{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T05:47:28Z","timestamp":1785822448697,"version":"3.56.0"},"reference-count":28,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T00:00:00Z","timestamp":1785801600000},"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>Objective<\/jats:title>\n                    <jats:p>To evaluate the performance of large language models (LLMs) and expert clinicians in optimizing Chinese patient education materials (PEMs) for temporomandibular disorders (TMD) across readability, accuracy, actionability, and cultural adaptability, and to determine whether a human-AI collaboration model can achieve an optimal balance among these dimensions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      Fifteen TMD education topics were selected through a Delphi consensus process. Four groups of PEMs were generated: original texts (Group A), LLM-rewritten texts (Group B, Claude Opus 4.6), clinician-rewritten texts (Group C), and human-AI collaboration texts (Group D). Blinded assessments were conducted by a professional panel (\n                      <jats:italic>n<\/jats:italic>\n                      \u202f=\u202f3) and a health literacy-stratified patient panel (\n                      <jats:italic>n<\/jats:italic>\n                      \u202f=\u202f6). Readability was measured by sentence length and common character proportion, accuracy by 5-point expert ratings against standardized checklists, actionability by the PEMAT instrument, and cultural adaptability by qualitative thematic analysis. Prompt sensitivity was tested across three distinct styles.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      LLM-rewritten texts demonstrated significantly shorter sentences (21.1 vs. 33.9 characters,\n                      <jats:italic>p<\/jats:italic>\n                      \u202f&amp;lt;\u202f0.001) and substantially higher actionability (95.6% vs. 16.7%,\n                      <jats:italic>p<\/jats:italic>\n                      \u202f&amp;lt;\u202f0.001) compared with original texts. Clinician-rewritten texts achieved the highest accuracy (4.48 vs. 3.23,\n                      <jats:italic>p<\/jats:italic>\n                      \u202f&amp;lt;\u202f0.001) but low actionability (46.7%). The human-AI collaboration model matched clinician accuracy (4.49,\n                      <jats:italic>p<\/jats:italic>\n                      \u202f=\u202f1.000) while preserving LLM actionability (95.6%), with 72% less clinician time. Sensitivity analysis confirmed actionability robustness under empathetic and authoritative prompts but attenuation under a concise prompt. Qualitative analysis identified four cultural adaptability themes, with LLMs excelling in terminology localization and behavioral structuring but showing limitations in TCM conceptual depth.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The human-AI collaboration model represents a promising and balanced approach for producing Chinese TMD patient education materials, combining LLM strengths in structural optimization with expert clinician oversight for accuracy and cultural appropriateness.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fpubh.2026.1923536","type":"journal-article","created":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T05:38:34Z","timestamp":1785821914000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Large language models versus expert clinicians in optimizing Chinese patient education materials for temporomandibular disorders: a mixed-methods study integrating readability, accuracy, actionability, and cultural adaptability"],"prefix":"10.3389","volume":"14","author":[{"given":"Jing","family":"Han","sequence":"first","affiliation":[{"name":"Department of Stomatology, Jinan Maternal and Child Health Care Hospital","place":["Jinan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan-li","family":"Shi","sequence":"additional","affiliation":[{"name":"Department of Stomatology, Shandong Provincial Hospital Affiliated to Shandong First Medical University","place":["Jinan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Dai","sequence":"additional","affiliation":[{"name":"Department of Stomatology, Shandong Provincial Hospital Affiliated to Shandong First Medical University","place":["Jinan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,4]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"692","DOI":"10.1177\/0333102416686302","article-title":"Temporomandibular disorders: old ideas and new concepts","volume":"37","author":"List","year":"2017","journal-title":"Cephalalgia"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"T102","DOI":"10.1016\/j.jpain.2013.08.006","article-title":"Summary of findings from the OPPERA prospective cohort study of incidence of first-onset temporomandibular disorder","volume":"14","author":"Slade","year":"2013","journal-title":"J Pain"},{"key":"ref3","volume-title":"Orofacial Pain: Guidelines for Assessment, Diagnosis, and Management","author":"de Leeuw","year":"2018"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"1672","DOI":"10.1016\/j.joms.2020.06.028","article-title":"Temporomandibular disorders: a report of the American Academy of orofacial pain","volume":"78","author":"Greene","year":"2020","journal-title":"J Oral Maxillofac Surg"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"1871","DOI":"10.1111\/j.1475-6773.2006.00689.x","article-title":"Time allocation in primary care office visits","volume":"42","author":"Tai-Seale","year":"2007","journal-title":"Health Serv Res"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"1165","DOI":"10.1007\/s11606-012-2047-4","article-title":"Readability of patient education materials available at the point of care","volume":"27","author":"Stossel","year":"2012","journal-title":"J Gen Intern Med"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"1257","DOI":"10.1001\/jamainternmed.2013.6060","article-title":"A comparative analysis of the quality of patient education materials from medical specialties","volume":"173","author":"Agarwal","year":"2013","journal-title":"JAMA