{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T08:13:37Z","timestamp":1788250417180,"version":"build-2803163510"},"reference-count":32,"publisher":"SAGE Publications","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["DIGITAL HEALTH"],"published-print":{"date-parts":[[2026,2]]},"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Generative AI (GenAI) shows promise for health literacy and awareness, with large language models (LLMs) increasingly used for health information-seeking despite concerns about misinformation. National health information portals provide authoritative, evidence-based content but lack conversational interfaces. Retrieval-augmented generation (RAG) offers a potential solution by grounding responses in verified health information portal content, yet evidence on such integration remains limited.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study aimed to design a national health information portal-integrated generative AI chatbot to support access to trustworthy health information and to evaluate its response characteristics relative to general-purpose LLMs through a multidimensional expert assessment.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A RAG-enhanced chatbot (NZIP AI assistant) was designed for the Czech Republic\u2019s National Health Information Portal and evaluated by eleven experts who compared it with ChatGPT, Microsoft Copilot, and Google Gemini across 67 health-related questions. Responses were rated on trustworthiness, clarity, user-friendliness, and relevance using a 5-point Likert scale (1 = best, 5 = worst). Content analysis examined response characteristics.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>In total, 267 assessments were collected. NZIP AI assistant achieved the highest trustworthiness score (mean 1.21) but ranked lowest on clarity (1.53), user-friendliness (1.46), and relevance (1.65). General-purpose LLMs demonstrated the inverse pattern. Content analysis revealed that the NZIP AI assistant provided source citations in 100% of responses, compared with 0\u20133% for general-purpose LLMs; included explicit safety disclaimers in 85% of responses, compared with 5\u201318%; and declined 10.4% of queries outside its knowledge base.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>National health information portals can integrate generative AI with RAG architecture to deliver verified, source-grounded health information, though trade-offs in user-oriented dimensions warrant consideration in future implementations. Still, this expert evaluation assessed response characteristics rather than direct effects on health literacy, awareness, or health outcomes.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1177\/20552076261481326","type":"journal-article","created":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T19:32:20Z","timestamp":1787945540000},"update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["Design and multidimensional expert evaluation of a national health information portal-integrated generative AI chatbot for health literacy and awareness"],"prefix":"10.1177","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2980-8213","authenticated-orcid":false,"given":"Hlib","family":"Aleksandrenko","sequence":"first","affiliation":[{"name":"Faculty of Medicine, Masaryk University, Brno, Czech Republic"},{"name":"Institute of Health Information and Statistics"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martin","family":"Komenda","sequence":"additional","affiliation":[{"name":"Faculty of Medicine, Masaryk University, Brno, Czech Republic"},{"name":"Institute of Health Information and Statistics"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2026,8,28]]},"reference":[{"key":"e_1_3_7_2_2","doi-asserted-by":"publisher","DOI":"10.2471\/B09619"},{"key":"e_1_3_7_3_2","volume-title":"International report on the methodology, results, and recommendations of the European Health Literacy Population Survey 2019-2021 (HLS19)","author":"HLS19 Consortium of the WHO Action Network M-POHL","year":"2021","unstructured":"HLS19 Consortium of the WHO Action Network M-POHL. International report on the methodology, results, and recommendations of the European Health Literacy Population Survey 2019-2021 (HLS19). Austrian National Public Health Institute, Vienna, 2021."},{"key":"e_1_3_7_4_2","volume-title":"Low health literacy: implications for national health policy","author":"Vernon JA","year":"2007","unstructured":"Vernon JA, Trujillo A, Rosenbaum S, et al. Low health literacy: implications for national health policy. Department of Health Policy, School of Public Health and Health Services, George Washington University, Washington, DC, 2007."},{"key":"e_1_3_7_5_2","doi-asserted-by":"publisher","DOI":"10.2196\/68560"},{"key":"e_1_3_7_6_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12909-025-08462-3"},{"key":"e_1_3_7_7_2","first-page":"03744","article-title":"Comparing traditional and LLM-based search for consumer choice: a randomized experiment","volume":"2307","author":"Spatharioti SE","year":"2023","unstructured":"Spatharioti SE, Rothschild DM, Goldstein DG, et al. Comparing traditional and LLM-based search for consumer choice: a randomized experiment. arXiv 2023; 2307: 03744.","journal-title":"arXiv"},{"key":"e_1_3_7_8_2","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare11060887"},{"key":"e_1_3_7_9_2","unstructured":"Choy V Martin S Lumpkin A. Can we rely on generative AI for healthcare information? Ipsos. 