{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T20:39:47Z","timestamp":1772138387385,"version":"3.50.1"},"reference-count":42,"publisher":"Oxford University Press (OUP)","issue":"12","license":[{"start":{"date-parts":[[2021,10,6]],"date-time":"2021-10-06T00:00:00Z","timestamp":1633478400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000092","name":"National Library of Medicine","doi-asserted-by":"publisher","award":["R01LM011176"],"award-info":[{"award-number":["R01LM011176"]}],"id":[{"id":"10.13039\/100000092","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000092","name":"National Library of Medicine","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000092","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,11,25]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>We address a first step toward using social media data to supplement current efforts in monitoring population-level medication nonadherence: detecting changes to medication treatment. Medication treatment changes, like changes to dosage or to frequency of intake, that are not overseen by physicians are, by that, nonadherence to medication. Despite the consequences, including worsening health conditions or death, 50% of patients are estimated to not take medications as indicated. Current methods to identify nonadherence have major limitations. Direct observation may be intrusive or expensive, and indirect observation through patient surveys relies heavily on patients\u2019 memory and candor. Using social media data in these studies may address these limitations.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We annotated 9830 tweets mentioning medications and trained a convolutional neural network (CNN) to find mentions of medication treatment changes, regardless of whether the change was recommended by a physician. We used active and transfer learning from 12 972 reviews we annotated from WebMD to address the class imbalance of our Twitter corpus. To validate our CNN and explore future directions, we annotated 1956 positive tweets as to whether they reflect nonadherence and categorized the reasons given.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Our CNN achieved 0.50 F1-score on this new corpus. The manual analysis of positive tweets revealed that nonadherence is evident in a subset with 9 categories of reasons for nonadherence.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>We showed that social media users publicly discuss medication treatment changes and may explain their reasons including when it constitutes nonadherence. This approach may be useful to supplement current efforts in adherence monitoring.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/jamia\/ocab158","type":"journal-article","created":{"date-parts":[[2021,7,24]],"date-time":"2021-07-24T07:09:04Z","timestamp":1627110544000},"page":"2551-2561","source":"Crossref","is-referenced-by-count":12,"title":["Active neural networks to detect mentions of changes to medication treatment in social media"],"prefix":"10.1093","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8331-3675","authenticated-orcid":false,"given":"Davy","family":"Weissenbacher","sequence":"first","affiliation":[{"name":"Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4802-6392","authenticated-orcid":false,"given":"Suyu","family":"Ge","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8281-3464","authenticated-orcid":false,"given":"Ari","family":"Klein","sequence":"additional","affiliation":[{"name":"Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7709-3813","authenticated-orcid":false,"given":"Karen","family":"O\u2019Connor","sequence":"additional","affiliation":[{"name":"Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6066-1159","authenticated-orcid":false,"given":"Robert","family":"Gross","sequence":"additional","affiliation":[{"name":"Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4726-9413","authenticated-orcid":false,"given":"Sean","family":"Hennessy","sequence":"additional","affiliation":[{"name":"Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6416-9556","authenticated-orcid":false,"given":"Graciela","family":"Gonzalez-Hernandez","sequence":"additional","affiliation":[{"name":"Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA"}]}],"member":"286","published-online":{"date-parts":[[2021,10,6]]},"reference":[{"issue":"1","key":"2021120106305098800_ocab158-B1","doi-asserted-by":"crossref","first-page":"30","DOI":"10.7326\/M18-0543","article-title":"ESPACOMP