{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T22:46:26Z","timestamp":1780699586721,"version":"3.54.1"},"reference-count":34,"publisher":"BMJ","issue":"8","funder":[{"DOI":"10.13039\/100000053","name":"National Eye Institute","doi-asserted-by":"publisher","award":["R01-EY029792"],"award-info":[{"award-number":["R01-EY029792"]}],"id":[{"id":"10.13039\/100000053","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100001818","name":"Research to Prevent Blindness","doi-asserted-by":"publisher","award":["N\/A"],"award-info":[{"award-number":["N\/A"]}],"id":[{"id":"10.13039\/100001818","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["Br J Ophthalmol"],"accepted":{"date-parts":[[2023,9,18]]},"published-print":{"date-parts":[[2024,8]]},"abstract":"<jats:sec><jats:title>Aim<\/jats:title><jats:p>We tested the hypothesis that visual field (VF) progression can be predicted with a deep learning model based on longitudinal pairs of optic disc photographs (ODP) acquired at earlier time points during follow-up.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>3919 eyes (2259 patients) with \u22652 ODPs at least 2 years apart, and \u22655 24\u20132 VF exams spanning \u22653 years of follow-up were included. Serial VF mean deviation (MD) rates of change were estimated starting at the fifth visit and subsequently by adding visits until final visit. VF progression was defined as a statistically significant negative slope at two consecutive visits and final visit. We built a twin-neural network with ResNet50-backbone. A pair of ODPs acquired up to a year before the VF progression date or the last VF in non-progressing eyes were included as input. Primary outcome measures were area under the receiver operating characteristic curve (AUC) and model accuracy.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The average (SD) follow-up time and baseline VF MD were 8.1 (4.8) years and \u20133.3 (4.9) dB, respectively. VF progression was identified in 761 eyes (19%). The median (IQR) time to progression in progressing eyes was 7.3 (4.5\u201311.1) years. The AUC and accuracy for predicting VF progression were 0.862 (0.812\u20130.913) and 80.0% (73.9%\u201384.6%). When only fast-progressing eyes were considered (MD rate &lt; \u20131.0\u2009dB\/year), AUC increased to 0.926 (0.857\u20130.994).<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>A deep learning model can predict subsequent glaucoma progression from longitudinal ODPs with clinically relevant accuracy. This model may be implemented, after validation, for predicting glaucoma progression in the clinical setting.<\/jats:p><\/jats:sec>","DOI":"10.1136\/bjo-2023-324277","type":"journal-article","created":{"date-parts":[[2023,10,13]],"date-time":"2023-10-13T17:21:08Z","timestamp":1697217668000},"page":"1107-1113","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":15,"title":["Prediction of visual field progression with serial optic disc photographs using deep learning"],"prefix":"10.1136","volume":"108","author":[{"given":"Vahid","family":"Mohammadzadeh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sean","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tyler","family":"Davis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arvind","family":"Vepa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Esteban","family":"Morales","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sajad","family":"Besharati","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kiumars","family":"Edalati","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jack","family":"Martinyan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mahshad","family":"Rafiee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arthur","family":"Martynian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fabien","family":"Scalzo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2383-7263","authenticated-orcid":false,"given":"Joseph","family":"Caprioli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9403-8904","authenticated-orcid":false,"given":"Kouros","family":"Nouri-Mahdavi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2023,10,13]]},"reference":[{"key":"2024072308350685000_108.8.1107.1","doi-asserted-by":"publisher","DOI":"10.1016\/S0161-6420(92)32018-4"},{"key":"2024072308350685000_108.8.1107.2","doi-asserted-by":"crossref","DOI":"10.1167\/tvst.8.5.2","article-title":"Comparison of methods to detect and measure glaucomatous visual field progression","volume":"8","author":"Rabiolo","year":"2019","journal-title":"Transl Vis Sci Technol"},{"key":"2024072308350685000_108.8.1107.3","doi-asserted-by":"crossref","first-page":"597","DOI":"10.1016\/j.survophthal.2020.03.002","article-title":"Macular imaging with optical coherence tomography