{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T09:07:57Z","timestamp":1770887277211,"version":"3.50.1"},"reference-count":56,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2018,5,13]],"date-time":"2018-05-13T00:00:00Z","timestamp":1526169600000},"content-version":"vor","delay-in-days":365,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1553109"],"award-info":[{"award-number":["IIS-1553109"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1552860"],"award-info":[{"award-number":["IIS-1552860"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,1,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Objective<\/jats:title>\n                  <jats:p>Recent years have seen increased worldwide popularity of e-cigarette use. However, the risks of e-cigarettes are underexamined. Most e-cigarette adverse event studies have achieved low detection rates due to limited subject sample sizes in the experiments and surveys. Social media provides a large data repository of consumers\u2019 e-cigarette feedback and experiences, which are useful for e-cigarette safety surveillance. However, it is difficult to automatically interpret the informal and nontechnical consumer vocabulary about e-cigarettes in social media. This issue hinders the use of social media content for e-cigarette safety surveillance. Recent developments in deep neural network methods have shown promise for named entity extraction from noisy text. Motivated by these observations, we aimed to design a deep neural network approach to extract e-cigarette safety information in social media.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Methods<\/jats:title>\n                  <jats:p>Our deep neural language model utilizes word embedding as the representation of text input and recognizes named entity types with the state-of-the-art Bidirectional Long Short-Term Memory (Bi-LSTM) Recurrent Neural Network.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>Our Bi-LSTM model achieved the best performance compared to 3 baseline models, with a precision of 94.10%, a recall of 91.80%, and an F-measure of 92.94%. We identified 1591 unique adverse events and 9930 unique e-cigarette components (ie, chemicals, flavors, and devices) from our research testbed.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusion<\/jats:title>\n                  <jats:p>Although the conditional random field baseline model had slightly better precision than our approach, our Bi-LSTM model achieved much higher recall, resulting in the best F-measure. Our method can be generalized to extract medical concepts from social media for other medical applications.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/jamia\/ocx045","type":"journal-article","created":{"date-parts":[[2017,4,11]],"date-time":"2017-04-11T11:56:57Z","timestamp":1491911817000},"page":"72-80","source":"Crossref","is-referenced-by-count":38,"title":["Mining e-cigarette adverse events in social media using Bi-LSTM recurrent neural network with word embedding representation"],"prefix":"10.1093","volume":"25","author":[{"given":"Jiaheng","family":"Xie","sequence":"first","affiliation":[{"name":"Department of Management Information Systems, University of Arizona, Tucson, AZ, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Operation and Information Systems, University of Utah, Salt Lake City, UT, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Dajun Zeng","sequence":"additional","affiliation":[{"name":"Department of Management Information Systems, University of Arizona, Tucson, AZ, USA"},{"name":"State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2017,5,13]]},"reference":[{"issue":"7","key":"2020110620011679300_ocx045-B1","doi-asserted-by":"crossref","first-page":"610","DOI":"10.1001\/jamapediatrics.2013.5488","article-title":"Electronic cigarettes and conventional cigarette use among US adolescents: a cross-sectional study","volume":"168","author":"Dutra","year":"2014","journal-title":"JAMA Pediatrics."