{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T00:36:08Z","timestamp":1783470968710,"version":"3.55.0"},"reference-count":62,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T00:00:00Z","timestamp":1729209600000},"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. Comput. Sci."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>Effective delivery of healthcare depends on timely and accurate triage decisions, directing patients to appropriate care pathways and reducing unnecessary visits. Artificial Intelligence (AI) solutions, particularly those based on Large Language Models (LLMs), may enable non-experts to make better triage decisions at home, thus easing the healthcare system's load. We investigate how LLM-powered conversational agents influence non-experts in making triage decisions, further studying different persona profiles embedded via prompting.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>We designed a randomized experiment where participants first assessed patient symptom vignettes independently, then consulted one of the two agent profiles\u2014rational or empathic\u2014for advice, and finally revised their triage ratings. We used linear models to quantify the effect of the agent profile and confidence on the weight of advice. We examined changes in confidence and accuracy of triage decisions, along with participants' perceptions of the agents.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>In a study with 49 layperson participants, we found that persona profiles can be differentiated in LLM-powered conversational agents. However, these profiles did not significantly affect the weight of advice. Notably, less confident participants were more influenced by LLM advice, leading to larger adjustments to initial decisions. AI guidance improved alignment with correct triage levels and boosted confidence in participants' decisions.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>While LLM advice improves triage recommendations accuracy, confidence plays an important role in its adoption. Our findings raise design considerations for human-AI interfaces, highlighting two key aspects: encouraging appropriate alignment with LLMs' advice and ensuring that people are not easily swayed in situations of uncertainty.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fcomp.2024.1427463","type":"journal-article","created":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T04:44:51Z","timestamp":1729226691000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":14,"title":["How large language model-powered conversational agents influence decision making in domestic medical triage contexts"],"prefix":"10.3389","volume":"6","author":[{"given":"Catalina","family":"Gomez","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junjie","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chien-Ming","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mathias","family":"Unberath","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2024,10,18]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"589","DOI":"10.1001\/jamainternmed.2023.1838","article-title":"Comparing physician and artificial intelligence chatbot responses to patient questions posted to a public social media forum","volume":"183","author":"Ayers","year":"2023","journal-title":"JAMA Int. Med"},{"key":"B2","doi-asserted-by":"publisher","first-page":"16492","DOI":"10.1038\/s41598-023-43436-9","article-title":"Comparing ChatGPT and GPT-4 performance in usmle soft skill assessments","volume":"13","author":"Brin","year":"2023","journal-title":"Sci. Rep"},{"key":"B3","article-title":"\u201cLanguage models are few-shot learners,\u201d","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems, NIPS '20","author":"Brown","year":"2020"},{"key":"B4","author":"Cohen","year":"1988","journal-title":"Statistical Power Analysis for the Behavioral Sciences"},{"key":"B5","doi-asserted-by":"crossref","first-page":"206","DOI":"10.1145\/3442381.3450140","article-title":"\u201cSearch engines vs. symptom checkers: A comparison of their effectiveness for online health advice,\u201d","volume-title":"Proceedings of the Web Conference 2021, WWW '21","author":"Cross","year":"2021"},{"key":"B6","first-page":"1","article-title":"\u201cThe illusion of empathy? notes on displays of emotion in human-computer interaction,\u201d","volume-title":"Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems, CHI '24","author":"Cuadra","year":"2024"},{"key":"B7","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1207\/s15327906mbr1602_2","article-title":"Factors in the natural language of personality: re-analysis, comparison, and interpretation of six major studies","volume":"16","author":"Digman","year":"1981","journal-title":"Multivariate Behav. Res"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1902.09022","article-title":"Designing for health chatbots","author":"Fadhil","year":"2019","journal-title":"arXiv"},{"key":"B9","doi-asserted-by":"publisher","first-page":"e19928","DOI":"10.2196\/19928","article-title":"Utilization of self-diagnosis health chatbots in real-world