Medication Adherence Reporting Guideline (EMERGE)","volume":"169","author":"De Geest","year":"2018","journal-title":"Ann Intern Med"},{"issue":"2","key":"2021120106305098800_ocab158-B2","doi-asserted-by":"crossref","first-page":"107","DOI":"10.4103\/0253-7176.101762","article-title":"Non-compliance in pharmacotherapy","volume":"34","author":"Reddy","year":"2012","journal-title":"Indian J Psychol Med"},{"issue":"5","key":"2021120106305098800_ocab158-B3","doi-asserted-by":"crossref","first-page":"691","DOI":"10.1111\/j.1365-2125.2012.04167.x","article-title":"A new taxonomy for describing and de\ufb01ning adherence to medications","volume":"73","author":"Vrijens","year":"2012","journal-title":"Br J Clin Pharmacol"},{"key":"2021120106305098800_ocab158-B4","year":"1923"},{"issue":"9","key":"2021120106305098800_ocab158-B5","doi-asserted-by":"crossref","first-page":"829","DOI":"10.1177\/1060028018765159","article-title":"Cost of prescription drug\u2013related morbidity and mortality","volume":"52","author":"Watanabe","year":"2018","journal-title":"Ann Pharmacother"},{"key":"2021120106305098800_ocab158-B6","doi-asserted-by":"crossref","first-page":"675","DOI":"10.2147\/PPA.S29549","article-title":"Definitions, variants, and causes of nonadherence with medication: a challenge for tailored interventions","volume":"7","author":"Hugtenburg","year":"2013","journal-title":"Patient Prefer Adherence"},{"issue":"20","key":"2021120106305098800_ocab158-B7","doi-asserted-by":"crossref","first-page":"2105","DOI":"10.1001\/jama.2013.4638","article-title":"Medication nonadherence: a diagnosable and treatable medical condition","volume":"309","author":"Marcum","year":"2013","journal-title":"JAMA"},{"issue":"5","key":"2021120106305098800_ocab158-B8","doi-asserted-by":"crossref","first-page":"487","DOI":"10.1056\/NEJMra050100","article-title":"Adherence to medication","volume":"353","author":"Osterberg","year":"2005","journal-title":"N Engl J Med"},{"key":"2021120106305098800_ocab158-B9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2015\/217047","article-title":"Medication adherence measures: an overview","volume":"2015","author":"Yin Lam","year":"2015","journal-title":"Biomed Res Int"},{"key":"2021120106305098800_ocab158-B10","author":"Shaban","year":"2019"},{"key":"2021120106305098800_ocab158-B11","doi-asserted-by":"crossref","first-page":"32","DOI":"10.18653\/v1\/W18-5908","article-title":"Dealing with medication nonadherence expressions in Twitter","volume-title":"Proceedings of the 2018 EMNLP Workshop SMM4H: The 3rd Social Media Mining for Health Applications Workshop & Shared Task","author":"Onishi","year":"2018"},{"key":"2021120106305098800_ocab158-B12","first-page":"762","article-title":"Classification of medication status change in clinical narratives","volume":"2010","author":"Sohn","year":"2010","journal-title":"AMIA Annu Symp Proc"},{"key":"2021120106305098800_ocab158-B13","first-page":"856","article-title":"Mining clinicians' electronic documentation to identify heart failure patients with ineffective self-management: a pilot text-mining study","volume":"225","author":"Topaz","year":"2016","journal-title":"Stud Health Technol Inform"},{"issue":"11","key":"2021120106305098800_ocab158-B14","doi-asserted-by":"crossref","first-page":"1444","DOI":"10.1093\/jamia\/ocy118","article-title":"The therapy is making me sick: how online portal communications between breast cancer patients and physicians indicate medication discontinuation","volume":"25","author":"Yin","year":"2018","journal-title":"J Am Med Inform Assoc"},{"issue":"3","key":"2021120106305098800_ocab158-B15","doi-asserted-by":"crossref","first-page":"256","DOI":"10.1002\/pds.3365","article-title":"Online discussion of drug side effects and discontinuation among breast cancer