{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T00:40:08Z","timestamp":1783125608960,"version":"3.54.6"},"reference-count":27,"publisher":"American Medical Association (AMA)","issue":"7","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JAMA Ophthalmol"],"published-print":{"date-parts":[[2023,7,1]]},"abstract":"<jats:sec id=\"ab-eoi230030-4\"><jats:title>Importance<\/jats:title><jats:p>Best-corrected visual acuity (BCVA) is a measure used to manage diabetic macular edema (DME), sometimes suggesting development of DME or consideration of initiating, repeating, withholding, or resuming treatment with anti\u2013vascular endothelial growth factor. Using artificial intelligence (AI) to estimate BCVA from fundus images could help clinicians manage DME by reducing the personnel needed for refraction, the time presently required for assessing BCVA, or even the number of office visits if imaged remotely.<\/jats:p><\/jats:sec><jats:sec id=\"ab-eoi230030-5\"><jats:title>Objective<\/jats:title><jats:p>To evaluate the potential application of AI techniques for estimating BCVA from fundus photographs with and without ancillary information.<\/jats:p><\/jats:sec><jats:sec id=\"ab-eoi230030-6\"><jats:title>Design, Setting, and Participants<\/jats:title><jats:p>Deidentified color fundus images taken after dilation were used post hoc to train AI systems to perform regression from image to BCVA and to evaluate resultant estimation errors. Participants were patients enrolled in the VISTA randomized clinical trial through 148 weeks wherein the study eye was treated with aflibercept or laser. The data from study participants included macular images, clinical information, and BCVA scores by trained examiners following protocol refraction and VA measurement on Early Treatment Diabetic Retinopathy Study (ETDRS) charts.<\/jats:p><\/jats:sec><jats:sec id=\"ab-eoi230030-7\"><jats:title>Main Outcomes<\/jats:title><jats:p>Primary outcome was regression evaluated by mean absolute error (MAE); the secondary outcome included percentage of predictions within 10 letters, computed over the entire cohort as well as over subsets categorized by baseline BCVA, determined from baseline through the 148-week visit.<\/jats:p><\/jats:sec><jats:sec id=\"ab-eoi230030-8\"><jats:title>Results<\/jats:title><jats:p>Analysis included 7185 macular color fundus images of the study and fellow eyes from 459 participants. Overall, the mean (SD) age was 62.2 (9.8) years, and 250 (54.5%) were male. The baseline BCVA score for the study eyes ranged from 73 to 24 letters (approximate Snellen equivalent 20\/40 to 20\/320). Using ResNet50 architecture, the MAE for the testing set (n\u2009=\u2009641 images) was 9.66 (95% CI, 9.05-10.28); 33% of the values (95% CI, 30%-37%) were within 0 to 5 letters and 28% (95% CI, 25%-32%) within 6 to 10 letters. For BCVA of 100 letters or less but more than 80 letters (20\/10 to 20\/25, n\u2009=\u2009161) and 80 letters or less but more than 55 letters (20\/32 to 20\/80, n\u2009=\u2009309), the MAE was 8.84 letters (95% CI, 7.88-9.81) and 7.91 letters (95% CI, 7.28-8.53), respectively.<\/jats:p><\/jats:sec><jats:sec id=\"ab-eoi230030-9\"><jats:title>Conclusions and Relevance<\/jats:title><jats:p>This investigation suggests AI can estimate BCVA directly from fundus photographs in patients with DME, without refraction or subjective visual acuity measurements, often within 1 to 2 lines on an ETDRS chart, supporting this AI concept if additional improvements in estimates can be achieved.<\/jats:p><\/jats:sec>","DOI":"10.1001\/jamaophthalmol.2023.2271","type":"journal-article","created":{"date-parts":[[2023,6,8]],"date-time":"2023-06-08T15:01:07Z","timestamp":1686236467000},"page":"677","source":"Crossref","is-referenced-by-count":19,"title":["Accuracy of Artificial Intelligence in Estimating Best-Corrected Visual Acuity From Fundus Photographs in Eyes With Diabetic Macular Edema"],"prefix":"10.1001","volume":"141","author":[{"given":"William","family":"Paul","sequence":"first","affiliation":[{"name":"Applied Physics Laboratory, Johns Hopkins University, Laurel, Maryland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Philippe","family":"Burlina","sequence":"additional","affiliation":[{"name":"Applied Physics Laboratory, Johns Hopkins