{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T16:25:54Z","timestamp":1790353554028,"version":"4.1.0"},"reference-count":126,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Med Internet Res"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec sec-type=\"background\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Large language models (LLMs) are increasingly embedded in conversational agents for cardiometabolic care. These systems could support self-management, but their behavior change content, delivery mechanisms, and implementation transparency are poorly understood.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"objective\">\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This scoping review mapped behavior change techniques (BCTs) used in LLM-driven conversational agents for cardiometabolic prevention and management, described how these techniques are delivered across static, rule-based, and generative mechanisms, examined LLM design, personalization, and safety reporting, and summarized user experience and behavioral or clinical outcomes.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"methods\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We searched PubMed, Web of Science, Embase, CINAHL, APA PsycInfo, IEEE Xplore, ACM Digital Library, arXiv, ClinicalTrials.gov, and the WHO International Clinical Trials Registry Platform for records published from January 1, 2020, to November 30, 2025. The final search was run on March 25, 2026, using this publication-date limit. Eligible studies reported a patient-facing text- or voice-based cardiometabolic conversational agent using an LLM or other transformer-based generative model. Two reviewers independently screened records and extracted data. BCTs were coded using the Behavior Change Technique Taxonomy v1; selected self-management BCTs were classified as static, rule-based or templated, or generative or context-aware. Empirical human-participant\u2013 or evaluator-based studies were appraised with the Mixed Methods Appraisal Tool, and a study-specific checklist assessed LLM implementation reporting transparency.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"results\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Thirty-eight studies were included; 19 involved empirical human-participant\u2013 or evaluator-based assessments, whereas 19 were technical and system-level evaluations, including framework-development, simulated-output, and proof-of-concept studies. Studies were concentrated in 2024\u20102025. Instruction on how to perform behavior was identified in 30 of 38 (79%) studies, information about health consequences in 27 of 38 (71%) studies, and feedback and monitoring techniques in 19 of 38 (50%) studies. Most agents were positioned as educators or coaches targeting type 2 diabetes, obesity, or related cardiometabolic risk, and GPT-family models embedded in hybrid architectures with retrieval-augmented generation or rule-based components predominated. Generative outputs were used mainly for tailored explanations, risk information, and socioemotional responses, whereas self-monitoring, reminders, and structured interactions were more often rule-based or mixed-mode. Only 13 of 38 (34%) studies fully reported prompts or system messages, and 16 of 38 (42%) studies fully reported safety or oversight mechanisms. User evaluations reported good usability and perceived helpfulness, but behavioral or physiological outcomes were sparse and usually limited to pilot, short-term, or single-case designs.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"conclusions\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>LLM-driven conversational agents for cardiometabolic care are proliferating but remain early-stage and methodologically heterogeneous. Current systems primarily use LLMs as educational and explanatory layers with \u201csynthetic empathy\u201d over rule-based data capture and safety functions, while behavior change content remains dominated by information provision and simple feedback. More rigorous comparative studies with longer follow-up are needed before firm conclusions can be drawn about sustained behavioral or clinical benefit.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.2196\/89190","type":"journal-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:52:17Z","timestamp":1784141537000},"page":"e89190-e89190","source":"Crossref","is-referenced-by-count":2,"title":["Behavior Change Content and Implementation of Large Language Model\u2013Driven Conversational Agents in Cardiometabolic Care: Scoping Review"],"prefix":"10.2196","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-0461-1913","authenticated-orcid":false,"given":"Yuhan","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2861-3023","authenticated-orcid":false,"given":"Rongrong","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6084-3662","authenticated-orcid":false,"given":"Yiqun","family":"Miao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1198-3877","authenticated-orcid":false,"given":"Yuan","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7708-3356","authenticated-orcid":false,"given":"Huiying","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8633-5404","authenticated-orcid":false,"given":"Ying","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,7,15]]},"reference":[{"issue":"6","key":"R1","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1093\/qjmed\/hcaf022","article-title":"Global