{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T23:17:05Z","timestamp":1792624625374,"version":"4.5.0"},"reference-count":21,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Nursing"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n The health care sector faces a projected shortfall of 10 million workers by 2030. Artificial intelligence (AI) automation in areas such as patient education and initial therapy screening presents a strategic response to mitigate this shortage and reallocate medical staff to higher-priority tasks. However, current methods of evaluating early-stage health care AI chatbots are highly limited due to safety concerns and the amount of time and effort that goes into evaluating them.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study introduces a novel 3-bot method for efficiently testing and validating early-stage AI health care provider chatbots. To extensively test AI provider chatbots without involving real patients or researchers, various AI patient bots and an evaluator bot were developed.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n Provider bots interacted with AI patient bots embodying frustrated, anxious, or depressed personas. An evaluator bot reviewed interaction transcripts based on specific criteria. Human experts then reviewed each interaction transcript, and the evaluator bot\u2019s results were compared to human evaluation results to ensure accuracy.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n The patient-education bot\u2019s evaluations by the AI evaluator and the human evaluator were nearly identical, with minimal variance, limiting the opportunity for further analysis. The screening bot\u2019s evaluations also yielded similar results between the AI evaluator and human evaluator. Statistical analysis confirmed the reliability and accuracy of the AI evaluations.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n The innovative evaluation method ensures a safe, adaptable, and effective means to test and refine early versions of health care provider chatbots without risking patient safety or investing excessive researcher time and effort. Our patient-education evaluator bots could have benefitted from larger evaluation criteria, as we had extremely similar results from the AI and human evaluators, which could have arisen because of the small number of evaluation criteria. We were limited in the amount of prompting we could input into each bot due to the practical consideration that response time increases with larger and larger prompts. In the future, using techniques such as retrieval augmented generation will allow the system to receive more information and become more specific and accurate in evaluating the chatbots. This evaluation method will allow for rapid testing and validation of health care chatbots to automate basic medical tasks, freeing providers to address more complex tasks.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/63058","type":"journal-article","created":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T10:31:33Z","timestamp":1740652293000},"page":"e63058-e63058","source":"Crossref","is-referenced-by-count":16,"title":["Advancing Clinical Chatbot Validation Using AI-Powered Evaluation With a New 3-Bot Evaluation System: Instrument Validation Study"],"prefix":"10.2196","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-1131-8526","authenticated-orcid":false,"given":"Seungheon","family":"Choo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1617-6719","authenticated-orcid":false,"given":"Suyoung","family":"Yoo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1061-8133","authenticated-orcid":false,"given":"Kumiko","family":"Endo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3401-0763","authenticated-orcid":false,"given":"Bao","family":"Truong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3505-5576","authenticated-orcid":false,"given":"Meong Hi","family":"Son","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2025,2,27]]},"reference":[{"key":"R1","unstructured":"Global strategy on human resources for health: workforce 2030. World Health Organization. 2016. URL: https:\/\/iris.who.int\/bitstream\/handle\/10665\/250368\/9789241511131-eng.pdf [Accessed 07-02-2025]"},{"key":"R2","doi-asserted-by":"crossref","unstructured":"Bohr A Memarzadeh K . The rise of artificial intelligence in healthcare applications. In: Artificial Intelligence in Healthcare. Elsevier; 2020:25-60. [doi: 10.1016\/B978-0-12-818438-7.00002-2]","DOI":"10.1016\/B978-0-12-818438-7.00002-2"},{"issue":"3","key":"R3","doi-asserted-by":"publisher","first-page":"19","DOI":"10.4018\/IJISSS.2019070102","article-title":"Machine learning for emergency department management","volume":"11","author":"Benbelkacem","journal-title":"Int J Inf Syst Serv Sect"},{"issue":"1","key":"R4","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1186\/s12875-024-02282-y","article-title":"Navigating the doctor-patient-AI relationship\u2014a mixed-methods study of physician attitudes toward artificial intelligence in primary care","volume":"25","author":"Allen","journal-title":"BMC Prim Care"},{"issue":"2","key":"R5","doi-asserted-by":"publisher","first-page":"90","DOI":"10.15406\/ahoaj.2024.06.00227","article-title":"Harnessing the power of AI in healthcare: benefits, concerns, and challenges for medical personnel training","volume":"6","author":"Puri","journal-title":"AHOAJ"},{"key":"R6","doi-asserted-by":"publisher","DOI":"10.1136\/leader-2023-000797","article-title":"ChatGPT and generative AI chatbots: challenges and opportunities for science, medicine and medical leaders","author":"Loh","journal-title":"BMJ Lead"},{"key":"R7","doi-asserted-by":"crossref","unstructured":"Wilhelm TI Roos J Kaczmarczyk R . Large language models for therapy recommendations across 3 clinical specialties: comparative study. 