},{"key":"2020110620011679300_ocx045-B2","first-page":"1","article-title":"Electronic cigarette use among adults: United States, 2014","volume":"217","author":"Schoenborn","year":"2015","journal-title":"NCHS Data Brief."},{"key":"2020110620011679300_ocx045-B3","unstructured":"FDA. Secondary2015. http:\/\/www.fda.gov\/NewsEvents\/PublicHealthFocus\/ucm172906.htm. Accessed April 2, 2017."},{"key":"2020110620011679300_ocx045-B4","unstructured":"Research\n              B\n            \n          . Electronic Cigarette & E Vapor (Vaporizer) Market Research Reports. Secondary Electronic Cigarette & E Vapor (Vaporizer) Market Research Reports2016. http:\/\/bisresearch.com\/electronic-cigarette-market-size-forecast.html. Accessed April 2, 2017."},{"issue":"Suppl 2","key":"2020110620011679300_ocx045-B5","doi-asserted-by":"crossref","first-page":"ii36","DOI":"10.1136\/tobaccocontrol-2013-051470","article-title":"Electronic cigarettes: human health effects","volume":"23","author":"Callahan-Lyon","year":"2014","journal-title":"Tobacco Control."},{"issue":"2","key":"2020110620011679300_ocx045-B6","doi-asserted-by":"crossref","first-page":"615","DOI":"10.1093\/ntr\/nts145","article-title":"FDA summary of adverse events on electronic cigarettes","volume":"15","author":"Chen","year":"2013","journal-title":"Nicotine Tobacco Res."},{"key":"2020110620011679300_ocx045-B7","unstructured":"FDA. \nFDA takes significant steps to protect Americans from dangers of tobacco through new regulation. Secondary FDA takes significant steps to protect Americans from dangers of tobacco through new regulation 2016. http:\/\/www.fda.gov\/NewsEvents\/Newsroom\/PressAnnouncements\/ucm499234.htm. Accessed April 2, 2017."},{"issue":"3","key":"2020110620011679300_ocx045-B8","doi-asserted-by":"crossref","first-page":"339","DOI":"10.1016\/j.amepre.2016.10.017","article-title":"Trends in E-Cigarette Awareness and Perceived Harmfulness in the US","volume":"52","author":"Huerta","year":"2016","journal-title":"Am J Prevent Med."},{"key":"2020110620011679300_ocx045-B9","doi-asserted-by":"crossref","first-page":"56","DOI":"10.3389\/fpubh.2013.00056","article-title":"Electronic cigarettes and vaping: a new challenge in clinical medicine and public health. A literature review","volume":"1","author":"Palazzolo","year":"2013","journal-title":"Front Public Health."},{"key":"2020110620011679300_ocx045-B10","first-page":"1","volume-title":"Evaluation of e-cigarettes","author":"Westenberger","year":"2009"},{"issue":"1","key":"2020110620011679300_ocx045-B11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/1471-2458-11-786","article-title":"Effect of an electronic nicotine delivery device (e-cigarette) on smoking reduction and cessation: a prospective 6-month pilot study","volume":"11","author":"Polosa","year":"2011","journal-title":"BMC Public Health."},{"issue":"2","key":"2020110620011679300_ocx045-B12","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1136\/tc.2009.031567","article-title":"Effect of an electronic nicotine delivery device (e cigarette) on desire to smoke and withdrawal, user preferences and nicotine delivery: randomised cross-over trial","volume":"19","author":"Bullen","year":"2010","journal-title":"Tobacco Control."},{"issue":"2","key":"2020110620011679300_ocx045-B13","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1136\/tobaccocontrol-2012-050859","article-title":"Levels of selected carcinogens and toxicants in vapour from electronic cigarettes","volume":"23","author":"Goniewicz","year":"2014","journal-title":"Tobacco Control."},{"issue":"2","key":"2020110620011679300_ocx045-B14","doi-asserted-by":"crossref","first-page":"91","DOI":"10.3109\/08958378.2012.758197","article-title":"Acute impact of active and passive electronic cigarette smoking on serum cotinine and lung function","volume":"25","author":"Flouris","year":"2013","journal-title":"Inhalation Toxicol."