burden of cardiovascular diseases and its risk factors, 1990-2021: a systematic analysis for the Global Burden of Disease Study 2021","volume":"118","author":"Tan","journal-title":"QJM"},{"issue":"9","key":"R2","doi-asserted-by":"publisher","first-page":"2739","DOI":"10.1007\/s11427-025-2948-y","article-title":"Global burden of atherosclerotic cardiovascular disease attributed to lifestyle and metabolic risks","volume":"68","author":"Xu","journal-title":"Sci China Life Sci"},{"issue":"7","key":"R3","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.42616","article-title":"Impact of lifestyle modifications on cardiovascular health: a narrative review","volume":"15","author":"Ghodeshwar","journal-title":"Cureus"},{"issue":"1 Suppl 1","key":"R4","doi-asserted-by":"publisher","first-page":"S86","DOI":"10.2337\/dc25-S005","article-title":"5. Facilitating positive health behaviors and well-being to improve health outcomes: standards of care in diabetes-2025","volume":"48","author":"American Diabetes Association Professional Practice Committee","journal-title":"Diabetes Care"},{"issue":"1","key":"R5","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1007\/s11332-023-01118-z","article-title":"Lifestyle modifications for preventing and managing cardiovascular diseases","volume":"20","author":"Samuel","journal-title":"Sport Sci Health"},{"issue":"3","key":"R6","first-page":"10737","volume":"13","author":"Patil","journal-title":"Front Health Inform"},{"key":"R7","doi-asserted-by":"publisher","DOI":"10.2196\/53576","article-title":"Current implementation of digital health in chronic disease management: scoping review","volume":"26","author":"Pong","journal-title":"J Med Internet Res"},{"key":"R8","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2024.1506641","article-title":"Application of artificial intelligence in the health management of chronic disease: bibliometric analysis","volume":"11","author":"Pan","journal-title":"Front Med (Lausanne)"},{"issue":"1","key":"R9","doi-asserted-by":"publisher","DOI":"10.1080\/07853890.2024.2302980","article-title":"A systematic review of artificial intelligence-powered (AI-powered) chatbot intervention for managing chronic illness","volume":"56","author":"Kurniawan","journal-title":"Ann Med"},{"key":"R10","doi-asserted-by":"publisher","DOI":"10.2196\/72309","article-title":"Conversational agents supporting self-management in people with a chronic disease: systematic review","volume":"27","author":"Peerbolte","journal-title":"J Med Internet Res"},{"issue":"11","key":"R11","doi-asserted-by":"publisher","DOI":"10.2196\/38525","article-title":"Design and evaluation challenges of conversational agents in health care and well-being: selective review study","volume":"24","author":"Kocaballi","journal-title":"J Med Internet Res"},{"issue":"1","key":"R12","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-023-00988-4","article-title":"Generative AI and large language models in health care: pathways to implementation","volume":"7","author":"Raza","journal-title":"NPJ Digit Med"},{"issue":"3","key":"R13","doi-asserted-by":"publisher","first-page":"57","DOI":"10.3390\/informatics11030057","article-title":"Large language models in healthcare and medical domain: a review","volume":"11","author":"Nazi","journal-title":"Informatics"},{"issue":"4","key":"R14","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1002\/hcs2.61","article-title":"Large language models in health care: development, applications, and challenges","volume":"2","author":"Yang","journal-title":"Health Care Sci"},{"issue":"8","key":"R15","doi-asserted-by":"publisher","first-page":"1930","DOI":"10.1038\/s41591-023-02448-8","article-title":"Large language models in medicine","volume":"29","author":"Thirunavukarasu","journal-title":"Nat Med"},{"issue":"10377","key":"R16","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(23)00216-7","article-title":"The promise of large language models in health care","volume":"401","author":"Arora","journal-title":"Lancet"},{"issue":"1","key":"R17","doi-asserted-by":"publisher","DOI":"10.1186\/s12967-023-04354-6","article-title":"Evaluate the accuracy of ChatGPT\u2019s responses to diabetes questions and misconceptions","volume":"21","author":"Huang","journal-title":"J Transl Med"},{"issue":"9","key":"R18","doi-asserted-by":"publisher","DOI":"10.1007\/s13410-024-01401-w","article-title":"Evaluating the accuracy and adequacy of ChatGPT in responding to queries of diabetes patients in primary healthcare","volume":"45","author":"\u015eenoymak","journal-title":"Int J Diabetes Dev Ctries"},{"issue":"5","key":"R19","doi-asserted-by":"publisher","first-page":"e103","DOI":"10.2337\/dc23-0197","article-title":"Potential and pitfalls of ChatGPT and natural-language artificial intelligence models for diabetes education","volume":"46","author":"Sng","journal-title":"Diabetes Care"},{"issue":"9","key":"R20","doi-asserted-by":"publisher","first-page":"e662","DOI":"10.1016\/S2589-7500(24)00124-9","article-title":"A future role for health applications of large language models depends on regulators enforcing safety standards","volume":"6","author":"Freyer","journal-title":"Lancet Digit