Intern Med"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1016\/j.pec.2014.05.027","article-title":"Development of the patient education materials assessment tool (PEMAT) and a user's guide","volume":"96","author":"Shoemaker","year":"2014","journal-title":"Patient Educ Couns"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"e24","DOI":"10.3928\/24748307-20150214-01","article-title":"Evaluating the actionability of patient education materials","volume":"2","author":"Zellmer","year":"2015","journal-title":"Health Lit Res Pract"},{"key":"ref10","first-page":"3","article-title":"Health literacy in China: findings from a national survey","volume":"36","author":"Chen","year":"2020","journal-title":"Chin J Health Educ"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"1036","DOI":"10.1111\/joor.12835","article-title":"Prevalence of TMD in a Chinese population: a systematic review","volume":"46","author":"Li","year":"2019","journal-title":"J Oral Rehabil"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"1233","DOI":"10.1056\/NEJMc2214184","article-title":"Benefits, limits, and risks of GPT-4 in medicine","volume":"388","author":"Lee","year":"2023","journal-title":"N Engl J Med"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"e48292","DOI":"10.2196\/48292","article-title":"ChatGPT utility in healthcare education and research: systematic review","volume":"25","author":"Sallam","year":"2023","journal-title":"J Med Internet Res"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1016\/j.ophtha.2023.09.015","article-title":"Assessing ChatGPT responses to ophthalmology patient questions","volume":"131","author":"Cheung","year":"2024","journal-title":"Ophthalmology"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"732","DOI":"10.2106\/JBJS.23.00932","article-title":"ChatGPT in orthopaedic patient education","volume":"106","author":"Moorthy","year":"2024","journal-title":"J Bone Joint Surg Am"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"109982","DOI":"10.1016\/j.radonc.2024.109982","article-title":"AI vs clinicians in radiotherapy patient education","volume":"192","author":"Lambert","year":"2025","journal-title":"Radiother Oncol"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"33","DOI":"10.3390\/japma116030033","article-title":"Comparison of ChatGPT-5 and DeepSeek V3 for artificial intelligence-assisted patient education in foot and ankle disorders","volume":"116","author":"Karagoz","year":"2026","journal-title":"J Am Podiatr Med Assoc"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1186\/s12911-025-03202-5","article-title":"Can large language models follow guidelines? A comparative study of ChatGPT-4o and DeepSeek AI in clavicle fracture management based on AAOS recommendations","volume":"25","author":"Ke\u00e7eci","year":"2025","journal-title":"BMC Med Inform Decis Mak"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"845","DOI":"10.1227\/neu.0000000000002714","article-title":"Bridging the literacy gap: comparing the effectiveness of patient education materials generated by artificial intelligence and expert clinicians","volume":"94","author":"Ali","year":"2024","journal-title":"Neurosurgery"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"6","DOI":"10.11607\/jop.1151","article-title":"Diagnostic criteria for temporomandibular disorders (DC\/TMD) for clinical and research applications: recommendations of the international RDC\/TMD consortium network and orofacial pain special interest group","volume":"28","author":"Schiffman","year":"2014","journal-title":"J Oral Facial Pain Headache"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"514","DOI":"10.1370\/afm.405","article-title":"Quick assessment of literacy in primary care: the newest vital sign","volume":"3","author":"Weiss","year":"2005","journal-title":"Ann Fam Med"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1191\/1478088706qp063oa","article-title":"Using thematic analysis in psychology","volume":"3","author":"Braun","year":"2006","journal-title":"Qual Res Psychol"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1016\/j.jcm.2016.02.012","article-title":"A guideline of selecting and reporting intraclass correlation coefficients for reliability research","volume":"15","author":"Koo","year":"2016","journal-title":"J Chiropr Med"},{"key":"ref24","volume-title":"Health Literacy and Patient Safety: Help Patients Understand","author":"Weiss","year":"2007"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1038\/s41586-023-06291-2","article-title":"Large language models encode clinical knowledge","volume":"620","author":"Singhal","year":"2023","journal-title":"Nature"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"e45312","DOI":"10.2196\/45312","article-title":"How does ChatGPT perform on medical licensing exams?","volume":"9","author":"Gilson","year":"2023","journal-title":"JMIR Med Educ"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"415","DOI":"10.5152\/j.aott.2025.25428","article-title":"Comparative evaluation of large language model-based chatbots in a septic arthritis scenario: ChatGPT, Claude, and perplexity","volume":"59","author":"Bayrak","year":"2025","journal-title":"Acta Orthop Traumatol Turc"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1258\/jrsm.96.5.219","article-title":"Patients' memory for medical information","volume":"96","author":"Kessels","year":"2003","journal-title":"J R Soc Med"}],"container-title":["Frontiers in Public Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2026.1923536\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T05:38:36Z","timestamp":1785821916000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2026.1923536\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,4]]},"references-count":28,"alternative-id":["10.3389\/fpubh.2026.1923536"],"URL":"https:\/\/doi.org\/10.3389\/fpubh.2026.1923536","relation":{},"ISSN":["2296-2565"],"issn-type":[{"value":"2296-2565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,4]]},"article-number":"1923536"}}