{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T13:59:08Z","timestamp":1786456748486,"version":"3.56.0"},"reference-count":55,"publisher":"Oxford University Press (OUP)","issue":"9","license":[{"start":{"date-parts":[[2024,4,17]],"date-time":"2024-04-17T00:00:00Z","timestamp":1713312000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"DOI":"10.13039\/100006093","name":"Patient-Centered Outcomes Research Institute","doi-asserted-by":"publisher","award":["ME-2018C3-14754"],"award-info":[{"award-number":["ME-2018C3-14754"]}],"id":[{"id":"10.13039\/100006093","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000054","name":"National Cancer Institute","doi-asserted-by":"publisher","award":["R01CA246418"],"award-info":[{"award-number":["R01CA246418"]}],"id":[{"id":"10.13039\/100000054","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000049","name":"National Institute on Aging","doi-asserted-by":"publisher","award":["NIA R56AG069880"],"award-info":[{"award-number":["NIA R56AG069880"]}],"id":[{"id":"10.13039\/100000049","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000049","name":"National Institute on Aging","doi-asserted-by":"publisher","award":["R01AG080624"],"award-info":[{"award-number":["R01AG080624"]}],"id":[{"id":"10.13039\/100000049","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000049","name":"National Institute on Aging","doi-asserted-by":"publisher","award":["R01AG083039"],"award-info":[{"award-number":["R01AG083039"]}],"id":[{"id":"10.13039\/100000049","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000049","name":"National Institute on Aging","doi-asserted-by":"publisher","award":["R01AG080991"],"award-info":[{"award-number":["R01AG080991"]}],"id":[{"id":"10.13039\/100000049","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000049","name":"National Institute on Aging","doi-asserted-by":"publisher","award":["R01AG084236"],"award-info":[{"award-number":["R01AG084236"]}],"id":[{"id":"10.13039\/100000049","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000049","name":"National Institute on Aging","doi-asserted-by":"publisher","award":["R01AG084178"],"award-info":[{"award-number":["R01AG084178"]}],"id":[{"id":"10.13039\/100000049","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000049","name":"National Institute on Aging","doi-asserted-by":"publisher","award":["R01AG076234"],"award-info":[{"award-number":["R01AG076234"]}],"id":[{"id":"10.13039\/100000049","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000049","name":"National Institute on Aging","doi-asserted-by":"publisher","award":["R33AG062884"],"award-info":[{"award-number":["R33AG062884"]}],"id":[{"id":"10.13039\/100000049","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Ed and Ethel Moore Alzheimer\u2019s Disease Research Program 23A09"},{"DOI":"10.13039\/100000060","name":"National Institute of Allergy and Infectious Diseases","doi-asserted-by":"publisher","award":["NIAID R01AI172875"],"award-info":[{"award-number":["NIAID R01AI172875"]}],"id":[{"id":"10.13039\/100000060","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000050","name":"National Heart, Lung, and Blood Institute","doi-asserted-by":"publisher","award":["NHLBI R01HL169277"],"award-info":[{"award-number":["NHLBI R01HL169277"]}],"id":[{"id":"10.13039\/100000050","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Cancer Informatics Shared Resource"},{"DOI":"10.13039\/100018776","name":"UF Health Cancer Center","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100018776","id-type":"DOI","asserted-by":"publisher"}]},{"name":"UF Clinical and Translational Science Institute Biomedical Informatics Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Objective<\/jats:title>\n                  <jats:p>To solve major clinical natural language processing (NLP) tasks using a unified text-to-text learning architecture based on a generative large language model (LLM) via prompt tuning.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Methods<\/jats:title>\n                  <jats:p>We formulated 7 key clinical NLP tasks as text-to-text learning and solved them using one unified generative clinical LLM, GatorTronGPT, developed using GPT-3 architecture and trained with up to 20 billion parameters. We adopted soft prompts (ie, trainable vectors) with frozen LLM, where the LLM parameters were not updated (ie, frozen) and only the vectors of soft prompts were updated, known as prompt tuning. We added additional soft prompts as a prefix to the input layer, which were optimized during the prompt tuning. We evaluated the proposed method using 7 clinical NLP tasks and compared them with previous task-specific solutions based on Transformer models.