settings: case study","volume":"23","author":"Fan","year":"2021","journal-title":"J. Med. Int. Res"},{"key":"B10","first-page":"1","article-title":"\u201cThe effects of warmth and competence perceptions on users' choice of an AI system,\u201d","volume-title":"Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems, CHI '21","author":"Gilad","year":"2021"},{"key":"B11","first-page":"141","article-title":"Language and individual differences: the search for universals in personality lexicons","volume":"2","author":"Goldberg","year":"1981","journal-title":"Rev. Person. Soc. Psychol"},{"key":"B12","doi-asserted-by":"publisher","first-page":"3531","DOI":"10.1145\/3485447.3512248","article-title":"To trust or not to trust: How a conversational interface affects trust in a decision support system","volume":"2022","author":"Gupta","year":"2022","journal-title":"Proc. ACM Web Conf"},{"key":"B13","doi-asserted-by":"publisher","first-page":"pkad010","DOI":"10.1093\/jncics\/pkad010","article-title":"Artificial intelligence chatbots will revolutionize how cancer patients access information: ChatGPT represents a paradigm-shift","volume":"7","author":"Hopkins","year":"2023","journal-title":"JNCI Cancer Spect"},{"key":"B14","doi-asserted-by":"publisher","first-page":"102839","DOI":"10.1016\/j.ijhcs.2022.102839","article-title":"Who needs explanation and when? Juggling explainable ai and user epistemic uncertainty","volume":"165","author":"Jiang","year":"2022","journal-title":"Int. J. Hum. Comp. Stud"},{"key":"B15","first-page":"1","article-title":"\u201cUnderstanding the benefits and challenges of deploying conversational ai leveraging large language models for public health intervention,\u201d","volume-title":"Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems, CHI '23","author":"Jo","year":"2023"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1101\/2023.09.12.23295399","article-title":"Testing the limits of language models: a conversational framework for medical AI assessment","author":"Johri","year":"2023","journal-title":"medRxiv"},{"key":"B17","doi-asserted-by":"publisher","first-page":"19","DOI":"10.15388\/Amed.2023.30.1.2","article-title":"Support systems of clinical decisions in the triage of the emergency department using artificial intelligence: the efficiency to support triage","volume":"30","author":"Karlafti","year":"2023","journal-title":"Acta Med. Lituanica"},{"key":"B18","first-page":"101","article-title":"\u201cDevelopment and evaluation of search tasks for iir experiments using a cognitive complexity framework,\u201d","volume-title":"Proceedings of the 2015 International Conference on the Theory of Information Retrieval, ICTIR '15","author":"Kelly","year":"2015"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1222","DOI":"10.1126\/science.adi0248","article-title":"How ai can distort human beliefs","volume":"380","author":"Kidd","year":"2023","journal-title":"Science"},{"key":"B20","article-title":"\u201cLarge language models are zeroshot reasoners,\u201d","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems, NIPS '22","author":"Kojima","year":"2024"},{"key":"B21","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1007\/978-3-319-96074-6_2","article-title":"\u201cTheoretical considerations and development of a questionnaire to measure trust in automation,\u201d","volume-title":"Proceedings of the 20th Congress of the International Ergonomics Association (IEA 2018) Volume VI: Transport Ergonomics and Human Factors (TEHF), Aerospace Human Factors and Ergonomics 20","author":"K\u00f6rber","year":"2019"},{"key":"B22","first-page":"31","article-title":"\u201cReceptionist or information kiosk: how do people talk with a robot?,\u201d","volume-title":"Proceedings of the 2010 ACM conference on Computer Supported Cooperative Work, CSCW '10","author":"Lee","year":"2010"},{"key":"B23","doi-asserted-by":"publisher","first-page":"1233","DOI":"10.1056\/NEJMsr2214184","article-title":"Benefits, limits, and risks of gpt-4 as an ai chatbot for medicine","volume":"388","author":"Lee","year":"2023","journal-title":"New Engl. J. Med"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1771","DOI":"10.1002\/asi.21359","article-title":"An exploration of the relationships between work task and interactive information search behavior","volume":"61","author":"Li","year":"2010","journal-title":"J. Am. Soc. Inf. Sci. Technol"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2312.00164","article-title":"Towards accurate differential diagnosis with large language models","author":"McDuff","year":"2023","journal-title":"arXiv"},{"key":"B26","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1016\/j.eswa.2019.03.054","article-title":"Survey of conversational agents in health","volume":"129","author":"Montenegro","year":"2019","journal-title":"Exp. Syst. Appl"},{"key":"B27","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1609\/hcomp.v8i1.7469","article-title":"\u201cThe role of domain expertise in user trust and the impact of first impressions with intelligent systems,\u201d","author":"Nourani","year":"2020","journal-title":"Proceedings