medical relations, as they show state-of-the-art performance while requiring no manual feature engineering.<\/jats:p>","DOI":"10.1093\/jamia\/ocx090","type":"journal-article","created":{"date-parts":[[2017,8,5]],"date-time":"2017-08-05T11:07:56Z","timestamp":1501931276000},"page":"93-98","source":"Crossref","is-referenced-by-count":55,"title":["Segment convolutional neural networks (Seg-CNNs) for classifying relations in clinical notes"],"prefix":"10.1093","volume":"25","author":[{"given":"Yuan","family":"Luo","sequence":"first","affiliation":[{"name":"Department of Preventive Medicine, Northwestern University, Chicago, IL, USA"}]},{"given":"Yu","family":"Cheng","sequence":"additional","affiliation":[{"name":"AI Foundations, IBM Thomas J Watson Research Center, Yorktown Heights, NY, USA"}]},{"given":"\u00d6zlem","family":"Uzuner","sequence":"additional","affiliation":[{"name":"Department of Computer Science, State University of New York at Albany, Albany, NY, USA"}]},{"given":"Peter","family":"Szolovits","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA, USA"}]},{"given":"Justin","family":"Starren","sequence":"additional","affiliation":[{"name":"Department of Preventive Medicine and Medical Social Science, Feinberg School of Medicine, Northwestern University, Chicago, IL, USA"}]}],"member":"286","published-online":{"date-parts":[[2017,8,31]]},"reference":[{"issue":"4\u20135","key":"2020110612453859300_ocx090-B1","first-page":"394","article-title":"Desiderata for controlled medical vocabularies in the twenty-first century","volume":"37","author":"Cimino","year":"1998","journal-title":"Methods Inf Med."},{"issue":"3","key":"2020110612453859300_ocx090-B2","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1016\/j.jbi.2005.11.008","article-title":"In defense of the desiderata","volume":"39","author":"Cimino","year":"2006","journal-title":"J Biomed Inform."},{"issue":"1","key":"2020110612453859300_ocx090-B3","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1093\/bib\/bbw001","article-title":"Bridging semantics and syntax with graph algorithms\u2014state-of-the-art of extracting biomedical relations","volume":"18","author":"Luo","year":"2016","journal-title":"Briefings Bioinform."},{"issue":"6","key":"2020110612453859300_ocx090-B4","doi-asserted-by":"crossref","first-page":"462","DOI":"10.1016\/j.jbi.2003.11.003","article-title":"The interaction of domain knowledge and linguistic structure in natural language processing: interpreting hypernymic propositions in biomedical text","volume":"36","author":"Rindflesch","year":"2003","journal-title":"J Biomed Inform."},{"issue":"5","key":"2020110612453859300_ocx090-B5","doi-asserted-by":"crossref","first-page":"824","DOI":"10.1136\/amiajnl-2013-002443","article-title":"Automatic lymphoma classification with sentence subgraph mining from pathology reports","volume":"21","author":"Luo","year":"2014","journal-title":"J Am Med Inform Assoc."},{"issue":"5","key":"2020110612453859300_ocx090-B6","doi-asserted-by":"crossref","first-page":"1009","DOI":"10.1093\/jamia\/ocv016","article-title":"Subgraph augmented non-negative tensor factorization (SANTF) for modeling clinical narrative text","volume":"22","author":"Luo","year":"2015","journal-title":"J Am Med Inform Assoc."},{"key":"2020110612453859300_ocx090-B7","doi-asserted-by":"crossref","first-page":"i116","DOI":"10.1136\/amiajnl-2011-000321","article-title":"EliXR: an approach to eligibility criteria extraction and representation","volume":"18","author":"Weng","year":"2011","journal-title":"J Am Med Inform Assoc."},{"issue":"6","key":"2020110612453859300_ocx090-B8","doi-asserted-by":"crossref","first-page":"1009","DOI":"10.1016\/j.jbi.2010.08.005","article-title":"Using text to build semantic networks for pharmacogenomics","volume":"43","author":"Coulet","year":"2010","journal-title":"J Biomed Inform."},{"issue":"2","key":"2020110612453859300_ocx090-B9","doi-asserted-by":"crossref","first-page":"S6","DOI":"10.1186\/1471-2105-10-S2-S6","article-title":"Pharmspresso: a text mining tool for extraction of pharmacogenomic concepts and relationships from full text","volume":"10","author":"Garten","year":"2009","journal-title":"BMC Bioinform."