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results and Conclusion<\/jats:title>\n                  <jats:p>The proposed approach achieved state-of-the-art performance for 5 out of 7 major clinical NLP tasks using one unified generative LLM. Our approach outperformed previous task-specific transformer models by \u223c3% for concept extraction and 7% for relation extraction applied to social determinants of health, 3.4% for clinical concept normalization, 3.4%-10% for clinical abbreviation disambiguation, and 5.5%-9% for natural language inference. Our approach also outperformed a previously developed prompt-based machine reading comprehension (MRC) model, GatorTron-MRC, for clinical concept and relation extraction. The proposed approach can deliver the \u201cone model for all\u201d promise from training to deployment using a unified generative LLM.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/jamia\/ocae078","type":"journal-article","created":{"date-parts":[[2024,4,17]],"date-time":"2024-04-17T19:53:12Z","timestamp":1713383592000},"page":"1892-1903","source":"Crossref","is-referenced-by-count":26,"title":["Generative large language models are all-purpose text analytics engines: text-to-text learning is all your need"],"prefix":"10.1093","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1994-893X","authenticated-orcid":false,"given":"Cheng","family":"Peng","sequence":"first","affiliation":[{"name":"Department of Health Outcomes and Biomedical Informatics, College of Medicine, University of Florida , Gainesville, FL 32611, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Health Outcomes and Biomedical Informatics, College of Medicine, University of Florida , Gainesville, FL 32611, United States"},{"name":"Cancer Informatics Shared Resource, University of Florida Health Cancer Center , Gainesville, FL 32610, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aokun","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Health Outcomes and Biomedical Informatics, College of Medicine, University of Florida , Gainesville, FL 32611, United States"},{"name":"Cancer Informatics Shared Resource, University of Florida Health Cancer Center , Gainesville, FL 32610, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zehao","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Health Outcomes and Biomedical Informatics, College of Medicine, University of Florida , Gainesville, FL 32611, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaleb E","family":"Smith","sequence":"additional","affiliation":[{"name":"NVIDIA , Santa Clara, CA 95051, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anthony B","family":"Costa","sequence":"additional","affiliation":[{"name":"NVIDIA , Santa Clara, CA 95051, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mona G","family":"Flores","sequence":"additional","affiliation":[{"name":"NVIDIA , Santa Clara, CA 95051, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2238-5429","authenticated-orcid":false,"given":"Jiang","family":"Bian","sequence":"additional","affiliation":[{"name":"Department of Health Outcomes and Biomedical Informatics, College of Medicine, University of Florida , Gainesville, FL 32611, United States"},{"name":"Cancer Informatics Shared Resource, University of Florida Health Cancer Center , Gainesville, FL 32610, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6780-6135","authenticated-orcid":false,"given":"Yonghui","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Health Outcomes and Biomedical Informatics, College of Medicine, University of Florida , Gainesville, FL 32611, United States"},{"name":"Cancer Informatics Shared Resource, University of Florida Health Cancer Center , Gainesville, FL 32610, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2024,4,17]]},"reference":[{"key":"2024082207513754900_ocae078-B1","first-page":"2493","article-title":"Natural language processing (almost) from scratch","volume":"12","author":"Collobert","year":"2011","journal-title":"J Mach Learn Res"},{"key":"2024082207513754900_ocae078-B2","first-page":"4171","author":"Devlin","year":"2019"},{"key":"2024082207513754900_ocae078-B3","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume":"27","author":"Sutskever","year":"2014","journal-title":"Adv Neural Inf Process Syst"},{"issue":"1","key":"2024082207513754900_ocae078-B4","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J Mach Learn Res"},{"key":"2024082207513754900_ocae078-B5","first-page":"1","author":"Peng"},{"issue":"9","key":"2024082207513754900_ocae078-B6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3560815","article-title":"Pre-train, prompt, and predict: a systematic survey of prompting methods in natural language processing","volume":"55","author":"Liu","year":"2023","journal-title":"ACM Comput