{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T16:10:10Z","timestamp":1792512610108,"version":"4.5.0"},"reference-count":53,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Med Inform"],"abstract":"\n Background<\/jats:title>\n Understanding the multifaceted nature of health outcomes requires a comprehensive examination of the social, economic, and environmental determinants that shape individual well-being. Among these determinants, behavioral factors play a crucial role, particularly the consumption patterns of psychoactive substances, which have important implications on public health. The Global Burden of Disease Study shows a growing impact in disability-adjusted life years due to substance use. The successful identification of patients\u2019 substance use information equips clinical care teams to address substance-related issues more effectively, enabling targeted support and ultimately improving patient outcomes.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n Traditional natural language processing methods face limitations in accurately parsing diverse clinical language associated with substance use. Large language models offer promise in overcoming these challenges by adapting to diverse language patterns. This study investigates the application of the generative pretrained transformer (GPT) model in specific GPT-3.5 for extracting tobacco, alcohol, and substance use information from patient discharge summaries in zero-shot and few-shot learning settings. This study contributes to the evolving landscape of health care informatics by showcasing the potential of advanced language models in extracting nuanced information critical for enhancing patient care.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n The main data source for analysis in this paper is Medical Information Mart for Intensive Care III data set. Among all notes in this data set, we focused on discharge summaries. Prompt engineering was undertaken, involving an iterative exploration of diverse prompts. Leveraging carefully curated examples and refined prompts, we investigate the model\u2019s proficiency through zero-shot as well as few-shot prompting strategies.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n Results show GPT\u2019s varying effectiveness in identifying mentions of tobacco, alcohol, and substance use across learning scenarios. Zero-shot learning showed high accuracy in identifying substance use, whereas few-shot learning reduced accuracy but improved in identifying substance use status, enhancing recall and F1-score at the expense of lower precision.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n Excellence of zero-shot learning in precisely extracting text span mentioning substance use demonstrates its effectiveness in situations in which comprehensive recall is important. Conversely, few-shot learning offers advantages when accurately determining the status of substance use is the primary focus, even if it involves a trade-off in precision. The results contribute to enhancement of early detection and intervention strategies, tailor treatment plans with greater precision, and ultimately, contribute to a holistic understanding of patient health profiles. By integrating these artificial intelligence\u2013driven methods into electronic health record systems, clinicians can gain immediate, comprehensive insights into substance use that results in shaping interventions that are not only timely but also more personalized and effective.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/56243","type":"journal-article","created":{"date-parts":[[2024,7,18]],"date-time":"2024-07-18T13:34:05Z","timestamp":1721309645000},"page":"e56243","source":"Crossref","is-referenced-by-count":18,"title":["Extraction of Substance Use Information From Clinical Notes: Generative Pretrained Transformer\u2013Based Investigation"],"prefix":"10.2196","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9034-7803","authenticated-orcid":false,"given":"Fatemeh","family":"Shah-Mohammadi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8084-7441","authenticated-orcid":false,"given":"Joseph","family":"Finkelstein","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2024,8,19]]},"reference":[{"key":"ref1","author":"Ezzati, M","year":"2004","journal-title":"Global and Regional Burden of Disease Attributable to Selected Major Risk Factors"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1002\/9780470713624.ch3","author":"Rehm, J","year":"2005","journal-title":"Preventing Harmful Substance Use: The Evidence Base for Policy and Practice"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1111\/j.1360-0443.2005.01338.x"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/009145090603300302"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1046\/j.1360-0443.1998.9379914.x"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10198-005-0282-5"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1111\/j.1468-1331.2005.01194.x"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1046\/j.1360-0443.2003.00467.x"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1177\/174182670301000104"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1046\/j.1360-0443.2000.951015056.x"},{"key":"ref11","first-page":"255","author":"Volkow, ND","year":"2010","journal-title":"Drugs, Brains, and