of the AAAI Conference on Human Computation and Crowdsourcing, Volume 8"},{"key":"B28","doi-asserted-by":"publisher","first-page":"e200024","DOI":"10.1148\/ryai.2020200024","article-title":"Active reprioritization of the reading worklist using artificial intelligence has a beneficial effect on the turnaround time for interpretation of head CT with intracranial hemorrhage","volume":"3","author":"O'neill","year":"2020","journal-title":"Radiology"},{"key":"B29","doi-asserted-by":"crossref","DOI":"10.1145\/3491102.3502104","article-title":"\u201cUnderstanding the impact of explanations on advice-taking: a user study for ai-based clinical decision support systems,\u201d","volume-title":"Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems, CHI '22","author":"Panigutti","year":"2022"},{"key":"B30","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1177\/1088868314538548","article-title":"Personality traits and personal values: a meta-analysis","volume":"19","author":"Parks-Leduc","year":"2015","journal-title":"Person. Soc. Psychol. Rev"},{"key":"B31","unstructured":"\u201cUnderstanding and predicting empathic behavior in counseling therapy,\u201d14261435\n            P\u00e9rez-RosasV.\n            MihalceaR.\n            ResnicowK.\n            SinghS.\n            AnL.\n          Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)2017"},{"key":"B32","first-page":"1","article-title":"\u201cReimagining the covid-19 digital experience: the value of user empowerment and accessibility in risk communication,\u201d","volume-title":"Proceedings of the 38th ACM International Conference on Design of Communication, SIGDOC '20","author":"Ponnada","year":"2020"},{"key":"B33","first-page":"4279","article-title":"\u201cAssigning personality\/profile to a chatting machine for coherent conversation generation,\u201d","volume-title":"Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI '18","author":"Qian","year":"2018"},{"key":"B34","doi-asserted-by":"publisher","first-page":"4825","DOI":"10.1007\/s00330-019-06186-9","article-title":"Can we reduce the workload of mammographic screening by automatic identification of normal exams with artificial intelligence? A feasibility study","volume":"29","author":"Rodriguez-Ruiz","year":"2019","journal-title":"Eur. Radiol"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.21203\/rs.3.rs-3296728\/v1","article-title":"Personality traits in large language models","author":"Safdari","year":"2023","journal-title":"arXiv"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2211.05100","article-title":"Bloom: a 176b-parameter open-access multilingual language model","author":"Scao","year":"2022","journal-title":"arXiv"},{"key":"B37","doi-asserted-by":"publisher","first-page":"h3480","DOI":"10.1136\/bmj.h3480","article-title":"Evaluation of symptom checkers for self diagnosis and triage: audit study","volume":"351","author":"Semigran","year":"2015","journal-title":"BMJ"},{"key":"B38","doi-asserted-by":"publisher","first-page":"e47564","DOI":"10.2196\/47564","article-title":"User intentions to use chatgpt for self-diagnosis and health-related purposes: cross-sectional survey study","volume":"10","author":"Shahsavar","year":"2023","journal-title":"JMIR Hum. Fact"},{"key":"B39","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1038\/s42256-022-00593-2","article-title":"Human-AI collaboration enables more empathic conversations in text-based peer-to-peer mental health support","volume":"5","author":"Sharma","year":"2023","journal-title":"Nat. Mach. Intell"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.425","article-title":"A computational approach to understanding empathy expressed in text-based mental health support","author":"Sharma","year":"","journal-title":"arXiv"},{"key":"B41","unstructured":"\u201cA computational approach to understanding empathy expressed in text-based mental health support,\u201d52635276\n            SharmaA.\n            MinerA. S.\n            AtkinsD. C.\n            AlthoffT.\n          Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)"},{"key":"B42","first-page":"1","article-title":"\u201cNo explainability without accountability: an empirical study of explanations and feedback in interactive ML,\u201d","volume-title":"Proceedings of the 2020 Chi Conference on Human Factors in Computing Systems, CHI '20","author":"Smith-Renner","year":"2020"},{"key":"B43","doi-asserted-by":"publisher","first-page":"396","DOI":"10.1016\/j.jen.2015.02.003","article-title":"Clinical decision making in triage: an integrative review","volume":"41","author":"Stanfield","year":"2015","journal-title":"J. Emerg. Nurs"},{"key":"B44","first-page":"1","article-title":"\u201cExploring the effects of interactive dialogue in improving user control for explainable online symptom checkers,\u201d","volume-title":"Extended Abstracts of the 2022 CHI Conference on Human Factors in Computing Systems, CHI EA '22","author":"Sun","year":"2022"},{"key":"B45","doi-asserted-by":"publisher","first-page":"491","DOI":"10.1007\/s42113-022-00157-y","article-title":"AI-assisted decision-making: a cognitive modeling approach