{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T07:54:46Z","timestamp":1790927686816,"version":"4.1.0"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T00:00:00Z","timestamp":1783468800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T00:00:00Z","timestamp":1790899200000},"content-version":"vor","delay-in-days":86,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Retin Vitr"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Ophthalmological reports are often written at a complexity level that exceeds the reading ability of many patients. Large language models (LLMs) may help simplify these texts, but their performance depends on prompt design and must preserve clinical fidelity. This study evaluated whether different prompting strategies improve the readability and safety of simplified ophthalmological reports.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We analyzed 443 de-identified reports from a tele-ophthalmology platform, including 280 retinal fundus and 163 ocular ultrasound reports. Each report was simplified by four LLMs (GPT-3.5, GPT-4.0, Gemini, and Copilot) using three prompts: a basic command, a patient-oriented prompt, and a targeted 7th-grade reading level prompt. Readability was measured with the average Readability Grade Level (aRGL). A representative eligible subset of the generated texts was independently evaluated by two third-year ophthalmology residents, and each selected response underwent independent review by both evaluators, with disagreements resolved by a board-certified retina ophthalmologist. Outcomes included factual accuracy, information completeness, and potential for harm.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The original reports were highly complex, with a median aRGL of 13.8 overall, 11.6 for fundus reports, and 15.4 for ocular ultrasound reports. All LLMs improved readability scores to varying degrees. Prompt engineering was a major determinant of performance, and the targeted 7th-grade prompt produced the best results across models. Copilot, Gemini, and GPT-4.0 achieved median aRGL values closest to the recommended patient-facing reading level, while GPT-3.5 showed weaker performance in some comparisons. Clinical validation showed substantial agreement between raters (kappa range, 0.70\u20130.97). After adjudication, 91% of simplified texts were factually accurate, 86% retained all critical information, and 95% showed no potential for harm.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>LLMs can simplify ophthalmological reports while preserving clinical fidelity, but performance depends strongly on prompt specificity. These tools show promise for patient-facing communication, although human oversight remains essential.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s40942-026-00896-1","type":"journal-article","created":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:14:59Z","timestamp":1783527299000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Large language model based simplification of ophthalmological clinical and ancillary results for patient readability"],"prefix":"10.1186","volume":"12","author":[{"given":"Alexandre Ant\u00f4nio Marques","family":"Rosa","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francisco Vin\u00edcius Moraes","family":"de Souza","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jos\u00e9 Leandro Nascimento","family":"da Silva","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rafael","family":"Scherer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Valberto Monteiro","family":"Nunes","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leandro Cabral","family":"Zacharias","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gustavo Barreto","family":"Melo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taurino dos Santos Rodrigues","family":"Neto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,8]]},"reference":[{"key":"896_CR1","doi-asserted-by":"crossref","unstructured":"Abrahamsson E, et al. Medical text simplification using synonym replacement: Adapting assessment of word difficulty to a compounding language. In: Proceedings of the 3rd Workshop on Predicting and Improving Text Readability for Target Reader Populations (PITR); 2014; Gothenburg, Sweden. Gothenburg: Assoc Comput Ling. 2014;48\u201357. Available from https:\/\/aclanthology.org\/W14-1207.","DOI":"10.3115\/v1\/W14-1207"},{"key":"896_CR2","doi-asserted-by":"crossref","unstructured":"n den Bercken L, Sips RJ, Lofi C. Evaluating neural text simplification in the medical domain. In: Proceedings of the Web Conference. 