},{"issue":"221","key":"2020110620011679300_ocx045-B15","first-page":"S86","article-title":"Acute and short term impact of active and passive tobacco and electronic cigarette smoking on inflammatory markers","volume":"2013","author":"Tzatzarakis","journal-title":"Toxicol Lett."},{"issue":"8","key":"2020110620011679300_ocx045-B16","doi-asserted-by":"crossref","first-page":"1945","DOI":"10.1158\/1055-9965.EPI-10-0288","article-title":"A clinical laboratory model for evaluating the acute effects of electronic \u201ccigarettes\u201d: nicotine delivery profile and cardiovascular and subjective effects","volume":"19","author":"Vansickel","year":"2010","journal-title":"Cancer Epidemiol Biomarkers Prevent."},{"issue":"6","key":"2020110620011679300_ocx045-B17","doi-asserted-by":"crossref","first-page":"1400","DOI":"10.1378\/chest.11-2443","article-title":"Short-term pulmonary effects of using an electronic cigarette: impact on respiratory flow resistance, impedance, and exhaled nitric oxide","volume":"141","author":"Vardavas","year":"2012","journal-title":"Chest J."},{"issue":"3","key":"2020110620011679300_ocx045-B18","doi-asserted-by":"crossref","first-page":"428","DOI":"10.1109\/TITB.2011.2131669","article-title":"A potential causal association mining algorithm for screening adverse drug reactions in postmarketing surveillance","volume":"15","author":"Ji","year":"2011","journal-title":"IEEE Trans Inf Technol Biomed."},{"issue":"2","key":"2020110620011679300_ocx045-B19","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1177\/2042098614524430","article-title":"Safety evaluation and risk assessment of electronic cigarettes as tobacco cigarette substitutes: a systematic review","volume":"5","author":"Farsalinos","year":"2014","journal-title":"Therapeutic Adv Drug Safety."},{"key":"2020110620011679300_ocx045-B20","unstructured":"FDA. \nMedWatch Online Voluntary Reporting Form. Secondary MedWatch Online Voluntary Reporting Form 2016. https:\/\/www.accessdata.fda.gov\/scripts\/medwatch\/index.cfm?action=reporting.home. Accessed April 2, 2017."},{"issue":"2","key":"2020110620011679300_ocx045-B21","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1016\/j.ipm.2014.10.006","article-title":"Analysis of named entity recognition and linking for tweets","volume":"51","author":"Derczynski","year":"2015","journal-title":"Inform Process Manag."},{"issue":"3","key":"2020110620011679300_ocx045-B22","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1109\/MIS.2015.7","article-title":"Identifying adverse drug events from patient social media: a case study for diabetes","volume":"30","author":"Liu","year":"2015","journal-title":"IEEE Intell Sys."},{"key":"2020110620011679300_ocx045-B23","first-page":"1160","article-title":"Adverse drug event-based stratification of tumor mutations: a case study of breast cancer patients receiving aromatase inhibitors","author":"Wang","year":"2014","journal-title":"AMIA Annual Symposium Proceedings. American Medical Informatics Association"},{"issue":"Suppl 1","key":"2020110620011679300_ocx045-B24","doi-asserted-by":"crossref","first-page":"i73","DOI":"10.1136\/amiajnl-2011-000417","article-title":"Focus on clinical care and patient safety: Facilitating adverse drug event detection in pharmacovigilance databases using molecular structure similarity: application to rhabdomyolysis","volume":"18","author":"Vilar","year":"2011","journal-title":"J Am Med Inform Assoc."},{"key":"2020110620011679300_ocx045-B25","doi-asserted-by":"crossref","first-page":"202","DOI":"10.1016\/j.jbi.2015.02.004","article-title":"Utilizing social media data for pharmacovigilance: a review","volume":"54","author":"Sarker","year":"2015","journal-title":"J Biomed Inform."},{"issue":"22","key":"2020110620011679300_ocx045-B26","doi-asserted-by":"crossref","first-page":"2087","DOI":"10.1056\/NEJMp1004986","article-title":"Pharmaceutical Marketing and the New Social Media","volume":"363","author":"Greene","year":"2010","journal-title":"New Engl J Med."