Surv"},{"key":"2024082207513754900_ocae078-B7","doi-asserted-by":"crossref","first-page":"799","DOI":"10.1007\/11550907_126","volume-title":"Artificial Neural Networks: Formal Models and Their Applications\u2014ICANN 2005","author":"Graves","year":"2005"},{"issue":"5","key":"2024082207513754900_ocae078-B8","doi-asserted-by":"crossref","first-page":"544","DOI":"10.1136\/amiajnl-2011-000464","article-title":"Natural language processing: an introduction","volume":"18","author":"Nadkarni","year":"2011","journal-title":"J Am Med Inform Assoc"},{"issue":"5","key":"2024082207513754900_ocae078-B9","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"},{"key":"2024082207513754900_ocae078-B10","doi-asserted-by":"crossref","first-page":"104346","DOI":"10.1016\/j.jbi.2023.104346","article-title":"Progress note understanding\u2013assessment and plan reasoning: overview of the 2022 N2C2 track 3 shared task","volume":"142","author":"Gao","year":"2023","journal-title":"J Biomed Inform"},{"key":"2024082207513754900_ocae078-B11","doi-asserted-by":"crossref","first-page":"212","DOI":"10.1007\/978-3-642-40802-1_24","volume-title":"Information Access Evaluation. Multilinguality, Multimodality, and Visualization","author":"Suominen","year":"2013"},{"issue":"5","key":"2024082207513754900_ocae078-B12","doi-asserted-by":"crossref","first-page":"806","DOI":"10.1136\/amiajnl-2013-001628","article-title":"Evaluating temporal relations in clinical text: 2012 i2b2 challenge","volume":"20","author":"Sun","year":"2013","journal-title":"J Am Med Inform Assoc"},{"key":"2024082207513754900_ocae078-B13","doi-asserted-by":"crossref","first-page":"104432","DOI":"10.1016\/j.jbi.2023.104432","article-title":"Overview of the 2022 n2c2 shared task on contextualized medication event extraction in clinical notes","volume":"144","author":"Mahajan","year":"2023","journal-title":"J Biomed Inform"},{"key":"2024082207513754900_ocae078-B14","first-page":"282"},{"key":"2024082207513754900_ocae078-B15","author":"Boser","year":"1992"},{"key":"2024082207513754900_ocae078-B16","volume-title":"Advances in Neural Information Processing Systems","author":"Mikolov","year":"2013"},{"key":"2024082207513754900_ocae078-B17","first-page":"1812","article-title":"Clinical named entity recognition using deep learning models","volume":"2017","author":"Wu","year":"2017","journal-title":"AMIA Annu Symp Proc"},{"issue":"1","key":"2024082207513754900_ocae078-B18","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1093\/jamia\/ocz144","article-title":"Identifying relations of medications with adverse drug events using recurrent convolutional neural networks and gradient boosting","volume":"27","author":"Yang","year":"2020","journal-title":"J Am Med Inform Assoc"},{"key":"2024082207513754900_ocae078-B19","first-page":"260","author":"Lample","year":"2016"},{"key":"2024082207513754900_ocae078-B20","first-page":"1","volume-title":"Proceedings of the 1st International Workshop on Medication and Adverse Drug Event Detection.","author":"Yang","year":"2018"},{"key":"2024082207513754900_ocae078-B21","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1186\/s12911-019-0935-4","article-title":"A study of deep learning methods for de-identification of clinical notes in cross-institute settings","volume":"19(Suppl 5)","author":"Yang","year":"2019","journal-title":"BMC Med Inform Decis Mak"},{"key":"2024082207513754900_ocae078-B22","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"issue":"12","key":"2024082207513754900_ocae078-B23","doi-asserted-by":"crossref","first-page":"1935","DOI":"10.1093\/jamia\/ocaa189","article-title":"Clinical concept extraction using transformers","volume":"27","author":"Yang","year":"2020","journal-title":"J Am Med Inform Assoc"},{"issue":"11","key":"2024082207513754900_ocae078-B24","doi-asserted-by":"crossref","first-page":"1297","DOI":"10.1093\/jamia\/ocz096","article-title":"Enhancing clinical concept extraction with contextual embeddings","volume":"26","author":"Si","year":"2019","journal-title":"J Am Med Inform Assoc"},{"key":"2024082207513754900_ocae078-B25","first-page":"1877","author":"Brown","year":"2020"},{"key":"2024082207513754900_ocae078-B26","author":"Touvron","year":"2023"},{"key":"2024082207513754900_ocae078-B27","author":"Yang"},{"key":"2024082207513754900_ocae078-B28","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1162\/tacl_a_00300","article-title":"SpanBERT: improving pre-training by representing and predicting spans","volume":"8","author":"Joshi","year":"2020","journal-title":"Trans Assoc Comput Linguist"},{"issue":"9","key":"2024082207513754900_ocae078-B29","doi-asserted-by":"crossref","first-page":"1486","DOI":"10.1093\/jamia\/ocad107","article-title":"Clinical concept and relation extraction using prompt-based machine reading comprehension","volume":"30","author":"Peng","year":"2023","journal-title":"J