{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,18]],"date-time":"2026-11-18T00:49:25Z","timestamp":1794962965161,"version":"4.9.1"},"reference-count":0,"publisher":"International Virtual Ophthalmic Research Center","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Med Hypothesis Discov Innov Ophthalmol"],"abstract":"<jats:p>Background: Artificial intelligence (AI) is rapidly transforming vision sciences, leveraging the imaging-rich nature of ophthalmology and optometry to address the global burden of ocular diseases. AI\u2019s ability to analyze complex imaging and clinical data offers unprecedented improvements in diagnosis, management, and patient outcomes. This narrative review aims to explore the current and emerging opportunities of AI in vision sciences, critically examine the associated challenges, and discuss the ethical implications of its integration into clinical practice.\r\nMethods: A narrative review was conducted by searching PubMed\/MEDLINE and Google Scholar for English-language articles published from January 1, 2005, to March 31, 2025. Studies with any design (clinical trials, observational studies, validation studies, systematic reviews, and meta-analyses) on AI applications in ophthalmology and optometry, focusing on diagnostic performance, clinical integration, and ethical considerations were included. Articles not related to AI in vision care were excluded.\r\nResults: AI has achieved high diagnostic accuracy across ocular domains. In the cornea and anterior segment, AI models analyzing Scheimpflug tomography and corneal biomechanics detect keratoconus with over 98% sensitivity and 99.6% accuracy, including subclinical cases. For cataract surgery, machine learning-based intraocular lens formulas such as Kane and ZEISS AI reduce refractive errors, achieving mean absolute errors below 0.30 diopters, especially in highly myopic eyes. Retinal AI systems like EyeArt and IDx-DR autonomously detect diabetic retinopathy with sensitivities above 95%, while deep learning models predict age-related macular degeneration progression with an area under the ROC curve exceeding 0.90. In glaucoma, fundus and optical coherence tomography based AI models reach pooled sensitivity and specificity above 90%, but performance varies by disease stage and population diversity. AI also advances strabismus detection, amblyopia risk prediction, and myopia progression forecasting using facial analysis and biometric data. Key challenges include dataset bias, limited external validation, regulatory hurdles, and ethical issues such as transparency and equitable access.\r\nConclusions: AI is rapidly transforming vision sciences by improving diagnostic accuracy, streamlining clinical workflows, and broadening access to quality eye care, particularly in underserved regions. Its integration into ophthalmology and optometry holds significant promise for enhancing patient outcomes and optimizing healthcare delivery. However, to fully harness AI\u2019s transformative potential, sustained multidisciplinary collaboration is essential\u2014bringing together clinicians, data scientists, ethicists, and policymakers. Equally important are rigorous validation processes, transparency in algorithm development, and strong ethical oversight to mitigate risks such as bias, data misuse, and unequal access. Responsible implementation will be key to ensuring AI serves all populations equitably.<\/jats:p>","DOI":"10.51329\/mehdiophthal1517","type":"journal-article","created":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T13:53:35Z","timestamp":1747144415000},"page":"255-272","source":"Crossref","is-referenced-by-count":37,"title":["Artificial intelligence in ophthalmology: opportunities, challenges, and ethical considerations"],"prefix":"10.51329","volume":"14","author":[{"given":"Kimia","family":"Kazemzadeh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"28503","published-online":{"date-parts":[[2025,5,10]]},"container-title":["Medical hypothesis discovery and innovation in ophthalmology"],"original-title":[],"link":[{"URL":"https:\/\/mehdijournal.com\/index.php\/mehdiophthalmol\/article\/download\/1229\/892","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/mehdijournal.com\/index.php\/mehdiophthalmol\/article\/download\/1229\/892","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T13:53:36Z","timestamp":1747144416000},"score":1,"resource":{"primary":{"URL":"https:\/\/mehdijournal.com\/index.php\/mehdiophthalmol\/article\/view\/1229"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,10]]},"references-count":0,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,4,30]]}},"URL":"https:\/\/doi.org\/10.51329\/mehdiophthal1517","relation":{},"ISSN":["2322-3219"],"issn-type":[{"value":"2322-3219","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,10]]}}}