},{"key":"2020110620011679300_ocx045-B27","unstructured":"NLM. Unified Medical Language System. Secondary Unified Medical Language System2009. https:\/\/www.nlm.nih.gov\/research\/umls\/. Accessed April 2, 2017."},{"issue":"2","key":"2020110620011679300_ocx045-B28","doi-asserted-by":"crossref","first-page":"e1002854","DOI":"10.1371\/journal.pcbi.1002854","article-title":"Getting more out of biomedical documents with GATE\u2019s full lifecycle open source text analytics","volume":"9","author":"Cunningham","year":"2013","journal-title":"PLoS Comput Biol."},{"key":"2020110620011679300_ocx045-B29","first-page":"270","article-title":"A broad-coverage natural language processing system","author":"Friedman","year":"2000","journal-title":"Proceedings of the AMIA Symposium. American Medical Informatics Association"},{"key":"2020110620011679300_ocx045-B30","article-title":"Evaluation of YTEX and MetaMap for Clinical Concept Recognition","author":"Osborne"},{"issue":"5","key":"2020110620011679300_ocx045-B31","doi-asserted-by":"crossref","first-page":"902","DOI":"10.1136\/amiajnl-2014-002669","article-title":"Induced lexico-syntactic patterns improve information extraction from online medical forums","volume":"21","author":"Gupta","year":"2014","journal-title":"J\u2009Am Med Inform Assoc."},{"issue":"5","key":"2020110620011679300_ocx045-B32","doi-asserted-by":"crossref","first-page":"808","DOI":"10.1136\/amiajnl-2013-002381","article-title":"A comprehensive study of named entity recognition in Chinese clinical text","volume":"21","author":"Lei","year":"2014","journal-title":"J Am Med Inform Assoc."},{"issue":"11","key":"2020110620011679300_ocx045-B33","doi-asserted-by":"crossref","first-page":"3040","DOI":"10.1109\/TPDS.2014.2368568","article-title":"Hadoop recognition of biomedical named entity using conditional random fields","volume":"26","author":"Li","year":"2015","journal-title":"IEEE Trans Parallel Distributed Sys."},{"key":"2020110620011679300_ocx045-B34","doi-asserted-by":"crossref","first-page":"baw140","DOI":"10.1093\/database\/baw140","article-title":"Disease named entity recognition by combining conditional random fields and bidirectional recurrent neural networks","volume":"2016","author":"Wei","year":"2016","journal-title":"Database."},{"key":"2020110620011679300_ocx045-B35","first-page":"389","article-title":"Event discovery in social media feeds","volume":"1","author":"Benson","year":"2011","journal-title":"Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics."},{"key":"2020110620011679300_ocx045-B36","first-page":"1035","article-title":"Extracting opinion targets in a single- and cross-domain setting with conditional random fields","author":"Jakob","year":"2010","journal-title":"Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics."},{"key":"2020110620011679300_ocx045-B37","doi-asserted-by":"crossref","volume-title":"Neural Architectures for Named Entity Recognition","author":"Lample","DOI":"10.18653\/v1\/N16-1030"},{"issue":"10","key":"2020110620011679300_ocx045-B38","doi-asserted-by":"crossref","first-page":"627","DOI":"10.1145\/365628.365657","article-title":"Contextual correlates of synonymy","volume":"8","author":"Rubenstein","year":"1965","journal-title":"Commun ACM."},{"key":"2020110620011679300_ocx045-B39","first-page":"1818","volume-title":"Learning Character-level Representations for Part-of-Speech Tagging","author":"Dos Santos","year":"2014"},{"key":"2020110620011679300_ocx045-B40","first-page":"126","article-title":"Shared tasks of the 2015 workshop on noisy user-generated text: Twitter lexical normalization and named entity recognition","volume":"2015","author":"Baldwin","journal-title":"ACL-IJCNLP"},{"key":"2020110620011679300_ocx045-B41","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"Sutskever","year":"2014","journal-title":"Adv Neural Inform Process Sys."},{"key":"2020110620011679300_ocx045-B42","first-page":"1310","article-title":"On the difficulty of training recurrent neural networks","volume":"28","author":"Pascanu","year":"2013","journal-title":"ICML (3)."