{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T15:28:47Z","timestamp":1793374127893,"version":"4.5.0"},"reference-count":12,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"Suppl 1","content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,1]]},"abstract":"<jats:sec>\n                    <jats:title>Purpose:<\/jats:title>\n                    <jats:p>Artificial intelligence (AI) is often trained on images without ocular co-morbidities, limiting its generalizability. This study aims to evaluate the accuracy of a convolutional neural network (CNN) applied to color fundus photos (CFPs) with simulated cataracts (SCs) in detecting diabetic retinopathy (DR).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods:<\/jats:title>\n                    <jats:p>A database of 3662 CFPs (from Asia Pacific Tele-Ophthalmology Society (APTOS) 2019) was used. Using transfer learning, a CNN was trained to classify the training images as either DR or non-DR. The CNN was then applied to classify the testing images after an SC was applied, using varying degrees of Gaussian blur.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results:<\/jats:title>\n                    <jats:p>Accuracy without SC was 97.0%, sensitivity (Sn) 95.7%, specificity (Sp) 98.3%. For mild SC, accuracy was 93.1%, Sn 91.8%, Sp 94.3%. For moderate SC, accuracy was 62.8%, Sn 31.4%, Sp 95.2%. For severe SC, accuracy was 53.5%, Sn 11.8%, Sp 96.5%.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion:<\/jats:title>\n                    <jats:p>SCs significantly impaired AI accuracy. To prepare AI for clinical use, cataracts and other real-world clinical challenges affecting image quality must be accounted for.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.4103\/ijo.ijo_1163_23","type":"journal-article","created":{"date-parts":[[2023,12,22]],"date-time":"2023-12-22T01:00:20Z","timestamp":1703206820000},"page":"S42-S45","update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":13,"title":["Effect of simulated cataract on the accuracy of artificial intelligence in detecting diabetic retinopathy in color fundus photos"],"prefix":"10.4103","volume":"72","author":[{"given":"Alexander B","family":"Crane","sequence":"first","affiliation":[{"name":"Department of Ophthalmology and Visual Sciences, Rutgers New Jersey Medical School, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hassaam S","family":"Choudhry","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology and Visual Sciences, Rutgers New Jersey Medical School, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammad H","family":"Dastjerdi","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology and Visual Sciences, Rutgers New Jersey Medical School, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","published-online":{"date-parts":[[2023,12,22]]},"reference":[{"key":"R1-20260508","doi-asserted-by":"crossref","first-page":"e2953","DOI":"10.1002\/cnm.2953","article-title":"Machine learning-based diagnosis of melanoma using macro images","volume":"34","author":"Gautam","year":"2018","journal-title":"Int J Numer Method Biomed Eng"},{"key":"R2-20260508","first-page":"1555","article-title":"Application of artificial intelligence in ophthalmology","volume":"11","author":"Du","year":"2018","journal-title":"Int J Ophthalmol"},{"key":"R3-20260508","doi-asserted-by":"crossref","first-page":"240","DOI":"10.1016\/j.jaad.2021.07.073","article-title":"Image quality issues in teledermatology: A comparative analysis of artificial intelligence solutions","volume":"87","author":"Maier","year":"2022","journal-title":"J Am Acad Dermatol"},{"key":"R4-20260508","first-page":"1","article-title":"Enhanced artificial intelligence system for diagnosing and predicting breast cancer using deep learning","volume":"11","author":"Alfifi","year":"2020","journal-title":"Int J Adv Comput Sci Appl"},{"key":"R5-20260508","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1016\/j.radi.2014.06.004","article-title":"A method to investigate image blurring due to mammography machine compression paddle movement","volume":"21","author":"Ma","year":"2015","journal-title":"Radiography"},{"key":"R6-20260508","doi-asserted-by":"crossref","first-page":"20150126","DOI":"10.1259\/bjr.20150126","article-title":"What is the minimum amount of simulated breast movement required for visual detection of blurring? An exploratory investigation","volume":"88","author":"Ma","year":"2015","journal-title":"Br J Radiol"},{"key":"R7-20260508","doi-asserted-by":"crossref","first-page":"892","DOI":"10.1136\/bjo.79.10.892","article-title":"Fundus imaging in patients with cataract: Role for a variable wavelength scanning laser ophthalmoscope","volume":"79","author":"Kirkpatrick","year":"1995","journal-title":"Br J Ophthalmol"},{"key":"R8-20260508","doi-asserted-by":"crossref","first-page":"1764","DOI":"10.1001\/archopht.124.12.1764","article-title":"Ophthalmology and art: Simulation of Monet's cataracts and Degas' retinal disease","volume":"124","author":"Marmor","year":"2006","journal-title":"Arch Ophthalmol"},{"key":"R9-20260508","doi-asserted-by":"crossref","first-page":"252","DOI":"10.1016\/j.survophthal.2021.03.003","article-title":"Artificial intelligence: The unstoppable revolution in ophthalmology","volume":"67","author":"Benet","year":"2022","journal-title":"Surv Ophthalmol"},{"key":"R10-20260508","doi-asserted-by":"crossref","first-page":"996","DOI":"10.1109\/TMI.2020.3043495","article-title":"Modeling and enhancing low-quality retinal fundus images","volume":"40","author":"Shen","year":"2020","journal-title":"IEEE Trans Med Imaging"},{"key":"R11-20260508","first-page":"1","article-title":"Cataract screening as a key step to vision restoring project in country","volume":"19","author":"Liang","year":"2010","journal-title":"Ophthalmol China"},{"key":"R12-20260508","doi-asserted-by":"crossref","first-page":"401","DOI":"10.1109\/42.41493","article-title":"Restoration of retinal images obtained through cataracts","volume":"8","author":"Peli","year":"1989","journal-title":"IEEE Trans Med Imaging"}],"container-title":["Indian Journal of Ophthalmology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.ovid.com\/10.4103\/IJO.IJO_1163_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T16:54:37Z","timestamp":1787763277000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ovid.com\/10.4103\/IJO.IJO_1163_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,22]]},"references-count":12,"journal-issue":{"issue":"Suppl 1","published-print":{"date-parts":[[2024]]}},"URL":"https:\/\/doi.org\/10.4103\/ijo.ijo_1163_23","relation":{},"ISSN":["0301-4738","1998-3689"],"issn-type":[{"value":"0301-4738","type":"print"},{"value":"1998-3689","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,22]]},"assertion":[{"value":"2023-05-05","name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-08-02","name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}}]}}