to infer latent reliance strategies","volume":"5","author":"Tejeda","year":"2022","journal-title":"Comp. Brain Behav"},{"key":"B46","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40991-016-0003-7","article-title":"Corporate social responsibility research: the importance of context","volume":"1","author":"Tilt","year":"2016","journal-title":"Int. J. Corp. Soc. Respons"},{"key":"B47","doi-asserted-by":"publisher","first-page":"1337","DOI":"10.1038\/s41591-018-0147-y","article-title":"Automated deep-neural-network surveillance of cranial images for acute neurologic events","volume":"24","author":"Titano","year":"2018","journal-title":"Nat. Med"},{"key":"B48","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1038\/s41591-018-0300-7","article-title":"High-performance medicine: the convergence of human and artificial intelligence","volume":"25","author":"Topol","year":"2019","journal-title":"Nat. Med"},{"key":"B49","volume-title":"Controllability and Explainability in a Hybrid Social Recommender System","author":"Tsai","year":"2019"},{"key":"B50","first-page":"1","article-title":"\u201cExploring and promoting diagnostic transparency and explainability in online symptom checkers,\u201d","volume-title":"Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems, CHI '21","author":"Tsai","year":"2021"},{"key":"B51","doi-asserted-by":"publisher","first-page":"fdad005","DOI":"10.1093\/pubmed\/fdad005","article-title":"Intelligent decision support in medical triage: are people robust to biased advice?","volume":"45","author":"van der Stigchel","year":"2023","journal-title":"J. Public Health"},{"key":"B52","first-page":"763","article-title":"\u201cDo humans trust advice more if it comes from AI? An analysis of human-AI interactions,\u201d","volume-title":"Proceedings of the 2022 AAAI\/ACM Conference on AI, Ethics, and Society, AIES '22","author":"Vodrahalli","year":"2022"},{"key":"B53","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3637364","article-title":"Leveraging large language models to power chatbots for collecting user self-reported data","volume":"8","author":"Wei","year":"","journal-title":"Proceedings of the ACM on Human-Computer Interaction"},{"key":"B54","article-title":"\u201cChain-of-thought prompting elicits reasoning in large language models,\u201d","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems, NIPS '22","author":"Wei","year":""},{"key":"B55","first-page":"2","article-title":"\u201cPowering an ai chatbot with expert sourcing to support credible health information access,\u201d","volume-title":"Proceedings of the 28th International Conference on Intelligent User Interfaces, IUI '23","author":"Xiao","year":"2023"},{"key":"B56","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1002\/(SICI)1099-0771(199703)10:1<21::AID-BDM243>3.0.CO;2-G","article-title":"Precision and accuracy of judgmental estimation","volume":"10","author":"Yaniv","year":"1997","journal-title":"J. Behav. Decis. Mak"},{"key":"B57","first-page":"1","article-title":"\u201cUnderstanding the effect of accuracy on trust in machine learning models,\u201d","volume-title":"Proceedings of the 2019 Chi Conference on Human Factors in Computing Systems, CHI '19","author":"Yin","year":"2019"},{"key":"B58","doi-asserted-by":"publisher","DOI":"10.1145\/3589959","article-title":"Beyond self-diagnosis: how a chatbot-based symptom checker should respond","author":"You","year":"2023","journal-title":"ACM Trans. Comput. Hum. Interact"},{"key":"B59","article-title":"\u201cRevisiting out-of-distribution robustness in NLP: benchmark, analysis, and LLMS evaluations,\u201d","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems, NIPS '23","author":"Yuan","year":"2024"},{"key":"B60","doi-asserted-by":"publisher","first-page":"610","DOI":"10.1002\/mar.21445","article-title":"Behavioral and neural evidence on consumer responses to human doctors and medical artificial intelligence","volume":"38","author":"Yun","year":"2021","journal-title":"Psychol. Market"},{"key":"B61","doi-asserted-by":"publisher","first-page":"AIoa2300068","DOI":"10.1056\/AIoa2300068","article-title":"Almanac\u2014retrieval-augmented language models for clinical medicine","volume":"1","author":"Zakka","year":"2024","journal-title":"NEJM AI"},{"key":"B62","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2302.13793","article-title":"Dr ChatGPT, tell me what i want to hear: how prompt knowledge impacts health answer correctness","author":"Zuccon","year":"2023","journal-title":"arXiv"}],"container-title":["Frontiers in Computer Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcomp.2024.1427463\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T04:45:04Z","timestamp":1729226704000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcomp.2024.1427463\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,18]]},"references-count":62,"alternative-id":["10.3389\/fcomp.2024.1427463"],"URL":"https:\/\/doi.org\/10.3389\/fcomp.2024.1427463","relation":{},"ISSN":["2624-9898"],"issn-type":[{"value":"2624-9898","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,18]]},"article-number":"1427463"}}