{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T17:25:00Z","timestamp":1793381100161,"version":"4.5.0"},"reference-count":31,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T00:00:00Z","timestamp":1781222400000},"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. Public Health"],"abstract":"<jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>To benchmark the informational quality, verifiability indicators, and readability of publicly accessible large language model (LLM) responses to standardized, patient-facing varicose veins (VV) questions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Twenty single-intent VV questions were derived from PubMed-indexed VV and chronic venous disease guidelines and consensus statements (search date: February 10, 2026). The question set was designed as a decision-critical benchmark across the care pathway rather than a prevalence-weighted sample of real-world patient queries. Five publicly accessible LLMs (ChatGPT 5.2, DeepSeek-V3.2, Gemini 3 Pro, Grok 4.1, and Qwen3-Max) were queried through their official web interfaces from February 10 to 12, 2026, under default settings, generating 100 responses. Each prompt was entered in a new privacy-mode session, and refusals or other non-responsive outputs were retained as returned. Two blinded clinicians independently rated DISCERN (16\u201380), EQIP (0%\u2212100%), GQS (1\u20135), and the JAMA benchmark (0\u20134). In this study, JAMA was used as a structured measure of visible attribution and verifiability-related features rather than as a comprehensive measure of transparency for conversational AI. Readability was assessed using six standard indices. Interrater reliability was evaluated with ICC(A,1) and weighted Cohen's \u03ba. Between-model differences were tested using Friedman tests with Kendall's W and Holm adjustment.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Interrater reliability was high [DISCERN ICC(A,1) = 0.913; EQIP ICC(A,1) = 0.859; GQS \u03ba = 0.883; JAMA \u03ba = 0.864]. Informational-quality scores were broadly similar across models (DISCERN means, 46.50\u201350.75; EQIP means, 71.50\u201374.25; GQS medians, 4.0). JAMA scores were uniformly low (means, 0.00\u20130.25; medians, 0), indicating sparse visible attribution and limited verifiability cues in default outputs. Between-model differences in the primary informational-quality outcomes were small and were not significant after Holm adjustment. Readability differences were more pronounced, and all models exceeded commonly recommended sixth-grade readability thresholds.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Under default public-user settings, publicly accessible LLMs generated fluent VV responses with limited visible verifiability indicators and suboptimal readability. Differences in the primary informational-quality outcomes were modest and should be interpreted cautiously. This benchmark evaluates communication-related performance rather than claim-level clinical accuracy or safety. These findings support efforts to improve auditability, provenance reporting, and uncertainty communication, but these dimensions do not substitute for formal assessment of factual accuracy, guideline concordance, and clinical safety.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fpubh.2026.1818821","type":"journal-article","created":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T05:45:01Z","timestamp":1781243101000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Benchmarking public large language model responses to patient-facing varicose veins questions: informational quality, verifiability indicators, and readability"],"prefix":"10.3389","volume":"14","author":[{"given":"Wei","family":"Zhong","sequence":"first","affiliation":[{"name":"Department of Vascular Surgery, Suining Central Hospital","place":["Suining, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guoxue","family":"Zheng","sequence":"additional","affiliation":[{"name":"Department of Vascular Surgery, Suining Central Hospital","place":["Suining, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qin","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Vascular Surgery, Suining Central Hospital","place":["Suining, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Vascular Surgery, Suining Central Hospital","place":["Suining, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinjie","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Vascular Surgery, Suining Central Hospital","place":["Suining, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,6,12]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"971","DOI":"10.1097\/SLA.0000000000004631","article-title":"Global epidemiology of chronic venous disease: a systematic review with pooled prevalence analysis","volume":"274","author":"Salim","year":"2021","journal-title":"Ann Surg."