Health"},{"issue":"4","key":"R21","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1001\/jama.2024.21700","article-title":"Testing and evaluation of health care applications of large language models: a systematic review","volume":"333","author":"Bedi","journal-title":"JAMA"},{"issue":"1","key":"R22","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1007\/s12160-013-9486-6","article-title":"The behavior change technique taxonomy (v1) of 93 hierarchically clustered techniques: building an international consensus for the reporting of behavior change interventions","volume":"46","author":"Michie","journal-title":"Ann Behav Med"},{"key":"R23","doi-asserted-by":"publisher","DOI":"10.12688\/wellcomeopenres.18002.2","article-title":"Behaviour change techniques taxonomy v1: feedback to inform the development of an ontology","volume":"7","author":"Corker","journal-title":"Wellcome Open Res"},{"key":"R24","doi-asserted-by":"publisher","DOI":"10.1177\/20552076241277693","article-title":"Exploring the characteristics of conversational agents in chronic disease management interventions: a scoping review","volume":"10","author":"Uetova","journal-title":"Digit Health"},{"key":"R25","doi-asserted-by":"crossref","unstructured":"Islam J Hasan M Hasan MM . A systematic review of chatbot-enabled chronic disease management interventions and mhealth. TechRxiv. Preprint posted online on Oct 2, 2023. [doi: 10.36227\/techrxiv.22815275.v2]","DOI":"10.36227\/techrxiv.22815275"},{"issue":"20","key":"R26","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare11202776","article-title":"Leveraging generative AI and large language models: a comprehensive roadmap for healthcare integration","volume":"11","author":"Yu","journal-title":"Healthcare (Basel)"},{"issue":"1","key":"R27","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1080\/1364557032000119616","article-title":"Scoping studies: towards a methodological framework","volume":"8","author":"Arksey","journal-title":"Int J Soc Res Methodol"},{"key":"R28","doi-asserted-by":"publisher","DOI":"10.1186\/1748-5908-5-69","article-title":"Scoping studies: advancing the methodology","volume":"5","author":"Levac","journal-title":"Implement Sci"},{"issue":"7","key":"R29","doi-asserted-by":"publisher","first-page":"467","DOI":"10.7326\/M18-0850","article-title":"PRISMA Extension for Scoping Reviews (PRISMA-ScR): checklist and explanation","volume":"169","author":"Tricco","journal-title":"Ann Intern Med"},{"issue":"4","key":"R30","doi-asserted-by":"publisher","first-page":"285","DOI":"10.3233\/EFI-180221","article-title":"The Mixed Methods Appraisal Tool (MMAT) version 2018 for information professionals and researchers","volume":"34","author":"Hong","journal-title":"EFI"},{"key":"R31","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.m3164","article-title":"Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: the CONSORT-AI Extension","volume":"370","author":"Liu","journal-title":"BMJ"},{"key":"R32","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.m3210","article-title":"Guidelines for clinical trial protocols for interventions involving artificial intelligence: the SPIRIT-AI extension","volume":"370","author":"Rivera","journal-title":"BMJ"},{"key":"R33","unstructured":"Measures for ethical review of life science and medical research involving humans. National Health Commission of the People\u2019s Republic of China (NHC). 2023. URL: https:\/\/www.nhc.gov.cn\/qjjys\/c100016\/202302\/6b6e447b3edc4338856c9a652a85f44b.shtml [Accessed 26-06-2026]"},{"key":"R34","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC53108.2024.10781547","article-title":"Knowledge-infused LLM-powered conversational health agent: a case study for diabetes patients","volume":"2024","author":"Abbasian","journal-title":"Annu Int Conf IEEE Eng Med Biol Soc"},{"issue":"1","key":"R35","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-025-02297-7","article-title":"RAG-enhanced open SLMs for hypertension management chatbots","volume":"49","author":"Aguzzi","journal-title":"J Med Syst"},{"key":"R36","unstructured":"Ahmadi S Rockwell M Stuart M et al. AI-facilitated episodic future thinking for adults with obesity. arXiv. Preprint posted online on Jun 23, 2025. [doi: 10.48550\/arXiv.2503.16484]"},{"key":"R37","doi-asserted-by":"publisher","DOI":"10.3233\/SHTI240565","article-title":"Bridging gaps with generative AI: enhancing hypertension monitoring through patient and provider insights","volume":"316","author":"Andreadis","journal-title":"Stud Health Technol Inform"},{"key":"R38","doi-asserted-by":"crossref","unstructured":"Antia SE Ugwu CN Ghodka V et al. Healthy heart assistant, a WhatsApp-based generative pre-trained transformer (GPT) technology, for self-care in hypertensive patients: a feasibility study. SSRN. Preprint posted online on Dec 17, 2024. [doi: 10.2139\/ssrn.5058475]","DOI":"10.2139\/ssrn.5058475"},{"issue":"7","key":"R39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3757517","article-title":"Understanding how chatbot phrasing styles and care demonstration influence overweight users\u2019 adherence intention towards chatbots supporting weight management","volume":"9","author":"Cheng","journal-title":"Proc ACM Hum-Comput Interact"},{"issue":"3-4","key":"R40","doi-asserted-by":"publisher","first-page":"567","DOI":"10.1007\/s11036-025-02472-7","article-title":"Generative-AI based health advisory system for