survivors","volume":"22","author":"Mao","year":"2013","journal-title":"Pharmacoepidemiol Drug Saf"},{"issue":"3","key":"2021120106305098800_ocab158-B16","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1007\/s40290-017-0186-6","article-title":"Using social media data in routine pharmacovigilance: a pilot study to identify safety signals and patient perspectives","volume":"31","author":"Bhattacharya","year":"2017","journal-title":"Pharm Med"},{"issue":"3","key":"2021120106305098800_ocab158-B17","doi-asserted-by":"crossref","first-page":"e85","DOI":"10.2196\/jmir.9222","article-title":"Detection of cases of noncompliance to drug treatment in patient forum posts: topic model approach","volume":"20","author":"Abdellaoui","year":"2018","journal-title":"J Med Internet Res"},{"key":"2021120106305098800_ocab158-B18","first-page":"30","article-title":"Detecting drug non-compliance in internet fora using information retrieval and machine learning approaches","volume":"264","author":"Bigeard","year":"2019","journal-title":"Stud Health Technol Inform"},{"key":"2021120106305098800_ocab158-B19","first-page":"202","article-title":"Conceptualisation and annotation of drug nonadherence information for knowledge extraction from patient-generated texts","volume-title":"Proceedings of the 2019 EMNLP Workshop W-NUT: The 5th Workshop on Noisy User-generated Text","author":"Belz","year":"2019"},{"key":"2021120106305098800_ocab158-B20","first-page":"618","article-title":"Reciprocity and its association with treatment adherence in an online breast cancer forum","author":"Yin, L. Song","year":"2017","journal-title":"EEE 30th International Symposium on Computer-Based Medical Systems (CBMS); IEEE Computer Society; Thessaloniki, Greece"},{"key":"2021120106305098800_ocab158-B21","doi-asserted-by":"crossref","DOI":"10.2139\/ssrn.3091923","article-title":"Understanding medication nonadherence from social media: a sentiment-enriched deep learning approach","author":"Xie","year":"2017","journal-title":"SSRN Electron J"},{"issue":"6","key":"2021120106305098800_ocab158-B22","doi-asserted-by":"crossref","first-page":"e208953","DOI":"10.1001\/jamanetworkopen.2020.8953","article-title":"Assessment of beliefs and attitudes about statins posted on Twitter","volume":"3","author":"Golder","year":"2020","journal-title":"JAMA Netw Open"},{"issue":"12","key":"2021120106305098800_ocab158-B23","doi-asserted-by":"crossref","first-page":"1618","DOI":"10.1093\/jamia\/ocz156","article-title":"Deep neural networks ensemble for detecting medication mentions in tweets","volume":"26","author":"Weissenbacher","year":"2019","journal-title":"J Am Med Inform Assoc"},{"key":"2021120106305098800_ocab158-B24","doi-asserted-by":"crossref","first-page":"220","DOI":"10.1016\/j.eswa.2016.12.035","article-title":"Learning from class-imbalanced data: Review of methods and applications","volume":"73","author":"Haixiang","year":"2017","journal-title":"Expert Syst Appl"},{"key":"2021120106305098800_ocab158-B25","first-page":"7949","volume-title":"Proceedings of the 2020 Conference on EMNLP","author":"Ein-Dor","year":"2020"},{"key":"2021120106305098800_ocab158-B26","doi-asserted-by":"crossref","first-page":"5851","DOI":"10.18653\/v1\/P19-1586","article-title":"Low-resource deep entity resolution with transfer and active learning","author":"Kasai","year":"2019","journal-title":"Annual Meeting of the Association for Computational Linguistics"},{"key":"2021120106305098800_ocab158-B27","doi-asserted-by":"crossref","first-page":"1417","DOI":"10.1109\/WACV45572.2020.9093475","article-title":"Active learning for imbalanced datasets","author":"Aggarwal","year":"2020","journal-title":"IEEE Winter Conference on Applications of Computer Vision (WACV)"},{"key":"2021120106305098800_ocab158-B28","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-98074-4","volume-title":"Learning from Imbalanced Data Sets","author":"Fern\u00e1ndez","year":"2018"},{"key":"2021120106305098800_ocab158-B29","doi-asserted-by":"crossref","first-page":"13","DOI":"10.18653\/v1\/W18-5904","article-title":"Overview of the Third Social Media Mining for Health (SMM4H) shared tasks at EMNLP 2018","volume-title":"Proceedings