University, Laurel, Maryland"},{"name":"Department of Computer Science and Malone Center for Engineering in Healthcare, Johns Hopkins University, Baltimore, Maryland"},{"name":"Zoox, Foster City, California"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rohita","family":"Mocharla","sequence":"additional","affiliation":[{"name":"Applied Physics Laboratory, Johns Hopkins University, Laurel, Maryland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Neil","family":"Joshi","sequence":"additional","affiliation":[{"name":"Applied Physics Laboratory, Johns Hopkins University, Laurel, Maryland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuolin","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Johns Hopkins University School of Medicine, Baltimore, Maryland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sophie","family":"Gu","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Johns Hopkins University School of Medicine, Baltimore, Maryland"},{"name":"Department of Ophthalmology, Edward S. Harkness Eye Institute, Columbia University Irving Medical Center, New York\u2013Presbyterian Hospital, New York, New York"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Onnisa","family":"Nanegrungsunk","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Johns Hopkins University School of Medicine, Baltimore, Maryland"},{"name":"Department of Ophthalmology, Faculty of Medicine, Chiang Mai University, Chiang Mai, Thailand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kira","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Johns Hopkins University School of Medicine, Baltimore, Maryland"},{"name":"Ruiz Department of Ophthalmology and Visual Science at McGovern Medical School at UTHealth Houston, Houston, Texas"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Susan B.","family":"Bressler","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Johns Hopkins University School of Medicine, Baltimore, Maryland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cindy X.","family":"Cai","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Johns Hopkins University School of Medicine, Baltimore, Maryland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Kong","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Johns Hopkins University School of Medicine, Baltimore, Maryland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"T. Y. Alvin","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Johns Hopkins University School of Medicine, Baltimore, Maryland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hadi","family":"Moini","sequence":"additional","affiliation":[{"name":"Regeneron Pharmaceuticals Inc, Tarrytown, New York"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiming","family":"Du","sequence":"additional","affiliation":[{"name":"Regeneron Pharmaceuticals Inc, Tarrytown, New York"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fouad","family":"Amer","sequence":"additional","affiliation":[{"name":"Regeneron Pharmaceuticals Inc, Tarrytown, New York"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karen","family":"Chu","sequence":"additional","affiliation":[{"name":"Regeneron Pharmaceuticals Inc, Tarrytown, New York"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert","family":"Vitti","sequence":"additional","affiliation":[{"name":"Regeneron Pharmaceuticals Inc, Tarrytown, New York"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Farshid","family":"Sepehrband","sequence":"additional","affiliation":[{"name":"Regeneron Pharmaceuticals Inc, Tarrytown, New York"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Neil M.","family":"Bressler","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Johns Hopkins University School of Medicine, Baltimore, Maryland"},{"name":"Editor, JAMA Ophthalmology"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"10","reference":[{"issue":"11","key":"eoi230030r1","doi-asserted-by":"publisher","first-page":"1334","DOI":"10.1001\/jamaophthalmol.2014.2854","article-title":"Prevalence of and risk factors for diabetic macular edema in the United States.","volume":"132","author":"Varma","year":"2014","journal-title":"JAMA Ophthalmol"},{"key":"eoi230030r3","doi-asserted-by":"publisher","first-page":"e5","DOI":"10.1016\/j.ophtha.2011.09.058","article-title":"Rationale for