patients with chronic diseases","volume":"30","author":"Chuang","journal-title":"Mobile Netw Appl"},{"key":"R41","doi-asserted-by":"publisher","DOI":"10.2196\/63503","article-title":"\u201cDigital clinicians\u201d performing obesity medication self-injection education: feasibility randomized controlled trial","volume":"10","author":"Coleman","journal-title":"JMIR Diabetes"},{"key":"R42","doi-asserted-by":"publisher","DOI":"10.1145\/3643479.3662049","article-title":"LLM-powered multimodal AI conversations for diabetes prevention","author":"Dao","journal-title":"ACM"},{"key":"R43","doi-asserted-by":"crossref","unstructured":"\u0110urkovi\u0107 J Stojanovi\u0107 R \u0160kraba A Vukmirovi\u0107 M Babi\u0107 B Miranovi\u0107 V . Cardiac rhythm monitoring with ChatGPT Integration. Presented at: 2025 14th Mediterranean Conference on Embedded Computing (MECO); Jun 10-14, 2025:1-4; Budva, Montenegro. [doi: 10.1109\/MECO66322.2025.11049165]","DOI":"10.1109\/MECO66322.2025.11049165"},{"key":"R44","doi-asserted-by":"crossref","unstructured":"Elfayoumi M AbouElazm M Mohamed O Abuhmed T El-Sappagh SHA . Knowledge augmented significant language model-based chatbot for explainable diabetes mellitus prediction. Presented at: 2025 19th International Conference on Ubiquitous Information Management and Communication (IMCOM); Jan 3-5, 2025:1-8; Bangkok, Thailand. [doi: 10.1109\/IMCOM64595.2025.10857525]","DOI":"10.1109\/IMCOM64595.2025.10857525"},{"key":"R45","unstructured":"Gollapalli SD Ng SK . PIRsuader: a persuasive chatbot for mitigating psychological insulin resistance in type-2 diabetic patients. Presented at: Proceedings of the 31st International Conference on Computational Linguistics; Jan 19-24, 2025; Abu Dhabi, UAE. URL: https:\/\/aclanthology.org\/2025.coling-main.401\/ [Accessed 02-07-2026]"},{"issue":"4","key":"R46","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1007\/s41347-025-00491-5","article-title":"Comparing large language model AI and human-generated coaching messages for behavioral weight loss","volume":"10","author":"Huang","journal-title":"J Technol Behav Sci"},{"key":"R47","unstructured":"Hussain W Grundy J . Advice for diabetes self-management by ChatGPT models: challenges and recommendations. arXiv. Preprint posted online on Jan 14, 2025. [doi: 10.48550\/arXiv.2501.07931]"},{"key":"R48","doi-asserted-by":"publisher","DOI":"10.2196\/72553","article-title":"Generative AI chatbot for diabetes management: formative 2-part qualitative study using DTalksBot involving patients and clinicians","volume":"9","author":"Jeon","journal-title":"JMIR Form Res"},{"key":"R49","doi-asserted-by":"publisher","DOI":"10.2196\/70131","article-title":"The effectiveness of a custom AI chatbot for type 2 diabetes mellitus health literacy: development and evaluation study","volume":"27","author":"Kelly","journal-title":"J Med Internet Res"},{"key":"R50","doi-asserted-by":"crossref","unstructured":"Kozaily E Geagea M Akdogan ER et al. Accuracy and consistency of online chat-based artificial intelligence platforms in answering patients\u2019 questions about heart failure. medRxiv. Preprint posted online on Sep 14, 2023. [doi: 10.1101\/2023.09.12.23295452]","DOI":"10.1101\/2023.09.12.23295452"},{"key":"R51","doi-asserted-by":"crossref","unstructured":"Liang M Wang J Luo Y . SmartEats: investigating the effects of customizable conversational agent in dietary recommendations. Presented at: Proceedings of the 7th ACM Conference on Conversational User Interfaces (CUI \u201925); Jul 8-10, 2025:1-16; Waterloo, Ontario, Canada. [doi: 10.1145\/3719160.3736635]","DOI":"10.1145\/3719160.3736635"},{"key":"R52","unstructured":"Meng Y Chen R Liu B Guan Y Ding X . Between knowledge and care: evaluating generative AI-based IUI in type 2 diabetes management through patient and physician perspectives. arXiv. Preprint posted online on Oct 11, 2025. [doi: 10.48550\/arXiv.2510.10048]"},{"key":"R53","unstructured":"Meng Y Liu Z Qin X . Design and evaluation of an AI-driven personalized mobile app to provide multifaceted health support for type 2 diabetes patients in China. arXiv. Preprint posted online on Nov 17, 2025. [doi: 10.48550\/arXiv.2511.12952]"},{"key":"R54","doi-asserted-by":"crossref","unstructured":"Suraya Mohd Dan A Linoby A Kasim SS et al. Personalized AI prompt generator and ChatGPT for weight loss: randomized controlled trial in adults with overweight and obesity. medRxiv. Preprint posted online on Sep 8, 2025. [doi: 10.1101\/2025.09.07.25335255]","DOI":"10.1101\/2025.09.07.25335255"},{"key":"R55","doi-asserted-by":"crossref","unstructured":"Montagna S Ferretti S Klopfenstein LC Florio A Pengo MF . Data decentralisation of LLM-based chatbot systems in chronic disease self-management. Presented at: Proceedings of the 2023 ACM Conference on Information Technology for Social Good (GoodIT \u201923); Sep 6-8, 2023; Lisbon, Portugal. [doi: 10.1145\/3582515.3609536]","DOI":"10.1145\/3582515.3609536"},{"key":"R56","doi-asserted-by":"crossref","unstructured":"Mustafa G Ong J Shaikh MZ et al. Assessing large language model utility and limitations in diabetes education: a cross-sectional study of patient interactions and specialist evaluations. medRxiv. Preprint posted online on Jun 24, 2025. [doi: 10.1101\/2025.06.24.25329401]","DOI":"10.1101\/2025.06.24.25329401"},{"key":"R57","doi-asserted-by":"publisher","DOI":"10.3389\/fdgth.2025.1460236","article-title":"Think