Behavior: The Science of Addiction"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1001\/jama.284.13.1689"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1001\/jamainternmed.2014.4052"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1300\/J465v28n03_03"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1002\/14651858.CD007210.pub3"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0175383"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/access.2020.3041895"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.annemergmed.2019.04.020"},{"key":"ref19","unstructured":"Shah-MohammadiFCuiWBachiKHurdYFinkelsteinJUsing natural language processing of clinical notes to predict outcomes of opioid treatment program202244th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)2022 July 11-15Glasgow, Scotland, United Kingdom44154420"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11904-018-0396-x"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1111\/add.13622"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11606-019-05251-9"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s40271-014-0095-7"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph20196873"},{"key":"ref25","unstructured":"StraussTOrganizational factors underlying the adoption of a patient-centered approach in physician-patient interaction [dissertation]. Israel: University of Haifa20202024-07-25https:\/\/login.ezproxy.lib.utah.edu\/login?url=https:\/\/www.proquest.com\/dissertations-theses\/organizational-factors-underlying-adoption\/docview\/2593014088\/se-2?accountid=14677"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1089\/pop.2021.0255"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1080\/15504263.2018.1518553"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1097\/ADM.0000000000000819"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18502\/ijph.v50i11.7600"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1080\/01947640701732148"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0272-7"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.7326\/M15-0510"},{"key":"ref33","first-page":"1","author":"Edmunds, M","year":"1997","journal-title":"Managing Managed Care: Quality Improvement in Behavioral Health"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3389\/fpubh.2022.850619"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocab170"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocad071"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2303.18223"},{"key":"ref38","unstructured":"GPT-4 technical reportOpenAI20232023-12-22https:\/\/cdn.openai.com\/papers\/gpt-4.pdf"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.9781\/ijimai.2023.04.007"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3857\/roj.2023.00633"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06291-2"},{"key":"ref42","unstructured":"OuyangLWuJJiangXAlmeidaDWainwrightCMishkinPZhangCAgarwalSSlamaKRayASchulmanJTraining language models to follow instructions with human feedbackAdv Neural Inf Process Syst202236th International Conference on Neural Information Processing Systems28 November 2022- 9 December 2022New Orleans LA USA2773027744"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2020.103631"},{"key":"ref44","unstructured":"BrownTMannBRyderNSubbiahMKaplanJDDhariwalPNeelakantanAShyamPSastryGAskellAAgarwalSLanguage models are few-shot learnersAdv Neural Inf Process Syst202034th International Conference on Neural Information Processing SystemsDecember 6 - 12Vancouver BC CanadaCurran Associates Inc.57 Morehouse LaneRed HookNYUnited States18771901"},{"issue":"Supplement 1","key":"ref45","first-page":"69","volume":"116","author":"Saeed, AM","year":"2023","journal-title":"QJM Int J Med"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21608\/muj.2023.209496.1139"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1164\/rccm.200703-456SO"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1097\/01.HCR.0000291300.55270.0d"},{"key":"ref49","unstructured":"American Lung AssociationLearn about COPD2024-01-01https:\/\/www.lung.org\/lung-health-diseases\/lung-disease-lookup\/copd\/learn-about-copd"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.3233\/SHTI231033"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3233\/SHTI230560"},{"key":"ref52","first-page":"2121","volume":"2015","author":"Wang, Y","year":"2015","journal-title":"AMIA Annu Symp Proc"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.3233\/SHTI210160"}],"container-title":["JMIR Medical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/medinform.jmir.org\/2024\/1\/e56243","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T17:45:00Z","timestamp":1782841500000},"score":1,"resource":{"primary":{"URL":"https:\/\/medinform.jmir.org\/2024\/1\/e56243"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,19]]},"references-count":53,"URL":"https:\/\/doi.org\/10.2196\/56243","relation":{"has-preprint":[{"id-type":"doi","id":"10.2196\/preprints.56243","asserted-by":"object"}]},"ISSN":["2291-9694"],"issn-type":[{"value":"2291-9694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,19]]}}}