2019; San Francisco, CA. New York: ACM; 2019;3258-64.","DOI":"10.1145\/3308558.3313630"},{"issue":"5","key":"896_CR3","doi-asserted-by":"publisher","first-page":"840","DOI":"10.1093\/her\/cym069","volume":"23","author":"JA Manganello","year":"2008","unstructured":"Manganello JA. Health literacy and adolescents: a framework and agenda for future research. Health Educ Res. 2008;23(5):840\u20137.","journal-title":"Health Educ Res"},{"key":"896_CR4","volume-title":"Health literacy and patient safety: Help patients understand","author":"BD Weiss","year":"2007","unstructured":"Weiss BD. Health literacy and patient safety: Help patients understand. 2nd ed. Chicago: American Medical Association Foundation; 2007.","edition":"2"},{"issue":"1","key":"896_CR5","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1186\/s12931-022-02290-5","volume":"23","author":"I Poureslami","year":"2022","unstructured":"Poureslami I, et al. Health literacy in asthma and chronic obstructive pulmonary disease (COPD) care: a narrative review and future directions. Respir Res. 2022;23(1):361.","journal-title":"Respir Res"},{"issue":"3","key":"896_CR6","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1592\/phco.22.5.282.33191","volume":"22","author":"MR Andrus","year":"2002","unstructured":"Andrus MR, Roth MT. Health literacy: a review. Pharmacotherapy. 2002;22(3):282\u2013302.","journal-title":"Pharmacotherapy"},{"issue":"5","key":"896_CR7","doi-asserted-by":"publisher","first-page":"1563","DOI":"10.1590\/1413-81232023285.14562022","volume":"28","author":"F Peres","year":"2023","unstructured":"Peres F, Alfabetiza\u00e7\u00e3o. letramento ou literacia em sa\u00fade? Traduzindo e aplicando o conceito de health literacy no Brasil. Cienc Saude Colet. 2023;28(5):1563\u201373.","journal-title":"Cienc Saude Colet"},{"key":"896_CR8","unstructured":"Instituto Paulo Montenegro. Indicador de analfabetismo funcional: INAF Brasil 2018 \u2013 Resultados preliminares. S\u00e3o Paulo: Instituto Paulo Montenegro. 2018. Available from: https:\/\/drive.google.com\/file\/d\/1ez-6jrlrRRUm9JJ3MkwxEUffltjCTEI6\/view."},{"key":"896_CR9","unstructured":"Instituto Pr\u00f3-Livro. Retratos da leitura no Brasil. 5th ed. S\u00e3o Paulo: Instituto Pr\u00f3-Livro. 2020. Available from: https:\/\/prolivro.org.br\/wp-content\/uploads\/2020\/09\/5a_edicao_Retratos_da_Leitura_no_Brasil_IPL-compactado.pdf."},{"key":"896_CR10","unstructured":"Instituto Nacional de Estudos e Pesquisas Educacionais An\u00edsio Teixeira (Inep). Brasil no Pisa 2018. Bras\u00edlia: Inep. 2020. Available from: https:\/\/download.inep.gov.br\/publicacoes\/institucionais\/avaliacoes_e_exames_da_educacao_basica\/relatorio_brasil_no_pisa_2018.pdf."},{"key":"896_CR11","unstructured":"International Organization for Standardization. ISO 24495-1: plain language - part 1: governing principles and guidelines. Geneva: ISO. 2023. Available from: https:\/\/www.iso.org\/standard\/78907.html."},{"key":"896_CR12","unstructured":"Zilio L et al. A lexical simplification tool for promoting health literacy. In: Proceedings of the 14th International Conference on advances in computer-human interactions; 2021 Feb 18\u201322; Valencia, Spain. Wilmington: IARIA; 2021; 70\u2009\u2013\u20096."},{"issue":"4","key":"896_CR13","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1136\/svn-2017-000101","volume":"2","author":"F Jiang","year":"2017","unstructured":"Jiang F, Jiang Y, Zhi H. Artificial intelligence in healthcare: past, present and future. Stroke Vasc Neurol. 2017;2(4):230\u201343.","journal-title":"Stroke Vasc Neurol"},{"key":"896_CR14","unstructured":"Pinto SCS. Processamento de linguagem natural e extra\u00e7\u00e3o de conhecimento [dissertation]. Coimbra: Universidade de Coimbra; 2015. Available from: http:\/\/hdl.handle.net\/10316\/35676."