},{"issue":"e1","key":"2020110612453859300_ocx090-B10","doi-asserted-by":"crossref","first-page":"e28","DOI":"10.1136\/amiajnl-2011-000699","article-title":"Large-scale prediction of adverse drug reactions using chemical, biological, and phenotypic properties of drugs","volume":"19","author":"Liu","year":"2012","journal-title":"J Am Med Inform Assoc."},{"issue":"3","key":"2020110612453859300_ocx090-B11","doi-asserted-by":"crossref","first-page":"413","DOI":"10.1136\/amiajnl-2012-000930","article-title":"Combing signals from spontaneous reports and electronic health records for detection of adverse drug reactions","volume":"20","author":"Harpaz","year":"2013","journal-title":"J Am Med Inform Assoc."},{"key":"2020110612453859300_ocx090-B12","doi-asserted-by":"crossref","DOI":"10.1007\/s40264-017-0558-6","article-title":"Natural language processing for EHR-based pharmacovigilance: a structured review","author":"Luo","year":"2017","journal-title":"Drug Saf."},{"issue":"5","key":"2020110612453859300_ocx090-B13","doi-asserted-by":"crossref","first-page":"552","DOI":"10.1136\/amiajnl-2011-000203","article-title":"2010 i2b2\/VA challenge on concepts, assertions, and relations in clinical text","volume":"18","author":"Uzuner","year":"2011","journal-title":"J Am Med Inform Assoc."},{"issue":"5","key":"2020110612453859300_ocx090-B14","doi-asserted-by":"crossref","first-page":"507","DOI":"10.1136\/jamia.2009.001560","article-title":"Mayo clinical Text Analysis and Knowledge Extraction System (cTAKES): architecture, component evaluation and applications","volume":"17","author":"Savova","year":"2010","journal-title":"J Am Med Inform Assoc."},{"key":"2020110612453859300_ocx090-B15","volume-title":"Effective mapping of biomedical text to the UMLS Metathesaurus: the MetaMap program","author":"Aronson","year":"2001"},{"key":"2020110612453859300_ocx090-B16","doi-asserted-by":"crossref","volume-title":"Bidirectional inference with the easiest-first strategy for tagging sequence data","author":"Tsuruoka","DOI":"10.3115\/1220575.1220634"},{"issue":"5","key":"2020110612453859300_ocx090-B17","doi-asserted-by":"crossref","first-page":"557","DOI":"10.1136\/amiajnl-2011-000150","article-title":"Machine-learned solutions for three stages of clinical information extraction: the state of the art at i2b2 2010","volume":"18","author":"de Bruijn","year":"2011","journal-title":"J Am Med Inform Assoc."},{"key":"2020110612453859300_ocx090-B18","volume-title":"Salt Lake City VA\u2019s challenge submissions","author":"Divita","year":"2010"},{"issue":"5","key":"2020110612453859300_ocx090-B19","doi-asserted-by":"crossref","first-page":"594","DOI":"10.1136\/amiajnl-2011-000153","article-title":"Automatic extraction of relations between medical concepts in clinical texts","volume":"18","author":"Rink","year":"2011","journal-title":"J Am Med Inform Assoc."},{"key":"2020110612453859300_ocx090-B20","volume-title":"Concept, assertion and relation extraction at the 2010 i2b2 relation extraction challenge using parsing information and dictionaries","author":"Solt","year":"2010"},{"issue":"1","key":"2020110612453859300_ocx090-B21","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1016\/j.jbi.2011.10.007","article-title":"Enhancing clinical concept extraction with distributional semantics","volume":"45","author":"Jonnalagadda","year":"2012","journal-title":"J Biomed Inform."},{"key":"2020110612453859300_ocx090-B22","volume-title":"I2B2 2010 challenge: machine learning for information extraction from patient records","author":"Anick","year":"2010"},{"key":"2020110612453859300_ocx090-B23","volume-title":"NLM\u2019s system description for the fourth i2b2\/VA challenge","author":"Demner-Fushman","year":"2010"},{"key":"2020110612453859300_ocx090-B24","volume-title":"i2b2 Challenges in Clinical Natural Language Processing 2010","author":"Patrick","year":"2010"},{"key":"2020110612453859300_ocx090-B25","volume-title":"OHSU\/portland VAMC team participation in the 2010 i2b2\/VA challenge tasks","author":"Cohen","year":"2010"},{"key":"2020110612453859300_ocx090-B26","volume-title":"CARAMBA: concept, assertion, and relation annotation using machine-learning based approaches","author":"Grouin","year":"2010"},{"issue":"2","key":"2020110612453859300_ocx090-B27","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1016\/j.jbi.2012.11.006","article-title":"Detecting concept relations in clinical text: Insights from a state-of-the-art model","volume":"46","author":"Zhu","year":"2013","journal-title":"J Biomed Inform."