FAST: a novel framework to evaluate fidelity, accuracy, safety, and tone in conversational AI health coach dialogues","volume":"7","author":"Neary","journal-title":"Front Digit Health"},{"key":"R58","doi-asserted-by":"crossref","unstructured":"Pan DP Luo L Wang Y Hui P . CGM-led multimodal tracking with chatbot support: an autoethnography in sub-health. Presented at: 2025 International Conference on Human-Engaged Computing (ICHEC \u201925); Nov 21-23, 2025; Singapore. [doi: 10.1145\/3786995.3787067]","DOI":"10.1145\/3786995.3787067"},{"key":"R59","doi-asserted-by":"crossref","unstructured":"Patil M Patel VR Giraddi SG S T H S . MedBot: intelligent health care assistant for heart disease powered by large language models. Presented at: 2025 International Conference on Sensors and Related Networks (SENNET) Special Focus on Digital Healthcare; Jul 24-27, 2025; Vellore, India. [doi: 10.1109\/SENNET64220.2025.11135992]","DOI":"10.1109\/SENNET64220.2025.11135992"},{"issue":"1","key":"R60","doi-asserted-by":"publisher","first-page":"35","DOI":"10.5543\/tkda.2024.78131","article-title":"Comparative evaluation of chatbot responses on coronary artery disease","volume":"53","author":"Pay","journal-title":"Turk Kardiyol Dern Ars"},{"issue":"24","key":"R61","doi-asserted-by":"publisher","DOI":"10.3390\/jcm13247810","article-title":"Comparison of the accuracy, completeness, reproducibility, and consistency of different AI chatbots in providing nutritional advice: an exploratory study","volume":"13","author":"Ponzo","journal-title":"J Clin Med"},{"key":"R62","doi-asserted-by":"crossref","unstructured":"Rodriguez DV Andreadis K Chen J Gonzalez J Mann D . Development of a genai-powered hypertension management assistant: early development phases and architectural design. Presented at: 2024 IEEE 12th International Conference on Healthcare Informatics (ICHI); Jul 3-6, 2024; Orlando, FL. [doi: 10.1109\/ICHI61247.2024.00052]","DOI":"10.1109\/ICHI61247.2024.00052"},{"key":"R63","doi-asserted-by":"crossref","unstructured":"Rossi D Citarella AA De Marco F Di Biasi L Tortora G . Comparative analysis of diabetes diagnosis: WE-LSTM networks and wizardlm-powered diabetalk chatbot. Presented at: 2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM); Dec 3-6, 2024:6859-6866; Lisbon, Portugal. 2024.[doi: 10.1109\/BIBM62325.2024.10821742]","DOI":"10.1109\/BIBM62325.2024.10821742"},{"issue":"19","key":"R64","doi-asserted-by":"publisher","first-page":"12551","DOI":"10.1080\/10447318.2025.2462752","article-title":"Evaluating the potential role of AI chatbots in designing personalized exercise programs for weight management","volume":"41","author":"Sara\u00e7","journal-title":"Int J Hum Comput Interact"},{"key":"R65","doi-asserted-by":"crossref","unstructured":"Str\u00f6mel KR Henry S Johansson T Niess J Wo\u017aniak PW . Narrating fitness: leveraging large language models for reflective fitness tracker data interpretation. Presented at: Proceedings of the CHI Conference on Human Factors in Computing Systems (CHI \u201924); May 11-16, 2024; Honolulu, HI. 2024.[doi: 10.1145\/3613904.3642032]","DOI":"10.1145\/3613904.3642032"},{"key":"R66","doi-asserted-by":"crossref","unstructured":"Szymanski A Wimer BL Anuyah O Eicher-Miller HA Metoyer RA . Integrating expertise in LLMs: crafting a customized nutrition assistant with refined template instructions. Presented at: Proceedings of the CHI Conference on Human Factors in Computing Systems (CHI \u201924); May 11-16, 2024; Honolulu, HI. [doi: 10.1145\/3613904.3641924]","DOI":"10.1145\/3613904.3641924"},{"key":"R67","doi-asserted-by":"crossref","unstructured":"Tayal A Salunke D Eugenio BD et al. Conversational assistants to support heart failure patients: comparing a neurosymbolic architecture with ChatGPT. arXiv. Preprint posted online on Apr 24, 2025. [doi: 10.48550\/arXiv.2504.17753]","DOI":"10.63317\/4tng9rshvsna"},{"key":"R68","unstructured":"Tayal A Salunke D Di Eugenio B et al. Towards conversational assistants for health applications: using ChatGPT to generate conversations about heart failure. Presented at: Proceedings of the 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue; Aug 25-27, 2025; Avignon, France. URL: https:\/\/aclanthology.org\/2025.sigdial-1.43\/ [Accessed 22-06-2026]"},{"key":"R69","doi-asserted-by":"crossref","unstructured":"Vats S Sharma K Revathi M . AI-powered early diagnosis and personalized health recommendations for coronary artery disease (CAD) using predictive analytics. Presented at: 2025 International Conference on Computing Technologies & Data Communication (ICCTDC); Jul 4-5, 2025:1-6; Hassan, India. 2025.