2023;25:e49324. [doi: 10.2196\/49324]","DOI":"10.2196\/49324"},{"issue":"7987","key":"R8","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1038\/s41586-023-06647-8","article-title":"Role play with large language models","volume":"623","author":"Shanahan","journal-title":"Nature New Biol"},{"key":"R9","doi-asserted-by":"crossref","unstructured":"Shao Y Li L Dai J Qiu X . Character-LLM: a trainable agent for role-playing. Presented at: The 2023 Conference on Empirical Methods in Natural Language Processing; Dec 6-10, 2023; Singapore. [doi: 10.18653\/v1\/2023.emnlp-main.814]","DOI":"10.18653\/v1\/2023.emnlp-main.814"},{"issue":"11","key":"R10","doi-asserted-by":"publisher","first-page":"1238","DOI":"10.1093\/clinchem\/hvad106","article-title":"AI chatbots in clinical laboratory medicine: foundations and trends","volume":"69","author":"Yang","journal-title":"Clin Chem"},{"issue":"10","key":"R11","doi-asserted-by":"publisher","first-page":"2396","DOI":"10.1038\/s41591-023-02412-6","article-title":"Large language model AI chatbots require approval as medical devices","volume":"29","author":"Gilbert","journal-title":"Nat Med"},{"key":"R12","doi-asserted-by":"publisher","DOI":"10.1016\/j.brat.2015.03.009","article-title":"Therapist competence in global mental health: Development of the ENhancing Assessment of Common Therapeutic factors (ENACT) rating scale","volume":"69","author":"Kohrt","journal-title":"Behav Res Ther"},{"issue":"1","key":"R13","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1080\/08998280.2017.11929552","article-title":"Improving health outcomes through patient education and partnerships with patients","volume":"30","author":"Paterick","journal-title":"Bayl Univ Med Cent Proc"},{"key":"R14","doi-asserted-by":"publisher","DOI":"10.1177\/20552076231173304","article-title":"An artificial intelligence-based chatbot for prostate cancer education: design and patient evaluation study","volume":"9","author":"G\u00f6rtz","journal-title":"Digit Health"},{"key":"R15","doi-asserted-by":"publisher","DOI":"10.21037\/jmai-23-92","article-title":"Artificial intelligence, chatbots and ChatGPT in healthcare\u2014narrative review of historical evolution, current application, and change management approach to increase adoption","volume":"6","author":"Singh","journal-title":"J Med Artif Intell"},{"issue":"11","key":"R16","doi-asserted-by":"publisher","first-page":"1582","DOI":"10.1038\/s41416-021-01542-3","article-title":"The mental health impacts of receiving a breast cancer diagnosis: a meta-analysis","volume":"125","author":"Fortin","journal-title":"Br J Cancer"},{"issue":"4","key":"R17","doi-asserted-by":"publisher","first-page":"2063","DOI":"10.1007\/s00405-023-08219-y","article-title":"Validity and reliability of an instrument evaluating the performance of intelligent chatbot: the Artificial Intelligence Performance Instrument (AIPI)","volume":"281","author":"Lechien","journal-title":"Eur Arch Otorhinolaryngol"},{"issue":"10","key":"R18","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2023.36483","article-title":"Accuracy and reliability of chatbot responses to physician questions","volume":"6","author":"Goodman","journal-title":"JAMA Netw Open"},{"key":"R19","doi-asserted-by":"crossref","unstructured":"Aljamaan F Temsah MH Altamimi I et al. Innovation of referencing hallucination score for medical AI chatbots\u2019 and comparison of six large language models. JMIR Preprints. Preprint posted online onNov6, 2023. [doi: 10.2196\/54345]","DOI":"10.2196\/54345"},{"issue":"1","key":"R20","doi-asserted-by":"publisher","DOI":"10.1186\/s12909-024-06115-5","article-title":"The future of AI clinicians: assessing the modern standard of chatbots and their approach to diagnostic uncertainty","volume":"24","author":"Huang","journal-title":"BMC Med Educ"},{"key":"R21","doi-asserted-by":"publisher","DOI":"10.1177\/1178222619829083","article-title":"Can your phone be your therapist? Young people\u2019s ethical perspectives on the use of fully automated conversational agents (chatbots) in mental health support","volume":"11","author":"Kretzschmar","journal-title":"Biomed Inform Insights"}],"container-title":["JMIR Nursing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/nursing.jmir.org\/2025\/1\/e63058","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T22:31:18Z","timestamp":1785537078000},"score":1,"resource":{"primary":{"URL":"https:\/\/nursing.jmir.org\/2025\/1\/e63058"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,27]]},"references-count":21,"URL":"https:\/\/doi.org\/10.2196\/63058","relation":{},"ISSN":["2562-7600"],"issn-type":[{"value":"2562-7600","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,27]]},"article-number":"v8i3e63058"}}