of the 2018 EMNLP Workshop SMM4H: The 3rd Social Media Mining for Health Applications Workshop and Shared Task","author":"Weissenbacher","year":"2018"},{"issue":"3","key":"2021120106305098800_ocab158-B30","doi-asserted-by":"crossref","first-page":"276","DOI":"10.11613\/BM.2012.031","article-title":"Interrater reliability: the kappa statistic","volume":"22","author":"McHugh","year":"2012","journal-title":"Biochem Med (Zagreb)"},{"key":"2021120106305098800_ocab158-B31","article-title":"Investigating the effectiveness of representations based on word-embeddings in active learning for labelling text datasets","author":"Lu","year":"2019","journal-title":"arXiv"},{"key":"2021120106305098800_ocab158-B32","first-page":"56","article-title":"Analyzing and interpreting neural networks for NLP","volume-title":"Proceedings of the 2018 EMNLP Workshop BlackboxNLP","author":"Jacovi","year":"2018"},{"key":"2021120106305098800_ocab158-B33","doi-asserted-by":"crossref","DOI":"10.1201\/9780849333750","volume-title":"Neural Networks for Applied Sciences and Engineering: From Fundamentals to Complex Pattern Recognition","author":"Samarasinghe","year":"2006"},{"key":"2021120106305098800_ocab158-B34","doi-asserted-by":"crossref","first-page":"146","DOI":"10.18653\/v1\/W15-4322","article-title":"Multimedia Lab@ACL WNUT NER shared task: named entity recognition for twitter microposts using distributed word representations","volume-title":"Proceedings of the Workshop on Noisy User-Generated Text","author":"Godin","year":"2015"},{"key":"2021120106305098800_ocab158-B35","volume-title":"Natural Language Processing with Python","author":"Bird","year":"2009"},{"key":"2021120106305098800_ocab158-B36","volume-title":"Active Learning, Synthesis Lectures on Artificial Intelligence and Machine Learning","author":"Settles","year":"2012"},{"key":"2021120106305098800_ocab158-B37","volume-title":"Extraction Automatique D'information: Du Texte Brut au Web S\u00e9mantique","author":"Poibeau","year":"2003"},{"key":"2021120106305098800_ocab158-B38","first-page":"548","article-title":"Textual Deconvolution Saliency ({TDS}): a deep tool box for linguistic analysis","volume-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics","author":"Vanni","year":"2018"},{"key":"2021120106305098800_ocab158-B39","first-page":"21","author":"Weissenbacher","year":"2019"},{"key":"2021120106305098800_ocab158-B40","doi-asserted-by":"crossref","first-page":"58","DOI":"10.18653\/v1\/W19-5006","article-title":"Transfer learning in biomedical natural language processing: an evaluation of BERT and ELMo on ten benchmarking datasets","volume-title":"Proceedings of the 18th BioNLP Workshop and Shared Task","author":"Peng","year":"2019"},{"key":"2021120106305098800_ocab158-B41","first-page":"25","article-title":"The benefits of word embeddings features for active learning in clinical information extraction","volume-title":"Proceedings of Australasian Language Technology Association Workshop","author":"Kholghi","year":"2016"},{"key":"2021120106305098800_ocab158-B42","first-page":"400","article-title":"Is the sample good enough? Comparing data from Twitter\u2019s streaming API with Twitter\u2019s firehose","volume-title":"Proceedings of the Seventh International AAAI Conference on Weblogs and Social Media","author":"Morstatter","year":"2013"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/28\/12\/2551\/41325314\/ocab158.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/28\/12\/2551\/41325314\/ocab158.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T05:00:49Z","timestamp":1638334849000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/28\/12\/2551\/6382264"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,6]]},"references-count":42,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2021,10,6]]},"published-print":{"date-parts":[[2021,11,25]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocab158","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2020.12.04.20244210","asserted-by":"object"}]},"ISSN":["1527-974X"],"issn-type":[{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,12,1]]},"published":{"date-parts":[[2021,10,6]]}}}