[doi: 10.1109\/ICCTDC64446.2025.11158896]","DOI":"10.1109\/ICCTDC64446.2025.11158896"},{"issue":"1","key":"R70","doi-asserted-by":"publisher","DOI":"10.1007\/s44337-024-00174-9","article-title":"A novel recommender framework with chatbot to stratify heart attack risk","volume":"1","author":"Wali","journal-title":"Discov Med (Singap)"},{"issue":"1","key":"R71","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1161\/HYPERTENSIONAHA.125.25305","article-title":"Large language model agent for managing patients with suspected hypertension","volume":"83","author":"Wang","journal-title":"Hypertension"},{"key":"R72","doi-asserted-by":"publisher","DOI":"10.2196\/66905","article-title":"Using large language models for chronic disease management tasks: scoping review","volume":"13","author":"Serugunda","journal-title":"JMIR Med Inform"},{"issue":"3","key":"R73","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.81001","article-title":"Artificial intelligence-based chatbots in chronic disease management: a systematic review of applications and challenges","volume":"17","author":"Altom","journal-title":"Cureus"},{"issue":"1","key":"R74","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-025-02236-6","article-title":"Smartphone-based digital health interventions: a comprehensive systematic review of efficacy for cardiovascular and cerebrovascular outcomes","volume":"49","author":"Suresh","journal-title":"J Med Syst"},{"key":"R75","doi-asserted-by":"publisher","DOI":"10.1016\/j.lanwpc.2023.100817","article-title":"Applications of digital health approaches for cardiometabolic diseases prevention and management in the Western Pacific region","volume":"43","author":"Liang","journal-title":"Lancet Reg Health West Pac"},{"issue":"10","key":"R76","doi-asserted-by":"publisher","first-page":"817","DOI":"10.1093\/abm\/kaad041","article-title":"Effective behavior change techniques in digital health interventions for the prevention or management of noncommunicable diseases: an umbrella review","volume":"57","author":"Mair","journal-title":"Ann Behav Med"},{"issue":"3","key":"R77","doi-asserted-by":"publisher","DOI":"10.2196\/21061","article-title":"Digital technology interventions for risk factor modification in patients with cardiovascular disease: systematic review and meta-analysis","volume":"9","author":"Akinosun","journal-title":"JMIR Mhealth Uhealth"},{"issue":"2","key":"R78","doi-asserted-by":"publisher","first-page":"1097","DOI":"10.3390\/biomedinformatics4020062","article-title":"Recent advances in large language models for healthcare","volume":"4","author":"Nassiri","journal-title":"BioMedInformatics"},{"issue":"10","key":"R79","doi-asserted-by":"publisher","first-page":"894","DOI":"10.3390\/info16100894","article-title":"Large language model agents for biomedicine: a comprehensive review of methods, evaluations, challenges, and future directions","volume":"16","author":"Xu","journal-title":"Information"},{"issue":"9","key":"R80","doi-asserted-by":"publisher","first-page":"226","DOI":"10.3390\/ai6090226","article-title":"Retrieval-augmented generation (RAG) in healthcare: a comprehensive review","volume":"6","author":"Neha","journal-title":"AI"},{"issue":"1","key":"R81","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1007\/s00062-025-01562-z","article-title":"Evaluating retrieval augmented generation-enhanced large language models for question answering on German neurovascular guidelines","volume":"36","author":"Vach","journal-title":"Clin Neuroradiol"},{"key":"R82","unstructured":"Yang R Wong MYH Li H et al. Retrieval-augmented generation in medicine: a scoping review of technical implementations, clinical applications, and ethical considerations. arXiv. Preprint posted online on Nov 13, 2025. [doi: 10.48550\/arXiv.2511.05901]"},{"key":"R83","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2025.106144","article-title":"A hybrid decision support system using rule-based and AI methods: the OnCATs knowledge-based framework","volume":"206","author":"Domingues","journal-title":"Int J Med Inform"},{"key":"R84","unstructured":"Ong JCL Jin L Elangovan K et al. Development and testing of a novel large language model-based clinical decision support systems for medication safety in 12 clinical specialties. arXiv. Preprint posted online on Feb 17, 2024. [doi: 10.48550\/arXiv.2402.01741]"},{"key":"R85","unstructured":"Hasan MM Mostafiz R Hossain MA Paul BK . CLIN-LLM: a safety-constrained hybrid framework for clinical diagnosis and treatment generation. arXiv. Preprint posted online on Apr 25, 2026. [doi: 10.48550\/arXiv.2510.22609]"},{"issue":"10","key":"R86","doi-asserted-by":"publisher","DOI":"10.1016\/j.xcrm.2025.102323","article-title":"Large language model as clinical decision support system augments medication safety in 16 clinical specialties","volume":"6","author":"Ong","journal-title":"Cell Rep Med"},{"key":"R87","doi-asserted-by":"publisher","DOI":"10.2196\/58974","article-title":"Empathic conversational agent platform designs and their evaluation in the context of mental health: systematic review","volume":"11","author":"Sanjeewa","journal-title":"JMIR Ment Health"},{"issue":"2","key":"R88","doi-asserted-by":"publisher","DOI":"10.1016\/j.chbah.2024.100067","article-title":"Artificial empathy in healthcare chatbots: does it feel authentic?","volume":"2","author":"Seitz","journal-title":"Comput Hum Behav Artif Hum"},{"key":"R89","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2021.08.015","article-title":"Empathic conversational agents for real-time monitoring and co-facilitation of patient-centered healthcare","volume":"126","author":"Adikari","journal-title":"Future Gener Comput Syst"},{"key":"R90","doi-asserted-by":"crossref","unstructured":"Zeltsi A Tsourma M Alexiadis A et al. Intelligent conversational agent for medical information. In: Rapp A Di Caro L Meziane F Sugumaran V , editors. Natural Language Processing and Information Systems, NLDB 2024. Springer; 2024:341-351. [doi: 10.1007\/978-3-031-70242-6_32] ISBN: 