},{"issue":"5","key":"2020110620011679300_ocx045-B43","doi-asserted-by":"crossref","first-page":"723","DOI":"10.1002\/(SICI)1097-0258(20000315)19:5<723::AID-SIM379>3.0.CO;2-A","article-title":"Interval estimation for Cohen\u2019s kappa as a measure of agreement","volume":"19","author":"Blackman","year":"2000","journal-title":"Stats Med."},{"key":"2020110620011679300_ocx045-B44","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"Milokov","year":"2013","journal-title":"Adv Neural Inform Process Sys."},{"key":"2020110620011679300_ocx045-B45","doi-asserted-by":"crossref","volume-title":"Improved Semantic Representations from Tree-structured Long Short-term Memory Networks","author":"Tai","DOI":"10.3115\/v1\/P15-1150"},{"key":"2020110620011679300_ocx045-B46","article-title":"Hybrid speech recognition with deep bidirectional LSTM","author":"Graves","journal-title":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding."},{"key":"2020110620011679300_ocx045-B47","volume-title":"Finding Function in Form: Compositional Character Models for Open Vocabulary Word Representation","author":"Ling"},{"key":"2020110620011679300_ocx045-B48","first-page":"384","article-title":"Word representations: a simple and general method for semi-supervised learning","author":"Turian","year":"2010","journal-title":"Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics."},{"key":"2020110620011679300_ocx045-B49","first-page":"1524","article-title":"Named entity recognition in tweets: an experimental study","author":"Ritter","year":"2011","journal-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics"},{"key":"2020110620011679300_ocx045-B50","first-page":"652","volume-title":"Pacific Symp Biocomput","author":"Leaman R, Gonzalez G. BANNER: an executable survey of advances in biomedical named entity recognition","year":"2008"},{"key":"2020110620011679300_ocx045-B51","volume-title":"CRFsuite: a Fast Implementation of Conditional Random Fields (CRFs)","author":"Okazaki","year":"2007"},{"key":"2020110620011679300_ocx045-B52","first-page":"17","article-title":"Effective mapping of biomedical text to the UMLS Metathesaurus: the MetaMap program","author":"Aronson","year":"2001","journal-title":"Proceedings of the AMIA Symposium. American Medical Informatics Association."},{"issue":"3","key":"2020110620011679300_ocx045-B53","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1136\/jamia.2009.002733","article-title":"An overview of MetaMap: historical perspective and recent advances","volume":"17","author":"Aronson","year":"2010","journal-title":"J Am Med Inform Assoc."},{"issue":"5","key":"2020110620011679300_ocx045-B54","doi-asserted-by":"crossref","first-page":"925","DOI":"10.1136\/amiajnl-2014-002767","article-title":"Applying MetaMap to Medline for identifying novel associations in a large clinical dataset: a feasibility analysis","volume":"21","author":"Hanauer","year":"2014","journal-title":"J Am Med Inform Assoc."},{"key":"2020110620011679300_ocx045-B55","unstructured":"Utah UO. Collaborative Consumer Health Vocabulary Initiative. Secondary Collaborative Consumer Health Vocabulary Initiative2011. http:\/\/consumerhealthvocab.org\/. Accessed April 2, 2017."},{"key":"2020110620011679300_ocx045-B56","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J Machine Learning Res."}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/25\/1\/72\/34149565\/ocx045.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/25\/1\/72\/34149565\/ocx045.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,7]],"date-time":"2020-11-07T01:03:14Z","timestamp":1604710994000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/25\/1\/72\/3826532"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,5,13]]},"references-count":56,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2017,5,13]]},"published-print":{"date-parts":[[2018,1,1]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocx045","relation":{},"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":[[2017,5,13]]}}}