2024. https:\/\/www.ipsos.com\/en-us\/can-we-rely-generative-ai-healthcare-information accessed 3 July 2026."},{"key":"e_1_3_7_10_2","doi-asserted-by":"publisher","DOI":"10.3389\/fdgth.2025.1616488"},{"key":"e_1_3_7_11_2","first-page":"1","article-title":"Generative AI and misinformation: a scoping review of the role of generative AI in the generation, detection, mitigation, and impact of misinformation","volume":"40","author":"Park S","year":"2025","unstructured":"Park S, Nan X. Generative AI and misinformation: a scoping review of the role of generative AI in the generation, detection, mitigation, and impact of misinformation. AI Soc 2025; 40: 1\u201324. https:\/\/doi.org\/10.1007\/s00146-025-02620-3","journal-title":"AI Soc"},{"key":"e_1_3_7_12_2","doi-asserted-by":"publisher","DOI":"10.1038\/s44401-024-00004-1"},{"key":"e_1_3_7_13_2","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2024.22951"},{"key":"e_1_3_7_14_2","unstructured":"\u00dastav zdravotnick\u00fdch informac\u00ed a statistiky \u010cR. Porovn\u00e1n\u00ed n\u00e1rodn\u00edch zdravotnick\u00fdch port\u00e1l\u016f (interaktivn\u00ed vizualizace). Prague: \u00daZIS \u010cR. 2025. https:\/\/www.nzip.cz\/data\/2307 accessed 28 December 2025."},{"key":"e_1_3_7_15_2","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","volume":"33","author":"Lewis P","year":"2020","unstructured":"Lewis P, Perez E, Piktus A, et al. Retrieval-augmented generation for knowledge-intensive NLP tasks. Adv Neural Inf Process Syst 2020; 33: 9459\u20139474.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_7_16_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000877"},{"key":"e_1_3_7_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706599.3720239"},{"key":"e_1_3_7_18_2","unstructured":"National health information portal. Ministry of Health of the Czech Republic and Institute of Health Information and Statistics of the Czech Republic. https:\/\/www.nzip.cz\/ accessed 28 December 2025."},{"key":"e_1_3_7_19_2","volume-title":"Context windows documentation","author":"Anthropic","year":"2025","unstructured":"Anthropic. Context windows documentation. Anthropic, 2025. https:\/\/docs.anthropic.com\/en\/docs\/build-with-claude\/context-windows, accessed 28 December 2025."},{"key":"e_1_3_7_20_2","doi-asserted-by":"publisher","DOI":"10.2196\/70131"},{"key":"e_1_3_7_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3708319.3733709"},{"key":"e_1_3_7_22_2","doi-asserted-by":"publisher","DOI":"10.4103\/jehp.jehp_1195_24"},{"key":"e_1_3_7_23_2","doi-asserted-by":"publisher","DOI":"10.59249\/ZTOZ1966"},{"key":"e_1_3_7_24_2","first-page":"e56766","article-title":"Performance of artificial intelligence chatbots on glaucoma questions adapted from patient brochures","volume":"16","author":"Yalla GR","year":"2024","unstructured":"Yalla GR, Hyman N, Hock LE, et al. Performance of artificial intelligence chatbots on glaucoma questions adapted from patient brochures. Cureus 2024; 16: e56766. https:\/\/doi.org\/10.7759\/cureus.56766","journal-title":"Cureus"},{"key":"e_1_3_7_25_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ebiom.2023.104770"},{"key":"e_1_3_7_26_2","doi-asserted-by":"publisher","DOI":"10.2196\/60291"},{"key":"e_1_3_7_27_2","doi-asserted-by":"publisher","DOI":"10.1111\/nyas.15413"},{"key":"e_1_3_7_28_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.chbah.2024.100066"},{"key":"e_1_3_7_29_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-92611-2_5"},{"key":"e_1_3_7_30_2","unstructured":"Ajwani RD Javaji SR Rudzicz F et al. LLM-generated black-box explanations can be adversarially helpful. In: NeurIPS 2024 Workshop on Regulatable ML 2025. https:\/\/openreview.net\/forum?id=F0j4PPyQzt"},{"key":"e_1_3_7_31_2","first-page":"01241","article-title":"First, do NOHARM: towards clinically safe large language models","volume":"2512","author":"Wu D","year":"2025","unstructured":"Wu D, Nateghi Haredasht F, Maharaj SK, et al. First, do NOHARM: towards clinically safe large language models. arXiv 2025; 2512: 01241.","journal-title":"arXiv"},{"key":"e_1_3_7_32_2","doi-asserted-by":"publisher","DOI":"10.3390\/hearts6030019"},{"key":"e_1_3_7_33_2","doi-asserted-by":"publisher","DOI":"10.2147\/JMDH.S473680"}],"container-title":["DIGITAL HEALTH"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/20552076261481326","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/20552076261481326","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/20552076261481326","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T07:20:09Z","timestamp":1788247209000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/20552076261481326"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":32,"alternative-id":["10.1177\/20552076261481326"],"URL":"https:\/\/doi.org\/10.1177\/20552076261481326","relation":{},"ISSN":["2055-2076","2055-2076"],"issn-type":[{"value":"2055-2076","type":"print"},{"value":"2055-2076","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]},"article-number":"20552076261481326"}}