978-3-031-70242-6","DOI":"10.1007\/978-3-031-70242-6_32"},{"issue":"1","key":"R91","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-025-01475-8","article-title":"Large language model agents can use tools to perform clinical calculations","volume":"8","author":"Goodell","journal-title":"NPJ Digit Med"},{"key":"R92","unstructured":"Shrestha S Kim M Ross K . Mathematical reasoning in large language models: assessing logical and arithmetic errors across wide numerical ranges. arXiv. Preprint posted online on Feb 12, 2025. [doi: 10.48550\/arXiv.2502.08680]"},{"issue":"12","key":"R93","doi-asserted-by":"publisher","DOI":"10.3390\/jpm14121131","article-title":"Enhancing large language model reliability: minimizing hallucinations with dual retrieval-augmented generation based on the latest diabetes guidelines","volume":"14","author":"Lee","journal-title":"J Pers Med"},{"key":"R94","doi-asserted-by":"crossref","unstructured":"Pandit S Xu J Hong J et al. MedHallu: a comprehensive benchmark for detecting medical hallucinations in large language models. Presented at: Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing; Nov 4-9, 2025:2858-2873; Suzhou, China. [doi: 10.18653\/v1\/2025.emnlp-main.143]","DOI":"10.18653\/v1\/2025.emnlp-main.143"},{"issue":"4","key":"R95","doi-asserted-by":"publisher","first-page":"460","DOI":"10.1016\/j.jnlssr.2024.06.001","article-title":"Exploring the risks of automation bias in healthcare artificial intelligence applications: a Bowtie analysis","volume":"5","author":"Abdelwanis","journal-title":"J Saf Sci Resil"},{"issue":"6","key":"R96","doi-asserted-by":"publisher","first-page":"5783","DOI":"10.1007\/s43681-025-00825-2","article-title":"Automation complacency: risks of abdicating medical decision making","volume":"5","author":"Saadeh","journal-title":"AI Ethics"},{"key":"R97","unstructured":"Tolsdorf J Luo AF Kodwani M et al. Safety perceptions of generative AI conversational agents: uncovering perceptual differences in trust, risk, and fairness. Presented at: Proceedings of the 21st Symposium on Usable Privacy and Security (SOUPS 2025); Aug 10-12, 2025:93-112; Seattle, WA. [doi: 10.5555\/3767870.3767876]"},{"key":"R98","doi-asserted-by":"publisher","DOI":"10.1108\/JHOM-10-2023-0302","article-title":"AI-enabled chatbots healthcare systems: an ethical perspective on trust and reliability","author":"Basharat","journal-title":"J Health Organ Manag"},{"issue":"4","key":"R99","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1093\/medlaw\/fwad013","article-title":"Artificial intelligence and clinical decision support: clinicians\u2019 perspectives on trust, trustworthiness, and liability","volume":"31","author":"Jones","journal-title":"Med Law Rev"},{"issue":"5","key":"R100","doi-asserted-by":"publisher","first-page":"924","DOI":"10.1038\/s41591-022-01772-9","article-title":"Reporting guideline for the early-stage clinical evaluation of decision support systems driven by artificial intelligence: DECIDE-AI","volume":"28","author":"Vasey","journal-title":"Nat Med"},{"key":"R101","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.g1687","article-title":"Better reporting of interventions: template for intervention description and replication (TIDieR) checklist and guide","volume":"348","author":"Hoffmann","journal-title":"BMJ"},{"issue":"1 Suppl","key":"R102","doi-asserted-by":"publisher","DOI":"10.1007\/s12160-014-9596-9","article-title":"Reporting behavior change interventions: The tidier interdisciplinary checklist of the minimum recommended information","volume":"47","author":"Johnston","journal-title":"Ann Behav Med"},{"issue":"17","key":"R103","doi-asserted-by":"publisher","DOI":"10.3390\/jcm13175101","article-title":"Large language model prompting techniques for advancement in clinical medicine","volume":"13","author":"Shah","journal-title":"J Clin Med"},{"issue":"1","key":"R104","doi-asserted-by":"publisher","DOI":"10.1038\/s44172-025-00453-y","article-title":"Explainability in the age of large language models for healthcare","volume":"4","author":"Mesinovic","journal-title":"Commun Eng"},{"issue":"4","key":"R105","doi-asserted-by":"publisher","first-page":"1999","DOI":"10.1007\/s00521-024-10868-x","article-title":"The role of explainability and transparency in fostering trust in AI healthcare systems: a systematic literature review, open issues and potential solutions","volume":"37","author":"Eke","journal-title":"Neural Comput Appl"},{"key":"R106","doi-asserted-by":"publisher","DOI":"10.2196\/40789","article-title":"Artificial intelligence-based chatbots for promoting health behavioral changes: systematic review","volume":"25","author":"Aggarwal","journal-title":"J Med Internet Res"},{"key":"R107","doi-asserted-by":"publisher","DOI":"10.2196\/51086","article-title":"AI hesitancy and acceptability-perceptions of AI chatbots for chronic health management and long COVID support: survey study","volume":"11","author":"Wu","journal-title":"JMIR Hum Factors"},{"issue":"1","key":"R108","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-023-00979-5","article-title":"Systematic review and meta-analysis of AI-based conversational agents for promoting mental health and well-being","volume":"6","author":"Li","journal-title":"NPJ Digit Med"},{"issue":"7","key":"R109","doi-asserted-by":"publisher","DOI":"10.3390\/info16070549","article-title":"Large language models in medical