{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T22:36:52Z","timestamp":1793486212163,"version":"4.5.0"},"reference-count":35,"publisher":"BMJ","issue":"10","content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["Br J Ophthalmol"],"accepted":{"date-parts":[[2024,7,24]]},"published-print":{"date-parts":[[2024,10]]},"abstract":"<jats:sec><jats:title>Background\/aims<\/jats:title><jats:p>This was a cross-sectional comparative study. We evaluated the ability of three large language models (LLMs) (ChatGPT-3.5, ChatGPT-4, and Google Bard) to generate novel patient education materials (PEMs) and improve the readability of existing PEMs on paediatric cataract.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>We compared LLMs\u2019 responses to three prompts. Prompt A requested they write a handout on paediatric cataract that was \u2018easily understandable by an average American.\u2019 Prompt B modified prompt A and requested the handout be written at a \u2018sixth-grade reading level, using the Simple Measure of Gobbledygook (SMOG) readability formula.\u2019 Prompt C rewrote existing PEMs on paediatric cataract \u2018to a sixth-grade reading level using the SMOG readability formula\u2019. Responses were compared on their quality (DISCERN; 1 (low quality) to 5 (high quality)), understandability and actionability (Patient Education Materials Assessment Tool (\u226570%: understandable, \u226570%: actionable)), accuracy (Likert misinformation; 1 (no misinformation) to 5 (high misinformation) and readability (SMOG, Flesch-Kincaid Grade Level (FKGL); grade level &lt;7: highly readable).<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>All LLM-generated responses were of high-quality (median DISCERN \u22654), understandability (\u226570%), and accuracy (Likert=1). All LLM-generated responses were not actionable (&lt;70%). ChatGPT-3.5 and ChatGPT-4 prompt B responses were more readable than prompt A responses (p&lt;0.001). ChatGPT-4 generated more readable responses (lower SMOG and FKGL scores; 5.59\u00b10.5\u2009and 4.31\u00b10.7, respectively) than the other two LLMs (p&lt;0.001) and consistently rewrote them to or below the specified sixth-grade reading level (SMOG: 5.14\u00b10.3).<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>LLMs, particularly ChatGPT-4, proved valuable in generating high-quality, readable, accurate PEMs and in improving the readability of existing materials on paediatric cataract.<\/jats:p><\/jats:sec>","DOI":"10.1136\/bjo-2024-325252","type":"journal-article","created":{"date-parts":[[2024,8,22]],"date-time":"2024-08-22T17:24:29Z","timestamp":1724347469000},"page":"1470-1476","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":34,"title":["Large language models: a new frontier in paediatric cataract patient education"],"prefix":"10.1136","volume":"108","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-1471-288X","authenticated-orcid":false,"given":"Qais","family":"Dihan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad Z","family":"Chauhan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taher K","family":"Eleiwa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew D","family":"Brown","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amr K","family":"Hassan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohamed M","family":"Khodeiry","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Reem H","family":"Elsheikh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6596-3284","authenticated-orcid":false,"given":"Isdin","family":"Oke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bharti R","family":"Nihalani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deborah K","family":"VanderVeen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7207-6782","authenticated-orcid":false,"given":"Ahmed B","family":"Sallam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1412-375X","authenticated-orcid":false,"given":"Abdelrahman M","family":"Elhusseiny","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2024,8,22]]},"reference":[{"key":"2024101503100694000_108.10.1470.1","doi-asserted-by":"crossref","unstructured":"Lambert SR . Childhood Cataracts. In: Taylor and Hoyt\u2019s Pediatric Ophthalmology and Strabismus 5th Ed. Elsevier, 2017:349\u201361.","DOI":"10.1016\/B978-0-7020-6616-0.00037-2"},{"key":"2024101503100694000_108.10.1470.2","doi-asserted-by":"crossref","first-page":"601","DOI":"10.1016\/S0886-3350(97)80040-5","article-title":"Epidemiology of cataract in childhood: a global perspective","volume":"23 Suppl 1","author":"Foster","year":"1997","journal-title":"J Cataract Refract Surg"},{"key":"2024101503100694000_108.10.1470.3","doi-asserted-by":"crossref","first-page":"1160","DOI":"10.1038\/eye.2016.156","article-title":"Global prevalence of childhood cataract: a systematic review","volume":"30","author":"Sheeladevi","year":"2016","journal-title":"Eye (Lond)"},{"key":"2024101503100694000_108.10.1470.4","doi-asserted-by":"crossref","first-page":"e137","DOI":"10.1016\/j.ophtha.2022.06.034","article-title":"The Importance of Health Literacy in Addressing Eye Health and Eye Care Disparities","volume":"129","author":"Cap\u00f3","year":"2022","journal-title":"Ophthalmology"},{"key":"2024101503100694000_108.10.1470.5","doi-asserted-by":"publisher","DOI":"10.1016\/j.survophthal.2010.03.005"},{"key":"2024101503100694000_108.10.1470.6","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1016\/j.acap.2022.09.001","article-title":"Parental factors affecting pediatric medication management in underserved communities","volume":"23","author":"Rungvivatjarus","year":"2023","journal-title":"Acad Pediatr"},{"key":"2024101503100694000_108.10.1470.7","doi-asserted-by":"crossref","first-page":"S265","DOI":"10.1542\/peds.2009-1162B","article-title":"Health literacy and child health outcomes: a systematic review of the literature","volume":"124 Suppl 3","author":"DeWalt","year":"2009","journal-title":"Pediatrics"},{"key":"2024101503100694000_108.10.1470.8","doi-asserted-by":"crossref","first-page":"438","DOI":"10.1097\/IJG.0000000000002012","article-title":"Readability of online patient education materials for glaucoma","volume":"31","author":"Cheng","year":"2022","journal-title":"J Glaucoma"},{"key":"2024101503100694000_108.10.1470.9","doi-asserted-by":"crossref","first-page":"641","DOI":"10.1016\/j.oret.2022.03.015","article-title":"Readability and accountability of online patient education materials for common retinal diseases","volume":"6","author":"Cohen","year":"2022","journal-title":"Ophthalmol Retina"},{"key":"2024101503100694000_108.10.1470.10","unstructured":"AHRQ . The patient education materials assessment tool (PEMAT) and user\u2019s guide: introduction. 2020. Available: https:\/\/www.ahrq.gov\/health-literacy\/patient-education\/pemat1.html"},{"key":"2024101503100694000_108.10.1470.11","unstructured":"Weiss BD . Health Literacy: Help Your Patients Understand: A Continuing Medical Education (CME) Program That Provides Tools to Enhance Patient Care, Improve Office Productivity, and Reduce Healthcare Costs. Chicago, Ill: American Medical Association Foundation and American Medical Association, 2003."},{"key":"2024101503100694000_108.10.1470.12","doi-asserted-by":"crossref","first-page":"384","DOI":"10.1080\/08820538.2021.1893758","article-title":"Evaluation of the content, quality, and readability of patient accessible online resources regarding cataracts","volume":"36","author":"Patel","year":"2021","journal-title":"Semin Ophthalmol"},{"key":"2024101503100694000_108.10.1470.13","doi-asserted-by":"crossref","first-page":"430","DOI":"10.1016\/j.jaapos.2015.07.286","article-title":"Analysis of online patient education materials in pediatric ophthalmology","volume":"19","author":"John","year":"2015","journal-title":"J Am Assoc Pediatr Ophthalmol Strabismus"},{"key":"2024101503100694000_108.10.1470.14","doi-asserted-by":"crossref","first-page":"1283","DOI":"10.1097\/j.jcrs.0000000000001283","article-title":"Quality, reliability, technical quality, and readability of online information on pediatric cataract","volume":"49","author":"Elhusseiny","year":"2023","journal-title":"J Cataract Refract Surg"},{"key":"2024101503100694000_108.10.1470.15","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1016\/j.oret.2023.09.008","article-title":"The Use of large language models to generate education materials about uveitis","volume":"8","author":"Kianian","year":"2024","journal-title":"Ophthalmol Retina"},{"key":"2024101503100694000_108.10.1470.16","doi-asserted-by":"crossref","first-page":"100105","DOI":"10.1016\/j.tbench.2023.100105","article-title":"ChatGPT for healthcare services: an emerging stage for an innovative perspective","volume":"3","author":"Javaid","year":"2023","journal-title":"BenchCouncil Trans Bench Stand Eval"},{"key":"2024101503100694000_108.10.1470.17","doi-asserted-by":"crossref","DOI":"10.2196\/47479","article-title":"Reliability of medical information provided by chatgpt: assessment against clinical guidelines and patient information quality instrument","volume":"25","author":"Walker","year":"2023","journal-title":"J Med Internet Res"},{"key":"2024101503100694000_108.10.1470.18","doi-asserted-by":"crossref","unstructured":"Kincaid JP , Robert p , et al . Derivation of New Readability Formulas (Automated Readability Index, Fog Count and Flesch Reading Ease Formula) for Navy Enlisted Personnel. Fort Belvoir, VA: Defense Technical Information Center, 1975. Available: http:\/\/www.dtic.mil\/docs\/citations\/ADA006655","DOI":"10.21236\/ADA006655"},{"key":"2024101503100694000_108.10.1470.19","first-page":"639","article-title":"SMOG Grading-a New Readability Formula","volume":"12","author":"Mc Laughlin","year":"1969","journal-title":"J Read"},{"key":"2024101503100694000_108.10.1470.20","unstructured":"OpenAI . OpenAI platform. prompt engineering. n.d. Available: https:\/\/platform.openai.com"},{"key":"2024101503100694000_108.10.1470.21","doi-asserted-by":"publisher","DOI":"10.1016\/j.iotcps.2023.04.003"},{"key":"2024101503100694000_108.10.1470.22","doi-asserted-by":"publisher","DOI":"10.1136\/jech.53.2.105"},{"key":"2024101503100694000_108.10.1470.23","doi-asserted-by":"crossref","first-page":"1437","DOI":"10.1001\/jamaoncol.2023.2947","article-title":"Assessment of Artificial Intelligence Chatbot Responses to Top Searched Queries About Cancer","volume":"9","author":"Pan","year":"2023","journal-title":"JAMA Oncol"},{"key":"2024101503100694000_108.10.1470.24","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1016\/j.pec.2014.05.027","article-title":"Development of the patient education materials assessment tool (pemat): a new measure of understandability and actionability for print and audiovisual patient information","volume":"96","author":"Shoemaker","year":"2014","journal-title":"Pat Educ Couns"},{"key":"2024101503100694000_108.10.1470.25","doi-asserted-by":"crossref","unstructured":"Veeramani A , Johnson AR , Lee BT , et al . Readability, understandability, usability, and cultural sensitivity of online patient educational materials (pems) for lower extremity reconstruction: a cross-sectional study. Plast Surg (Oakv) 2022. doi:10.1177\/22925503221120548","DOI":"10.1177\/22925503221120548"},{"key":"2024101503100694000_108.10.1470.26","doi-asserted-by":"crossref","first-page":"564","DOI":"10.1016\/j.eururo.2018.10.056","article-title":"Dissemination of misinformative and biased information about prostate cancer on youTube","volume":"75","author":"Loeb","year":"2019","journal-title":"Eur Urol"},{"key":"2024101503100694000_108.10.1470.27","unstructured":"Insights C . The value of google result positioning. Westborough:Chitika Inc; 2013. Available: https:\/\/research.chitika.com\/wp-content\/uploads\/2022\/02\/chitikainsights-valueofgoogleresultspositioning.pdf"},{"key":"2024101503100694000_108.10.1470.28","doi-asserted-by":"crossref","DOI":"10.1016\/j.xops.2023.100394","article-title":"Generative artificial intelligence through chatgpt and other large language models in ophthalmology: clinical applications and challenges","volume":"3","author":"Tan","year":"2023","journal-title":"Ophthalmol Sci"},{"key":"2024101503100694000_108.10.1470.29","unstructured":"OpenAI . OpenAI platform. Models; 2024. Available: https:\/\/platform.openai.com"},{"key":"2024101503100694000_108.10.1470.30","doi-asserted-by":"crossref","first-page":"507","DOI":"10.1001\/jamainternmed.2023.1832","article-title":"Medicine in the era of artificial intelligence: hey chatbot, write me an H&P","volume":"183","author":"Brender","year":"2023","journal-title":"JAMA Intern Med"},{"key":"2024101503100694000_108.10.1470.31","doi-asserted-by":"crossref","first-page":"819","DOI":"10.1001\/jamaophthalmol.2023.3119","article-title":"Evaluation and comparison of ophthalmic scientific abstracts and references by current artificial intelligence chatbots","volume":"141","author":"Hua","year":"2023","journal-title":"JAMA Ophthalmol"},{"key":"2024101503100694000_108.10.1470.32","unstructured":"Teixeira PEP , Pacheco-Barrios K , Almarie B . The use of large language models in science: opportunities and challenges. Princ Pract Clin Res 2015;1\u20134."},{"key":"2024101503100694000_108.10.1470.33","doi-asserted-by":"crossref","DOI":"10.1001\/jamanetworkopen.2019.2622","article-title":"Level and Prevalence of Spin in Published Cardiovascular Randomized Clinical Trial Reports With Statistically Nonsignificant Primary Outcomes: a Systematic Review","volume":"2","author":"Khan","year":"2019","journal-title":"JAMA Netw Open"},{"key":"2024101503100694000_108.10.1470.34","first-page":"227","article-title":"Childhood blindness in the context of VISION 2020--the right to sight","volume":"79","author":"Gilbert","year":"2001","journal-title":"Bull World Health Organ"},{"key":"2024101503100694000_108.10.1470.35","unstructured":"StatCounter Global . Desktop search engine market share worldwide. 2024. Available: https:\/\/gs.statcounter.com\/search-engine-market-share\/desktop\/worldwide\/"}],"container-title":["British Journal of Ophthalmology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bjo-2024-325252","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,15]],"date-time":"2024-10-15T10:14:35Z","timestamp":1728987275000},"score":1,"resource":{"primary":{"URL":"https:\/\/bjo.bmj.com\/lookup\/doi\/10.1136\/bjo-2024-325252"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,22]]},"references-count":35,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2024,9,20]]},"published-print":{"date-parts":[[2024,10]]}},"alternative-id":["10.1136\/bjo-2024-325252"],"URL":"https:\/\/doi.org\/10.1136\/bjo-2024-325252","relation":{},"ISSN":["0007-1161","1468-2079"],"issn-type":[{"value":"0007-1161","type":"print"},{"value":"1468-2079","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,22]]}}}