{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T14:22:09Z","timestamp":1787840529224,"version":"build-2784847793"},"reference-count":15,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"4","license":[{"start":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:00:00Z","timestamp":1750204800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10]]},"abstract":"<jats:title>Abstract:<\/jats:title>\n                  <jats:sec>\n                    <jats:title>PURPOSE:<\/jats:title>\n                    <jats:p>This study aims to evaluate and compare the performance of generative pretrained transformer (GPT)-4o and GPT-4 in answering Taiwan\u2019s National Medical Licensing Examination (NMLE) ophthalmology questions from 2014 to 2023, focusing on both answer accuracy and explanation quality.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>MATERIALS AND METHODS:<\/jats:title>\n                    <jats:p>A total of 169 ophthalmology questions from Taiwan\u2019s NMLE over the past decade were selected. GPT-4o and GPT-4 were tested on each question, and their performance was measured by correct answers and explanations. The results were categorized by ophthalmologic subspecialty and analyzed using statistical methods to determine significant differences between the two models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>RESULTS:<\/jats:title>\n                    <jats:p>\n                      GPT-4o achieved a significantly higher overall correct answer rate (92.9%) compared to GPT-4 (69.2%) across all ophthalmology questions from 2014 to 2023 (\n                      <jats:italic toggle=\"yes\">P<\/jats:italic>\n                      &lt; 0.01). GPT-4o outperformed GPT-4 in most subspecialties, including retina (95.8% vs. 58.3%,\n                      <jats:italic toggle=\"yes\">P<\/jats:italic>\n                      &lt; 0.01), external disease and cornea (96.3% vs. 77.8%,\n                      <jats:italic toggle=\"yes\">P<\/jats:italic>\n                      = 0.04), and neuro-ophthalmology (87.5% vs. 50%,\n                      <jats:italic toggle=\"yes\">P<\/jats:italic>\n                      = 0.02). GPT-4o and GPT-4 performed similarly in glaucoma and uveitis, with no significant differences observed. In terms of explanation quality, GPT-4o provided accurate explanations for 90.7% of the questions, with the highest accuracy in pediatric ophthalmology and strabismus (100%) and the lowest in uveitis (83.3%).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>CONCLUSION:<\/jats:title>\n                    <jats:p>GPT-4o exhibited superior performance in both answering and explaining ophthalmology questions from Taiwan\u2019s NMLE compared to GPT-4. These results suggest that GPT-4o may be a more reliable tool for educational and diagnostic purposes in ophthalmology.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.4103\/tjo.tjo-d-24-00164","type":"journal-article","created":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T07:00:31Z","timestamp":1750230031000},"page":"647-654","update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":0,"title":["Assessing GPT-4o and GPT-4 in answering and explaining ophthalmology examination questions from Taiwan\u2019s medical licensing test"],"prefix":"10.4103","volume":"15","author":[{"given":"Chen-Wei","family":"Lin","sequence":"first","affiliation":[{"name":"Department of Ophthalmology, Chang Gung Memorial Hospital, Chiayi, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chau-Yin","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Chang Gung Memorial Hospital, Chiayi, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pei-Lun","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Chang Gung Memorial Hospital, Chiayi, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ching-Lung","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Chang Gung Memorial Hospital, Chiayi, Taiwan"},{"name":"Department of Optometry, Chung Hwa University of Medical Technology, Tainan, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chien-Hsiung","family":"Lai","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Chang Gung Memorial Hospital, Chiayi, Taiwan"},{"name":"Department of Medicine, Chang Gung University, Taoyuan, Taiwan"},{"name":"Department of Nursing, Chang Gung University of Science and Technology, Chiayi, Taiwan"},{"name":"School of Traditional Chinese Medicine, College of Medicine, Chang Gung University, Taoyuan, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","published-online":{"date-parts":[[2025,6,18]]},"reference":[{"key":"R1-20251223","doi-asserted-by":"crossref","first-page":"100324","DOI":"10.1016\/j.xops.2023.100324","article-title":"Evaluating