chatbots: opportunities, challenges, and the need to address AI risks","volume":"16","author":"Chow","journal-title":"Information"},{"key":"R110","doi-asserted-by":"publisher","DOI":"10.2196\/67913","article-title":"Engagement with conversational agent-enabled interventions in cardiometabolic disease self-management: systematic review","volume":"13","author":"Kashyap","journal-title":"JMIR Mhealth Uhealth"},{"key":"R111","unstructured":"Naderi N Safavi-Naini SAA Savage T et al. Self-reported confidence of large language models in gastroenterology: analysis of commercial, open-source, and quantized models. arXiv. Preprint posted online on Mar 24, 2025. [doi: 10.48550\/arXiv.2503.18562]"},{"issue":"3","key":"R112","doi-asserted-by":"publisher","DOI":"10.4239\/wjd.v16.i3.98408","article-title":"Prospects and perils of ChatGPT in diabetes","volume":"16","author":"Sridhar","journal-title":"World J Diabetes"},{"issue":"5","key":"R113","doi-asserted-by":"publisher","first-page":"487","DOI":"10.1016\/j.bushor.2024.03.003","article-title":"A framework of diversity, equity, and inclusion safeguards for chatbots","volume":"67","author":"Abdelhalim","journal-title":"Bus Horiz"},{"key":"R114","doi-asserted-by":"publisher","DOI":"10.2196\/52597","article-title":"Large language models and empathy: systematic review","volume":"26","author":"Sorin","journal-title":"J Med Internet Res"},{"issue":"3","key":"R115","doi-asserted-by":"publisher","first-page":"628","DOI":"10.1038\/s41591-024-02815-z","article-title":"Interventions to enhance digital health equity in cardiovascular care","volume":"30","author":"Mihan","journal-title":"Nat Med"},{"issue":"4","key":"R116","doi-asserted-by":"publisher","first-page":"e282","DOI":"10.1016\/S2589-7500(24)00255-3","article-title":"Large language models for the mental health community: framework for translating code to care","volume":"7","author":"Malgaroli","journal-title":"Lancet Digit Health"},{"key":"R117","doi-asserted-by":"publisher","DOI":"10.1186\/1748-5908-6-42","article-title":"The behaviour change wheel: a new method for characterising and designing behaviour change interventions","volume":"6","author":"Michie","journal-title":"Implement Sci"},{"issue":"10","key":"R118","doi-asserted-by":"publisher","DOI":"10.2196\/39243","article-title":"Conversational agents in health care: scoping review of their behavior change techniques and underpinning theory","volume":"24","author":"Martinengo","journal-title":"J Med Internet Res"},{"issue":"4","key":"R119","doi-asserted-by":"publisher","first-page":"3981","DOI":"10.1007\/s43681-025-00696-7","article-title":"An integrated framework for ethical healthcare chatbots using LangChain and NeMo guardrails","volume":"5","author":"Arun","journal-title":"AI Ethics"},{"key":"R120","doi-asserted-by":"crossref","unstructured":"Adirim T Rao R . U.S. and global regulatory frameworks for AI in healthcare. In: Digital Health, AI and Generative AI in Healthcare: A Concise, Practical Guide for Clinicians. Springer; 2025:179-188. [doi: 10.1007\/978-3-031-83526-1_14] ISBN: 978-3-031-83525-4","DOI":"10.1007\/978-3-031-83526-1_14"},{"key":"R121","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2024.105780","article-title":"Towards secure and trusted AI in healthcare: a systematic review of emerging innovations and ethical challenges","volume":"195","author":"Mohsin Khan","journal-title":"Int J Med Inform"},{"key":"R122","unstructured":"Alkan M Zakariyya I Leighton S Sivangi KB Anagnostopoulos C Deligianni F . Artificial intelligence-driven clinical decision support systems. arXiv. Preprint posted online on Feb 17, 2025. [doi: 10.48550\/arXiv.2501.09628]"},{"key":"R123","doi-asserted-by":"crossref","unstructured":"Lal M Neduncheliyan S . The evolution and potential of conversational agents in healthcare. In: Communications in Computer and Information Science. Springer; 2025:209-220. [doi: 10.1007\/978-3-031-75861-4_19] ISBN: 978-3-031-75860-7","DOI":"10.1007\/978-3-031-75861-4_18"},{"issue":"12","key":"R124","doi-asserted-by":"publisher","first-page":"3590","DOI":"10.1038\/s41591-024-03258-2","article-title":"A toolbox for surfacing health equity harms and biases in large language models","volume":"30","author":"Pfohl","journal-title":"Nat Med"},{"key":"R125","doi-asserted-by":"publisher","DOI":"10.2196\/54375","article-title":"Digital behavior change intervention designs for habit formation: systematic review","volume":"26","author":"Zhu","journal-title":"J Med Internet Res"},{"issue":"2","key":"R126","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1016\/j.imed.2025.03.002","article-title":"Evaluating large language models and agents in healthcare: key challenges in clinical applications","volume":"5","author":"Chen","journal-title":"Intell Med"}],"container-title":["Journal of Medical Internet Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jmir.org\/2026\/1\/e89190","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T22:24:43Z","timestamp":1785536683000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jmir.org\/2026\/1\/e89190"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,15]]},"references-count":126,"URL":"https:\/\/doi.org\/10.2196\/89190","relation":{},"ISSN":["1438-8871"],"issn-type":[{"value":"1438-8871","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,15]]},"article-number":"v28i6e89190"}}