{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,29]],"date-time":"2026-08-29T08:16:52Z","timestamp":1787991412859,"version":"build-2784847793"},"reference-count":26,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2026,8,29]],"date-time":"2026-08-29T00:00:00Z","timestamp":1787961600000},"content-version":"vor","delay-in-days":240,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82271118"],"award-info":[{"award-number":["82271118"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Journal of Ophthalmology"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>To evaluate the guideline knowledge alignment of two large language models (LLMs), GPT\u20105.5 Instant and DeepSeek\u2010V4, and to determine their preclinical reliability as reference tools in refractive surgery.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Using the 38 evidence\u2010based recommendations of the international keratorefractive lenticule extraction (KLEx) guidelines as the gold standard, both LLMs were evaluated in their default configurations. Two ophthalmologists independently assessed the clinical safety and medical accuracy of the model responses using a 5\u2010point Likert scale (1\u20135 points). Agreement between each model\u2019s recommendation strength and the guideline was quantified by intraclass correlation coefficient (ICC), structural reliability by the DISCERN scale, and readability by the Flesch Reading Ease (FRE) and Flesch\u2013Kincaid Grade Level (FKGL) indices.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Likert ratings did not differ between GPT\u20105.5 Instant (4.96\u2009\u00b1\u20090.206) and DeepSeek\u2010V4 (4.89\u2009\u00b1\u20090.385;\n                      <jats:italic>p<\/jats:italic>\n                      = 0.134). Across 114 independent generations, the ICC for agreement with the guideline was 0.884 (95% CI, 0.836\u20130.918) for GPT\u20105.5 Instant and 0.739 (0.640\u20130.813) for DeepSeek\u2010V4 (both\n                      <jats:italic>p<\/jats:italic>\n                      &lt; 0.001). DISCERN scores were 70.18\u2009\u00b1\u20095.16 and 68.05\u2009\u00b1\u20095.41 (\n                      <jats:italic>p<\/jats:italic>\n                      = 0.085); FRE, 9.93\u2009\u00b1\u20098.33 and 3.74\u2009\u00b1\u20095.24 (\n                      <jats:italic>p<\/jats:italic>\n                      &lt; 0.001); and FKGL, 16.07\u2009\u00b1\u20092.21 and 18.95\u2009\u00b1\u20091.96 (\n                      <jats:italic>p<\/jats:italic>\n                      &lt; 0.001).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Both models aligned closely with the guidelines, with significant concordance in GRADE\u2010based recommendation strength. They may serve as preclinical reference tools in refractive surgery but not as a substitute for specialist judgment.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1155\/joph\/4163980","type":"journal-article","created":{"date-parts":[[2026,8,29]],"date-time":"2026-08-29T07:45:21Z","timestamp":1787989521000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Assessing Guideline Knowledge Alignment of Large Language Models in Ophthalmology: A Preclinical Benchmarking Study on KLEx Evidence\u2010Based Guidelines"],"prefix":"10.1155","volume":"2026","author":[{"given":"Hongxia","family":"Lu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7368-4621","authenticated-orcid":false,"given":"Yan","family":"Huo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruisi","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhengyuan","family":"Qu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yutong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengjin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0588-9753","authenticated-orcid":false,"given":"Haohan","family":"Zou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1257-6635","authenticated-orcid":false,"given":"Yan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,8,29]]},"reference":[{"key":"e_1_2_14_1_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2016.01.006"},{"key":"e_1_2_14_2_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2024.11.016"},{"key":"e_1_2_14_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(18)33209-4"},{"key":"e_1_2_14_4_2","doi-asserted-by":"publisher","DOI":"10.3928\/1081597X-20220623-01"},{"key":"e_1_2_14_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2017.10.003"},{"key":"e_1_2_14_6_2","doi-asserted-by":"publisher","DOI":"10.3928\/1081597X-20231010-0"},{"key":"e_1_2_14_7_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12886-022-02333-x"},{"key":"e_1_2_14_8_2","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare13060603"},{"key":"e_1_2_14_9_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-03423-7"},{"key":"e_1_2_14_10_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06291-2"},{"key":"e_1_2_14_11_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-025-01684-1"},{"key":"e_1_2_14_12_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11604-024-01552-0"},{"key":"e_1_2_14_13_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-025-02197-w"},{"key":"e_1_2_14_14_2","volume-title":"GPT-5.5 Instant System Card","author":"OpenAI","year":"2026"},{"key":"e_1_2_14_15_2","volume-title":"DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence","author":"DeepSeek A. I.","year":"2026"},{"key":"e_1_2_14_16_2","doi-asserted-by":"publisher","DOI":"10.1111\/jep.13659"},{"key":"e_1_2_14_17_2","doi-asserted-by":"publisher","DOI":"10.1136\/jech.53.2.105"},{"key":"e_1_2_14_18_2","doi-asserted-by":"publisher","DOI":"10.7150\/ijms.111780"},{"key":"e_1_2_14_19_2","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2024.21700"},{"key":"e_1_2_14_20_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-024-01258-7"},{"key":"e_1_2_14_21_2","volume-title":"GPT-5.5 Instant: Smarter, Clearer, and More Personalized","author":"OpenAI","year":"2026"},{"key":"e_1_2_14_22_2","volume-title":"Deepseekmoe: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models","author":"Dai D.","year":"2024"},{"key":"e_1_2_14_23_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2422455122"},{"key":"e_1_2_14_24_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.oret.2023.05.022"},{"key":"e_1_2_14_25_2","doi-asserted-by":"publisher","DOI":"10.1097\/CORR.0000000000002668"},{"key":"e_1_2_14_26_2","doi-asserted-by":"publisher","DOI":"10.1093\/eurjcn\/zvad087"}],"container-title":["Journal of Ophthalmology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/joph\/4163980","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1155\/joph\/4163980","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/joph\/4163980","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,29]],"date-time":"2026-08-29T07:45:23Z","timestamp":1787989523000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/joph\/4163980"}},"subtitle":[],"editor":[{"given":"Kunbei","family":"Lai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":26,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1155\/joph\/4163980"],"URL":"https:\/\/doi.org\/10.1155\/joph\/4163980","archive":["Portico"],"relation":{},"ISSN":["2090-004X","2090-0058"],"issn-type":[{"value":"2090-004X","type":"print"},{"value":"2090-0058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"2025-11-25","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-28","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-08-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"4163980"}}