},{"issue":"7553","key":"896_CR15","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"I Goodfellow","year":"2016","unstructured":"Goodfellow I, Bengio Y, Courville A. Deep learning. Nature. 2016;521(7553):436\u201344.","journal-title":"Nature"},{"key":"896_CR16","volume-title":"Introdu\u00e7\u00e3o \u00e0 intelig\u00eancia artificial","author":"MH Santos","year":"2021","unstructured":"Santos MH. Introdu\u00e7\u00e3o \u00e0 intelig\u00eancia artificial. S\u00e3o Paulo: Editora Saraiva; 2021."},{"issue":"4","key":"896_CR17","first-page":"e170","volume":"5","author":"SR Ali","year":"2023","unstructured":"Ali SR, et al. Using ChatGPT to write patient clinic letters. Lancet Digit Health. 2023;5(4):e170\u20132.","journal-title":"Lancet Digit Health"},{"key":"896_CR18","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1016\/j.ijcard.2019.06.039","volume":"293","author":"P Dunn","year":"2019","unstructured":"Dunn P, Hazzard E. Technology approaches to digital health literacy. Int J Cardiol. 2019;293:294\u20136.","journal-title":"Int J Cardiol"},{"key":"896_CR19","unstructured":"RedCheck\u00ae [Internet]. Available from: https:\/\/redcheck.com.br."},{"key":"896_CR20","unstructured":"ALT - An\u00e1lise. de Legibilidade textual [Internet]. Available from: https:\/\/legibilidade.com\/."},{"key":"896_CR21","unstructured":"Weiss BD. Health literacy and patient safety: help patients understand: manual for clinicians. Chicago: AMA Foundation; 2007. Available from: http:\/\/www.hhvna.com\/files\/Courses\/HealthLiteracy\/Health_Literacy_Manual_AMA_Revised.pdf."},{"issue":"1","key":"896_CR22","doi-asserted-by":"publisher","first-page":"111","DOI":"10.2214\/AJR.14.13086","volume":"204","author":"DR Hansberry","year":"2015","unstructured":"Hansberry DR, Agarwal N, Baker SR. Health literacy and online educational resources: an opportunity to educate patients. AJR Am J Roentgenol. 2015;204(1):111\u20136.","journal-title":"AJR Am J Roentgenol"},{"key":"896_CR23","unstructured":"Instituto Nacional de Estudos e Pesquisas Educacionais An\u00edsio Teixeira (Inep). Brasil no PIRLS 2021: Sum\u00e1rio Executivo. Bras\u00edlia: Inep. 2023. Available from: https:\/\/download.inep.gov.br\/pirls\/2021\/brasil_sumario_executivo.pdf."},{"issue":"9","key":"896_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3649447","volume":"56","author":"WX Zhao","year":"2024","unstructured":"Zhao WX, Zhou K, Li J, et al. A Survey of Large Language Models. ACM Comput Surv. 2024;56(9):1\u201336.","journal-title":"ACM Comput Surv"},{"key":"896_CR25","unstructured":"Fan L, Li L, Ma Z, Lee S, Yu H, Hemphill L. A Bibliometric Review of large language models research from 2017 to 2023. arXiv [Preprint]. 2023 [cited 2024 Apr 2]:arXiv:2304.02021. Available from: https:\/\/arxiv.org\/abs\/2304.02021."},{"key":"896_CR26","unstructured":"Microsoft Support. Copilot no Bing: nossa abordagem para IA respons\u00e1vel. Available from:https:\/\/support.microsoft.com\/pt-br\/topic\/copilot-no-bing-nossa-abordagem-para-ia-respons%C3%A1vel-45b5eae8-7466-43e1-ae98-b48f8ff8fd44"},{"key":"896_CR27","unstructured":"Jeblick K, Schachtner B, Dexl J, et al. ChatGPT makes medicine easy to swallow: an exploratory case study on simplified radiology reports. arXiv [Preprint]. 2022 [cited 2024 Apr 2]:arXiv:2212.14882. Available from: https:\/\/arxiv.org\/abs\/2212.14882."}],"container-title":["International Journal of Retina and Vitreous"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s40942-026-00896-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40942-026-00896-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40942-026-00896-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T07:20:30Z","timestamp":1790925630000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s40942-026-00896-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,8]]},"references-count":27,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["896"],"URL":"https:\/\/doi.org\/10.1186\/s40942-026-00896-1","relation":{},"ISSN":["2056-9920"],"issn-type":[{"value":"2056-9920","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,8]]},"assertion":[{"value":"28 April 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"133"}}