Am Med Inform Assoc"},{"issue":"1","key":"2024082207513754900_ocae078-B30","doi-asserted-by":"crossref","first-page":"194","DOI":"10.1038\/s41746-022-00742-2","article-title":"A large language model for electronic health records","volume":"5","author":"Yang","year":"2022","journal-title":"NPJ Digit Med"},{"key":"2024082207513754900_ocae078-B31","author":"Agrawal","year":"2022"},{"key":"2024082207513754900_ocae078-B32","author":"Peng"},{"issue":"1","key":"2024082207513754900_ocae078-B33","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1093\/jamia\/ocz166","article-title":"2018 n2c2 shared task on adverse drug events and medication extraction in electronic health records","volume":"27","author":"Henry","year":"2020","journal-title":"J Am Med Inform Assoc"},{"issue":"8","key":"2024082207513754900_ocae078-B34","doi-asserted-by":"crossref","first-page":"1367","DOI":"10.1093\/jamia\/ocad012","article-title":"The 2022 n2c2\/UW shared task on extracting social determinants of health","volume":"30","author":"Lybarger","year":"2023","journal-title":"J Am Med Inform Assoc"},{"key":"2024082207513754900_ocae078-B35","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":"Sci Data"},{"issue":"1","key":"2024082207513754900_ocae078-B36","doi-asserted-by":"crossref","first-page":"75","DOI":"10.3163\/1536-5050.100.1.017","article-title":"Introduction to modern information retrieval. 3rd ed","volume":"100","author":"Davenport","year":"2012","journal-title":"J Med Libr Assoc"},{"key":"2024082207513754900_ocae078-B37","first-page":"303","author":"Elhadad","year":"2015"},{"issue":"6","key":"2024082207513754900_ocae078-B38","doi-asserted-by":"crossref","first-page":"414","DOI":"10.1016\/j.jbi.2003.11.002","article-title":"Exploring semantic groups through visual approaches","volume":"36","author":"Bodenreider","year":"2003","journal-title":"J Biomed Inform"},{"key":"2024082207513754900_ocae078-B39","doi-asserted-by":"crossref","first-page":"641","DOI":"10.1109\/CIC.2002.1166854","volume-title":"Computers in Cardiology","author":"Saeed","year":"2002"},{"key":"2024082207513754900_ocae078-B40","author":"Moon","year":"2012"},{"key":"2024082207513754900_ocae078-B41","first-page":"1586","author":"Shivade","year":"2019"},{"key":"2024082207513754900_ocae078-B42","author":"Gao","year":"2020"},{"key":"2024082207513754900_ocae078-B43","first-page":"412","author":"Pathak","year":"2015"},{"key":"2024082207513754900_ocae078-B44","first-page":"406","author":"Leal","year":"2015"},{"key":"2024082207513754900_ocae078-B45","first-page":"311","author":"Xu","year":"2015"},{"issue":"4","key":"2024082207513754900_ocae078-B46","doi-asserted-by":"crossref","first-page":"501","DOI":"10.1007\/s41666-023-00146-1","article-title":"Sequence labeling for disambiguating medical abbreviations","volume":"7","author":"Cevik","year":"2023","journal-title":"J Healthc Inform Res"},{"issue":"4","key":"2024082207513754900_ocae078-B47","doi-asserted-by":"crossref","first-page":"1234","DOI":"10.1093\/bioinformatics\/btz682","article-title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","volume":"36","author":"Lee","year":"2020","journal-title":"Bioinformatics"},{"key":"2024082207513754900_ocae078-B48","author":"Sanh","year":"2020"},{"key":"2024082207513754900_ocae078-B49","first-page":"72","author":"Alsentzer","year":"2019"},{"key":"2024082207513754900_ocae078-B50","first-page":"4700","author":"Shin","year":"2020"},{"key":"2024082207513754900_ocae078-B51","first-page":"58","author":"Peng","year":"2019"},{"key":"2024082207513754900_ocae078-B52","doi-asserted-by":"crossref","first-page":"104370","DOI":"10.1016\/j.jbi.2023.104370","article-title":"Contextualized medication information extraction using transformer-based deep learning architectures","volume":"142","author":"Chen","year":"2023","journal-title":"J Biomed Inform"},{"key":"2024082207513754900_ocae078-B53","author":"Singhal","year":"2022"},{"key":"2024082207513754900_ocae078-B54","author":"Wei","year":"2022"},{"key":"2024082207513754900_ocae078-B55","author":"Chung","year":"2022"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/31\/9\/1892\/58868096\/ocae078.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/31\/9\/1892\/58868096\/ocae078.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,22]],"date-time":"2024-08-22T11:31:56Z","timestamp":1724326316000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/31\/9\/1892\/7648661"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,17]]},"references-count":55,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2024,4,17]]},"published-print":{"date-parts":[[2024,9,1]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocae078","relation":{},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,9]]},"published":{"date-parts":[[2024,4,17]]}}}