},{"key":"B2","doi-asserted-by":"publisher","first-page":"103729","DOI":"10.1016\/j.jscai.2025.103729","article-title":"2025 SCAI clinical practice guidelines for the management of chronic venous disease: this statement was endorsed by the society for Vascular Medicine (SVM)","volume":"4","author":"Attaran","year":"2025","journal-title":"J Soc Cardiovasc Angiogr Interv."},{"key":"B3","doi-asserted-by":"publisher","first-page":"550","DOI":"10.1186\/s12912-025-03155-0","article-title":"Global prevalence and risk factors of varicose veins among health care workers: a systematic review and meta-analysis","volume":"24","author":"He","year":"2025","journal-title":"BMC Nurs."},{"key":"B4","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1016\/j.ejvs.2022.06.022","article-title":"Editor's Choice - European Society for Vascular Surgery (ESVS) 2022 clinical practice guidelines on the management of chronic venous disease of the lower limbs","volume":"63","author":"De Maeseneer","year":"2022","journal-title":"Eur J Vasc Endovasc Surg."},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvsv.2022.09.004","article-title":"The 2022 Society for Vascular Surgery, American Venous Forum, and American Vein and Lymphatic Society clinical practice guidelines for the management of varicose veins of the lower extremities. Part I. Duplex scanning and treatment of superficial truncal reflux: endorsed by the society for vascular medicine and the international union of phlebology","author":"Gloviczki","year":"2023","journal-title":"J Vasc Surg Venous Lymphat Disord"},{"key":"B6","doi-asserted-by":"publisher","first-page":"845","DOI":"10.1111\/iwj.13931","article-title":"The burden of costs on health services from patients with venous leg ulcers in Singapore","volume":"20","author":"Nazeha","year":"2023","journal-title":"Int Wound J."},{"key":"B7","doi-asserted-by":"publisher","first-page":"e39555","DOI":"10.2196\/39555","article-title":"Credibility, accuracy, and comprehensiveness of readily available internet-based information on treatment and management of peripheral artery disease and intermittent claudication: review","volume":"24","author":"Alexander","year":"2022","journal-title":"J Med Internet Res."},{"key":"B8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.avsg.2021.12.079","article-title":"Quality analysis of online resources for patients with peripheral artery disease","volume":"83","author":"Treffalls","year":"2022","journal-title":"Ann Vasc Surg."},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvsv.2020.12.072","article-title":"Critical analysis of the quality of internet resources for patients with varicose veins","author":"Yan","year":"2021","journal-title":"J Vasc Surg Venous Lymphat Disord"},{"key":"B10","doi-asserted-by":"publisher","first-page":"556","DOI":"10.1177\/02683555231190454","article-title":"A readability analysis of patient education materials about chronic venous disease provided by professional vascular societies","volume":"38","author":"Liao","year":"2023","journal-title":"Phlebology."},{"key":"B11","doi-asserted-by":"publisher","first-page":"210","DOI":"10.5694\/mja2.52598","article-title":"Use of ChatGPT to obtain health information in Australia, 2024: insights from a nationally representative survey","volume":"222","author":"Ayre","year":"2025","journal-title":"Med J Aust."},{"key":"B12","doi-asserted-by":"publisher","first-page":"490","DOI":"10.1038\/s43856-025-01216-8","article-title":"Implications of integrating large language models into clinical decision making","volume":"5","author":"Christof","year":"2025","journal-title":"Commun Med."},{"key":"B13","doi-asserted-by":"publisher","first-page":"e68560","DOI":"10.2196\/68560","article-title":"Online health information-seeking in the era of large language models: cross-sectional web-based survey study","volume":"27","author":"Yun","year":"2025","journal-title":"J Med Internet Res."},{"key":"B14","doi-asserted-by":"publisher","first-page":"748","DOI":"10.1136\/bmjqs-2023-016690","article-title":"Generative artificial intelligence, patient safety and healthcare quality: a review","volume":"33","author":"Howell","year":"2024","journal-title":"BMJ Qual Saf."},{"key":"B15","doi-asserted-by":"publisher","first-page":"e2457879","DOI":"10.1001\/jamanetworkopen.2024.57879","article-title":"Large language models for chatbot health advice studies: a systematic review","volume":"8","author":"Huo","year":"2025","journal-title":"JAMA Netw Open."},{"key":"B16","doi-asserted-by":"publisher","first-page":"e001632","DOI":"10.1136\/bmjmed-2025-001632","article-title":"Reporting guideline for chatbot health advice studies: the Chatbot Assessment Reporting Tool (CHART) statement","volume":"4","author":"Collaborative","year":"2025","journal-title":"BMJ Med."},{"key":"B17","doi-asserted-by":"publisher","first-page":"104620","DOI":"10.1016\/j.jbi.2024.104620","article-title":"Evaluation of ChatGPT-generated medical responses: a systematic review and meta-analysis","volume":"151","author":"Wei","year":"2024","journal-title":"J Biomed Inform."