},{"key":"2020110612453859300_ocx090-B28","volume-title":"Generalizing biomedical event extraction","author":"Bj\u00f6rne","year":"2011"},{"key":"2020110612453859300_ocx090-B29","doi-asserted-by":"crossref","volume-title":"Patch-based convolutional neural network for whole slide tissue image classification","author":"Hou","year":"2016","DOI":"10.1109\/CVPR.2016.266"},{"key":"2020110612453859300_ocx090-B30","article-title":"Relation extraction from clinical texts using domain invariant convolutional neural network","author":"Sahu","year":"2016","journal-title":"arXiv preprint arXiv:160609370."},{"issue":"2","key":"2020110612453859300_ocx090-B31","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1016\/j.artmed.2010.05.006","article-title":"Semantic relations for problem-oriented medical records","volume":"50","author":"Uzuner","year":"2010","journal-title":"Artif Intell Med."},{"key":"2020110612453859300_ocx090-B32","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.jbi.2017.07.006","article-title":"Recurrent neural networks for classifying relations in clinical notes","volume":"72","author":"Luo","year":"2017","journal-title":"J Biomed Inform"},{"key":"2020110612453859300_ocx090-B33","article-title":"Distributed representations of words and phrases and their compositionality","author":"Mikolov","year":"2013","journal-title":"Adv Neural Inf Process Syst."},{"key":"2020110612453859300_ocx090-B34","article-title":"Convolutional neural networks for sentence classification","author":"Kim","year":"2014","journal-title":"arXiv preprint arXiv:14085882."},{"key":"2020110612453859300_ocx090-B35","first-page":"2493","article-title":"Natural language processing (almost) from scratch","volume":"12","author":"Collobert","year":"2011","journal-title":"J Machine Learning Res."},{"issue":"3","key":"2020110612453859300_ocx090-B36","doi-asserted-by":"crossref","first-page":"671","DOI":"10.1093\/jamia\/ocu041","article-title":"Pharmacovigilance from social media: mining adverse drug reaction mentions using sequence labeling with word embedding cluster features","volume":"22","author":"Nikfarjam","year":"2015","journal-title":"J Am Med Inform Assoc."},{"key":"2020110612453859300_ocx090-B37","volume-title":"The New York Times Annotated Corpus 2008","author":"Sandhaus"},{"key":"2020110612453859300_ocx090-B38","doi-asserted-by":"crossref","first-page":"160035","DOI":"10.1038\/sdata.2016.35","article-title":"MIMIC-III, a freely accessible critical care database","volume":"3","author":"Johnson","year":"2016","journal-title":"Scientific Data."},{"key":"2020110612453859300_ocx090-B39","article-title":"A convolutional neural network for modelling sentences","author":"Kalchbrenner","year":"2014","journal-title":"arXiv preprint arXiv:14042188."},{"key":"2020110612453859300_ocx090-B40","volume-title":"Relation classification via convolutional deep neural network","author":"Zeng"},{"key":"2020110612453859300_ocx090-B41","article-title":"Improving neural networks by preventing co-adaptation of feature detectors","author":"Hinton","year":"2012","journal-title":"arXiv preprint arXiv:12070580."},{"issue":"1","key":"2020110612453859300_ocx090-B42","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J Machine Learning Res."},{"key":"2020110612453859300_ocx090-B43","volume-title":"Theano: A CPU and GPU math compiler in Python","author":"Bergstra"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/25\/1\/93\/34149652\/ocx090.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/25\/1\/93\/34149652\/ocx090.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,31]],"date-time":"2022-07-31T20:47:23Z","timestamp":1659300443000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/25\/1\/93\/4101223"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,8,31]]},"references-count":43,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2017,8,31]]},"published-print":{"date-parts":[[2018,1,1]]}},"URL":"http:\/\/dx.doi.org\/10.1093\/jamia\/ocx090","relation":{"has-review":[{"id-type":"doi","id":"10.3410\/f.731974174.793551524","asserted-by":"object"}]},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2018,1]]},"published":{"date-parts":[[2017,8,31]]}}}