the performance of ChatGPT in ophthalmology:An analysis of its successes and shortcomings","volume":"3","author":"Antaki","year":"2023","journal-title":"Ophthalmol Sci"},{"key":"R2-20251223","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1001\/jamaophthalmol.2024.0017","article-title":"Accuracy of an artificial intelligence Chatbot's interpretation of clinical ophthalmic images","volume":"142","author":"Mihalache","year":"2024","journal-title":"JAMA Ophthalmol"},{"key":"R3-20251223","doi-asserted-by":"crossref","first-page":"589","DOI":"10.1001\/jamaophthalmol.2023.1144","article-title":"Performance of an artificial intelligence chatbot in ophthalmic knowledge assessment","volume":"141","author":"Mihalache","year":"2023","journal-title":"JAMA Ophthalmol"},{"key":"R4-20251223","doi-asserted-by":"crossref","first-page":"410","DOI":"10.3390\/educsci13040410","article-title":"What is the impact of ChatGPT on education?A rapid review of the literature","volume":"13","author":"Lo","year":"2023","journal-title":"Educ Sci"},{"key":"R5-20251223","doi-asserted-by":"crossref","first-page":"14886","DOI":"10.31004\/joe.v5i4.2563","article-title":"Analysing the role of ChatGPT in improving student productivity in higher education","volume":"5","author":"Fauzi","year":"2023","journal-title":"Journal on Education"},{"key":"R6-20251223","doi-asserted-by":"crossref","first-page":"20552076241277021","DOI":"10.1177\/20552076241277021","article-title":"Evaluation of the quality and readability of ChatGPT responses to frequently asked questions about myopia in traditional Chinese language","volume":"10","author":"Chang","year":"2024","journal-title":"Digit Health"},{"key":"R7-20251223","doi-asserted-by":"crossref","first-page":"e50842","DOI":"10.2196\/50842","article-title":"Performance of ChatGPT on ophthalmology-related questions across various examination levels:Observational study","volume":"10","author":"Haddad","year":"2024","journal-title":"JMIR Med Educ"},{"key":"R8-20251223","first-page":"e49903","article-title":"Performance of ChatGPT in board examinations for specialists in the Japanese Ophthalmology Society","volume":"15","author":"Sakai","year":"2023","journal-title":"Cureus"},{"key":"R9-20251223","first-page":"08774","article-title":"(2023). Gpt-4 technical report","author":"Achiam","year":"2303","journal-title":"arXiv preprint arXiv"},{"key":"R10-20251223","article-title":"Gpt-4o:The cutting-edge advancement in multimodal llm","author":"Islam","year":"2024","journal-title":"Authorea Preprints"},{"key":"R11-20251223","doi-asserted-by":"crossref","first-page":"6159","DOI":"10.1080\/10494820.2023.2253858","article-title":"The opportunities and challenges of ChatGPT in education","volume":"32","author":"Adeshola","year":"2024","journal-title":"Interactive Learning Environments"},{"key":"R12-20251223","doi-asserted-by":"crossref","first-page":"52","DOI":"10.61969\/jai.1337500","article-title":"Education in the era of generative artificial intelligence (AI):Understanding the potential benefits of ChatGPT in promoting teaching and learning","volume":"7","author":"Baidoo-Anu","year":"2023","journal-title":"J AI"},{"key":"R13-20251223","doi-asserted-by":"crossref","first-page":"2345","DOI":"10.1007\/s00417-023-06363-z","article-title":"Diagnostic capabilities of ChatGPT in ophthalmology","volume":"262","author":"Shemer","year":"2024","journal-title":"Graefes Arch Clin Exp Ophthalmol"},{"key":"R14-20251223","doi-asserted-by":"crossref","first-page":"100394","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":"R15-20251223","doi-asserted-by":"crossref","first-page":"798","DOI":"10.1001\/jamaophthalmol.2023.2754","article-title":"Performance of an upgraded artificial intelligence Chatbot for ophthalmic knowledge assessment","volume":"141","author":"Mihalache","year":"2023","journal-title":"JAMA Ophthalmol"}],"container-title":["Taiwan Journal of Ophthalmology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.ovid.com\/10.4103\/tjo.TJO-D-24-00164","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T13:24:32Z","timestamp":1787837072000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ovid.com\/10.4103\/tjo.TJO-D-24-00164"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,18]]},"references-count":15,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.4103\/tjo.tjo-d-24-00164","relation":{},"ISSN":["2211-5056","2211-5072"],"issn-type":[{"value":"2211-5056","type":"print"},{"value":"2211-5072","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,18]]},"assertion":[{"value":"2024-12-14","name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-03-04","name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}}]}}