{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T04:13:57Z","timestamp":1776917637662,"version":"3.51.2"},"reference-count":23,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,4,12]],"date-time":"2023-04-12T00:00:00Z","timestamp":1681257600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Digit. Health"],"abstract":"<jats:p>As large language models (LLMs) expand and become more advanced, so do the natural language processing capabilities of conversational AI, or \u201cchatbots\u201d. OpenAI's recent release, ChatGPT, uses a transformer-based model to enable human-like text generation and question-answering on general domain knowledge, while a healthcare-specific Large Language Model (LLM) such as GatorTron has focused on the real-world healthcare domain knowledge. As LLMs advance to achieve near human-level performances on medical question and answering benchmarks, it is probable that Conversational AI will soon be developed for use in healthcare. In this article we discuss the potential and compare the performance of two different approaches to generative pretrained transformers\u2014ChatGPT, the most widely used general conversational LLM, and Foresight, a GPT (generative pretrained transformer) based model focused on modelling patients and disorders. The comparison is conducted on the task of forecasting relevant diagnoses based on clinical vignettes. We also discuss important considerations and limitations of transformer-based chatbots for clinical use.<\/jats:p>","DOI":"10.3389\/fdgth.2023.1161098","type":"journal-article","created":{"date-parts":[[2023,4,12]],"date-time":"2023-04-12T01:41:41Z","timestamp":1681263701000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":143,"title":["AI chatbots not yet ready for clinical use"],"prefix":"10.3389","volume":"5","author":[{"given":"Joshua","family":"Au Yeung","sequence":"first","affiliation":[]},{"given":"Zeljko","family":"Kraljevic","sequence":"additional","affiliation":[]},{"given":"Akish","family":"Luintel","sequence":"additional","affiliation":[]},{"given":"Alfred","family":"Balston","sequence":"additional","affiliation":[]},{"given":"Esther","family":"Idowu","sequence":"additional","affiliation":[]},{"given":"Richard J.","family":"Dobson","sequence":"additional","affiliation":[]},{"given":"James T.","family":"Teo","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2023,4,12]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1877","DOI":"10.48550\/arXiv.2005.14165","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"B2","author":"Chowdhery","year":""},{"key":"B3","author":"Rae","year":""},{"key":"B4","author":"Hoffmann","year":""},{"key":"B5","doi-asserted-by":"publisher","first-page":"543405","DOI":"10.3389\/frai.2020.543405","article-title":"A comparison of artificial intelligence and human doctors for the purpose of triage and diagnosis","volume":"3","author":"Baker","year":"2020","journal-title":"Front Artif Intell"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1706.03762","article-title":"Attention is all you need","author":"Vaswani","year":"","journal-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS'17)"},{"key":"B7","author":"Taylor","year":""},{"key":"B8","year":""},{"key":"B9","author":"Singhal","year":""},{"key":"B10","author":"Li\u00e9vin","year":""},{"key":"B11","year":""},{"key":"B12","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1126\/science.aal4230","article-title":"Semantics derived automatically from language corpora contain human-like biases","volume":"356","author":"Caliskan","year":"2017","journal-title":"Science"},{"key":"B13","doi-asserted-by":"publisher","first-page":"7155","DOI":"10.1038\/s41598-020-62922-y","article-title":"BEHRT: transformer for electronic health records","volume":"10","author":"Li","year":"2020","journal-title":"Sci Rep"},{"key":"B14","first-page":"248","article-title":"MedMCQA: a large-scale multi-subject multi-choice dataset for medical domain question answering","volume":"174","author":"Pal","year":"2022","journal-title":"Proc Mach Learn Res"},{"key":"B15","doi-asserted-by":"publisher","first-page":"6421","DOI":"10.3390\/APP11146421","article-title":"What disease does this patient have? A large-scale open domain question answering dataset from medical exams","volume":"11","author":"Jin","year":"2021","journal-title":"Appl Sci"},{"key":"B16","first-page":"2567","author":"Jin","year":""},{"key":"B17","doi-asserted-by":"publisher","first-page":"104274","DOI":"10.1016\/J.JBI.2022.104274","article-title":"Benchmark datasets driving artificial intelligence development fail to capture the needs of medical professionals","volume":"137","author":"Blagec","year":"2023","journal-title":"J Biomed Inform"},{"key":"B18","author":"Kraljevic","year":""},{"key":"B19","author":"Weidinger","year":""},{"key":"B20","author":"Huang","year":""},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1371\/JOURNAL.PONE.0159224","article-title":"Racial-Ethnic disparities in opioid prescriptions at emergency department visits for conditions commonly associated with prescription drug abuse","volume":"11","author":"Singhal","year":"2016","journal-title":"PLoS One"},{"key":"B22","author":"Maynez","year":""},{"key":"B23","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1016\/J.CHB.2011.09.006","article-title":"Anthropomorphism of computers: is it mindful or mindless?","volume":"28","author":"Kim","year":"2012","journal-title":"Comput Human Behav"}],"container-title":["Frontiers in Digital Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2023.1161098\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,12]],"date-time":"2023-04-12T01:41:46Z","timestamp":1681263706000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2023.1161098\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,12]]},"references-count":23,"alternative-id":["10.3389\/fdgth.2023.1161098"],"URL":"https:\/\/doi.org\/10.3389\/fdgth.2023.1161098","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2023.03.02.23286705","asserted-by":"object"}]},"ISSN":["2673-253X"],"issn-type":[{"value":"2673-253X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,12]]},"article-number":"1161098"}}