the Diabetic Retinopathy Clinical Research Network treatment protocol for center-involved diabetic macular edema.","volume":"118","author":"Diabetic Retinopathy Clinical Research Network","year":"2011","journal-title":"Ophthalmology"},{"issue":"4","key":"eoi230030r4","doi-asserted-by":"publisher","first-page":"789","DOI":"10.1016\/j.ophtha.2011.12.039","article-title":"Ranibizumab for diabetic macular edema: results from 2 phase III randomized trials: RISE and RIDE.","volume":"119","author":"Nguyen","year":"2012","journal-title":"Ophthalmology"},{"issue":"10","key":"eoi230030r5","doi-asserted-by":"publisher","first-page":"2044","DOI":"10.1016\/j.ophtha.2015.06.017","article-title":"Intravitreal aflibercept for diabetic macular edema: 100-week results from the VISTA and VIVID studies.","volume":"122","author":"Brown","year":"2015","journal-title":"Ophthalmology"},{"issue":"10326","key":"eoi230030r6","doi-asserted-by":"publisher","first-page":"741","DOI":"10.1016\/S0140-6736(22)00018-6","article-title":"Efficacy, durability, and safety of intravitreal faricimab with extended dosing up to every 16 weeks in patients with diabetic macular oedema (YOSEMITE and RHINE): two randomised, double-masked, phase 3 trials.","volume":"399","author":"Wykoff","year":"2022","journal-title":"Lancet"},{"key":"eoi230030r7","first-page":"2612","article-title":"Visual acuity with habitual correction on an ETDRS chart vs protocol refraction on an electronic ETDRS chart in diabetic macular edema [abstract].","volume":"60","author":"Tsou","year":"2019","journal-title":"Invest Ophthalmol Vis Sci"},{"key":"eoi230030r8","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2022.12.008","article-title":"Comparison of Snellen visual acuity measurements in retinal clinical practice to electronic ETDRS protocol visual acuity assessment.","author":"Baker","year":"2022","journal-title":"Ophthalmology"},{"issue":"22","key":"eoi230030r9","doi-asserted-by":"publisher","first-page":"2402","DOI":"10.1001\/jama.2016.17216","article-title":"Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs.","volume":"316","author":"Gulshan","year":"2016","journal-title":"JAMA"},{"issue":"5","key":"eoi230030r10","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1038\/s41591-018-0029-3","article-title":"AI for medical imaging goes deep.","volume":"24","author":"Ting","year":"2018","journal-title":"Nat Med"},{"issue":"11","key":"eoi230030r11","doi-asserted-by":"publisher","first-page":"1170","DOI":"10.1001\/jamaophthalmol.2017.3782","article-title":"Automated grading of age-related macular degeneration from color fundus images using deep convolutional neural networks.","volume":"135","author":"Burlina","year":"2017","journal-title":"JAMA Ophthalmol"},{"issue":"11","key":"eoi230030r12","doi-asserted-by":"publisher","first-page":"1305","DOI":"10.1001\/jamaophthalmol.2018.3799","article-title":"Utility of deep learning methods for referability classification of age-related macular degeneration.","volume":"136","author":"Burlina","year":"2018","journal-title":"JAMA Ophthalmol"},{"key":"eoi230030r13","first-page":"3962","article-title":"Automatic screening of age-related macular degeneration and retinal abnormalities.","volume":"2011","author":"Burlina","year":"2011","journal-title":"Annu Int Conf IEEE Eng Med Biol Soc"},{"issue":"3","key":"eoi230030r14","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1001\/jamaophthalmol.2018.6156","article-title":"Assessment of deep generative models for high-resolution synthetic retinal image generation of age-related macular degeneration.","volume":"137","author":"Burlina","year":"2019","journal-title":"JAMA Ophthalmol"},{"key":"eoi230030r15","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2019.103445","article-title":"Deep learning based retinal OCT segmentation.","volume":"114","author":"Pekala","year":"2019","journal-title":"Comput Biol Med"},{"issue":"10","key":"eoi230030r16","doi-asserted-by":"crossref","first-page":"1070","DOI":"10.1001\/jamaophthalmol.2020.3269","article-title":"Low-shot deep learning of diabetic retinopathy with potential applications to address artificial intelligence bias in retinal diagnostics and rare ophthalmic diseases.","volume":"138","author":"Burlina","year":"2020","journal-title":"JAMA