},{"key":"B18","doi-asserted-by":"publisher","first-page":"14045","DOI":"10.1038\/s41598-023-41032-5","article-title":"Fabrication and errors in the bibliographic citations generated by ChatGPT","volume":"13","author":"Walters","year":"2023","journal-title":"Sci Rep."},{"key":"B19","doi-asserted-by":"publisher","first-page":"115334","DOI":"10.1016\/j.psychres.2023.115334","article-title":"ChatGPT and Bard exhibit spontaneous citation fabrication during psychiatry literature search","volume":"326","author":"McGowan","year":"2023","journal-title":"Psychiatry Res."},{"key":"B20","doi-asserted-by":"publisher","first-page":"e53164","DOI":"10.2196\/53164","article-title":"Hallucination rates and reference accuracy of ChatGPT and bard for systematic reviews: comparative analysis","volume":"26","author":"Chelli","year":"2024","journal-title":"J Med Internet Res."},{"key":"B21","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1016\/j.avsg.2024.07.083","article-title":"Clinical guidelines on compression therapy in venous diseases","volume":"110","author":"Sun","year":"2025","journal-title":"Ann Vasc Surg"},{"key":"B22","doi-asserted-by":"publisher","first-page":"101670","DOI":"10.1016\/j.jvsv.2023.08.011","article-title":"The 2023 Society for Vascular Surgery, American Venous Forum, and American Vein and Lymphatic Society clinical practice guidelines for the management of varicose veins of the lower extremities. Part II: endorsed by the society of interventional radiology and the society for vascular medicine","volume":"12","author":"Gloviczki","year":"2024","journal-title":"J Vasc Surg Venous Lymphat Disord."},{"key":"B23","year":"2013","journal-title":"Varicose Veins: Diagnosis and Management"},{"key":"B24","doi-asserted-by":"publisher","first-page":"106248","DOI":"10.1016\/j.ijmedinf.2025.106248","article-title":"A scoping review: how evaluation methods shape our understanding of ChatGPT's effectiveness in healthcare","volume":"209","author":"Liu","year":"2026","journal-title":"Int J Med Inform."},{"key":"B25","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1370\/afm.250386","article-title":"Reporting guideline for Chatbot Health Advice Studies: Chatbot Assessment Reporting Tool (CHART) statement","volume":"23","author":"Collaborative","year":"2025","journal-title":"Ann Fam Med."},{"key":"B26","doi-asserted-by":"publisher","first-page":"1244","DOI":"10.1001\/jama.1997.03540390074039","article-title":"Assessing, controlling, and assuring the quality of medical information on the Internet: caveant lector et viewor\u2013Let the reader and viewer beware","volume":"277","author":"Silberg","year":"1997","journal-title":"JAMA."},{"key":"B27","doi-asserted-by":"publisher","first-page":"1240","DOI":"10.1001\/jamaophthalmol.2019.3116","article-title":"Assessment of the quality, content, and readability of freely available online information for patients regarding diabetic retinopathy","volume":"137","author":"Kloosterboer","year":"2019","journal-title":"JAMA Ophthalmol."},{"key":"B28","doi-asserted-by":"publisher","first-page":"e80371","DOI":"10.2196\/80371","article-title":"Influence of topic familiarity and prompt specificity on citation fabrication in mental health research using large language models: experimental study","volume":"12","author":"Linardon","year":"2025","journal-title":"JMIR Ment Health."},{"key":"B29","doi-asserted-by":"publisher","first-page":"1059","DOI":"10.1016\/j.amjmed.2023.06.012","article-title":"Hallucinations in ChatGPT: a cautionary tale for biomedical researchers","volume":"136","author":"Goddard","year":"2023","journal-title":"Am J Med."},{"key":"B30","doi-asserted-by":"publisher","first-page":"226","DOI":"10.1016\/j.mcpdig.2023.05.004","article-title":"Learning to fake it: limited responses and fabricated references provided by ChatGPT for medical questions","volume":"1","author":"Gravel","year":"2023","journal-title":"Mayo Clin Proc Digit Health."},{"key":"B31","doi-asserted-by":"publisher","first-page":"3615","DOI":"10.1038\/s41467-025-58551-6","article-title":"An automated framework for assessing how well LLMs cite relevant medical references","volume":"16","author":"Wu","year":"2025","journal-title":"Nat Commun."}],"container-title":["Frontiers in Public Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2026.1818821\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T05:45:03Z","timestamp":1781243103000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2026.1818821\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,12]]},"references-count":31,"alternative-id":["10.3389\/fpubh.2026.1818821"],"URL":"https:\/\/doi.org\/10.3389\/fpubh.2026.1818821","relation":{},"ISSN":["2296-2565"],"issn-type":[{"value":"2296-2565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,12]]},"article-number":"1818821"}}