Ophthalmol"},{"issue":"2","key":"eoi230030r17","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1001\/jamaophthalmol.2021.5557","article-title":"Detecting anomalies in retinal diseases using generative, discriminative, and self-supervised deep learning.","volume":"140","author":"Burlina","year":"2022","journal-title":"JAMA Ophthalmol"},{"issue":"12","key":"eoi230030r18","doi-asserted-by":"publisher","first-page":"1359","DOI":"10.1001\/jamaophthalmol.2018.4118","article-title":"Use of deep learning for detailed severity characterization and estimation of 5-year risk among patients with age-related macular degeneration.","volume":"136","author":"Burlina","year":"2018","journal-title":"JAMA Ophthalmol"},{"issue":"2","key":"eoi230030r19","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1001\/jamaophthalmol.2018.5806","article-title":"High-resolution direct ophthalmoscopy with an unmodified iPhone X.","volume":"137","author":"Gunasekera","year":"2019","journal-title":"JAMA Ophthalmol"},{"issue":"1","key":"eoi230030r20","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1007\/s10916-021-01795-8","article-title":"Diabetic macular edema screened by handheld smartphone-based retinal camera and artificial intelligence.","volume":"46","author":"Malerbi","year":"2021","journal-title":"J Med Syst"},{"issue":"5","key":"eoi230030r21","doi-asserted-by":"publisher","first-page":"57008","DOI":"10.1117\/1.JBO.18.5.057008","article-title":"Estimating physiological skin parameters from hyperspectral signatures.","volume":"18","author":"Vyas","year":"2013","journal-title":"J Biomed Opt"},{"issue":"21","key":"eoi230030r22","doi-asserted-by":"publisher","first-page":"4732","DOI":"10.3390\/s19214732","article-title":"Automatic visual acuity estimation by means of computational vascularity biomarkers using OCT angiographies.","volume":"19","author":"D\u00edaz","year":"2019","journal-title":"Sensors (Basel)"},{"issue":"6","key":"eoi230030r23","doi-asserted-by":"publisher","first-page":"3190","DOI":"10.3390\/app12063190","article-title":"A deep learning ensemble method to visual acuity measurement using fundus images.","volume":"12","author":"Kim","year":"2022","journal-title":"Appl Sci"},{"issue":"2","key":"eoi230030r24","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1016\/S0002-9394(02)01825-1","article-title":"A computerized method of visual acuity testing: adaptation of the early treatment of diabetic retinopathy study testing protocol.","volume":"135","author":"Beck","year":"2003","journal-title":"Am J Ophthalmol"},{"key":"eoi230030r26","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1016\/j.neucom.2021.03.091","article-title":"A review on the attention mechanism of deep learning.","volume":"452","author":"Niu","year":"2021","journal-title":"Neurocomputing"},{"key":"eoi230030r25","doi-asserted-by":"crossref","DOI":"10.1002\/047084535X","volume-title":"Recurrent Neural Networks for Prediction: Learning Algorithms, Architectures and Stability","author":"Mandic","year":"2001"},{"key":"eoi230030r2","unstructured":"Institute for Health Metrics and Evaluation, Global Burden of Disease Collaborative Network. Global Burden of Disease Study 2019 (GBD 2019) results. Accessed January 5, 2023. https:\/\/vizhub.healthdata.org\/gbd-results\/"},{"key":"eoi230030r27","unstructured":"Dosovitskiy? A, Beyer? L, Kolesnikov? A, . An image is worth 16x16 words: transformers for image recognition at scale.? arXiv. Preprint posted online October 22, 2020. doi:10.48550\/arXiv.2010.11929"}],"container-title":["JAMA Ophthalmology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/jamanetwork.com\/journals\/jamaophthalmology\/articlepdf\/2805759\/jamaophthalmology_paul_2023_oi_230030_1688589998.84161.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,20]],"date-time":"2023-07-20T15:51:48Z","timestamp":1689868308000},"score":1,"resource":{"primary":{"URL":"https:\/\/jamanetwork.com\/journals\/jamaophthalmology\/fullarticle\/2805759"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,1]]},"references-count":27,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2023,7,1]]}},"URL":"https:\/\/doi.org\/10.1001\/jamaophthalmol.2023.2271","relation":{},"ISSN":["2168-6165"],"issn-type":[{"value":"2168-6165","type":"print"}],"subject":[],"published":{"date-parts":[[2023,7,1]]}}}