in glaucoma","volume":"65","author":"Mohammadzadeh","year":"2020","journal-title":"Surv Ophthalmol"},{"key":"2024072308350685000_108.8.1107.4","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajo.2007.12.003"},{"key":"2024072308350685000_108.8.1107.5","doi-asserted-by":"publisher","DOI":"10.1167\/iovs.10-6414"},{"key":"2024072308350685000_108.8.1107.6","doi-asserted-by":"publisher","DOI":"10.1034\/j.1600-0420.2003.00070.x"},{"key":"2024072308350685000_108.8.1107.7","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1111\/aos.13290","article-title":"Detection of glaucoma progression by perimetry and optic disc photography at different stages of the disease: results from the early manifest glaucoma trial","volume":"95","author":"\u00d6hnell","year":"2017","journal-title":"Acta Ophthalmol"},{"key":"2024072308350685000_108.8.1107.8","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1167\/tvst.6.5.14","article-title":"Optic disc image subtraction as an aid to detect glaucoma progression","volume":"6","author":"Amini","year":"2017","journal-title":"Trans Vis Sci Tech"},{"key":"2024072308350685000_108.8.1107.9","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2010.08.019"},{"key":"2024072308350685000_108.8.1107.10","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajo.2008.07.023"},{"key":"2024072308350685000_108.8.1107.11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajo.2018.10.007"},{"key":"2024072308350685000_108.8.1107.12","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1001\/jamaophthalmol.2019.5983","article-title":"Assessment of a segmentation-free deep learning algorithm for diagnosing glaucoma from optical coherence tomography scans","volume":"138","author":"Thompson","year":"2020","journal-title":"JAMA Ophthalmol"},{"key":"2024072308350685000_108.8.1107.13","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1167\/tvst.9.2.27","article-title":"Effects of study population, labeling and training on glaucoma detection using deep learning algorithms","volume":"9","author":"Christopher","year":"2020","journal-title":"Trans Vis Sci Tech"},{"key":"2024072308350685000_108.8.1107.14","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2020.12.020"},{"key":"2024072308350685000_108.8.1107.15","doi-asserted-by":"crossref","first-page":"383","DOI":"10.1016\/j.ophtha.2020.07.045","article-title":"Detection of progressive glaucomatous optic nerve damage on fundus photographs with deep learning","volume":"128","author":"Medeiros","year":"2021","journal-title":"Ophthalmology"},{"key":"2024072308350685000_108.8.1107.16","doi-asserted-by":"crossref","unstructured":"Hassan ON , Sahin S , Mohammadzadeh V , et al . Conditional GAN for prediction of glaucoma progression with macular optical coherence tomography. In: International symposium on visual computing springer. Cham, 2020: 761\u201372.","DOI":"10.1007\/978-3-030-64559-5_61"},{"key":"2024072308350685000_108.8.1107.17","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1097\/OPX.0000000000000139","article-title":"Glaucomatous visual field loss associated with less travel from home","volume":"91","author":"Ramulu","year":"2014","journal-title":"Optom Vis Sci"},{"key":"2024072308350685000_108.8.1107.18","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1016\/j.ophtha.2014.08.014","article-title":"Longitudinal changes in quality of life and rates of progressive visual field loss in glaucoma patients","volume":"122","author":"Medeiros","year":"2015","journal-title":"Ophthalmology"},{"key":"2024072308350685000_108.8.1107.19","unstructured":"Liu J , Chao F , Lin CM . Task augmentation by rotating for meta-learning. arXiv 2003. doi:10.48550\/arXiv.2003.00804"},{"key":"2024072308350685000_108.8.1107.20","doi-asserted-by":"crossref","unstructured":"Kapishnikov A , Bolukbasi T , Viegas F , et al . Xrai: better Attributions through regions. Proceedings of the IEEE\/CVF International conference on computer Vision; 2019","DOI":"10.1109\/ICCV.2019.00505"},{"key":"2024072308350685000_108.8.1107.21","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2006.08.031"},{"key":"2024072308350685000_108.8.1107.22","doi-asserted-by":"publisher","DOI":"10.1001\/archopht.123.10.1351"},{"key":"2024072308350685000_108.8.1107.23","doi-asserted-by":"crossref","first-page":"619","DOI":"10.1038\/s41598-017-19113-z","article-title":"Visual field loss and vision-related quality of life in the Italian primary open angle glaucoma study","volume":"8","author":"Rulli","year":"2018","journal-title":"Sci Rep"},{"key":"2024072308350685000_108.8.1107.24","doi-asserted-by":"publisher","DOI":"10.1016\/j.preteyeres.2007.08.001"},{"key":"2024072308350685000_108.8.1107.25","doi-asserted-by":"publisher","DOI":"10.1167\/iovs.12-10345"},{"key":"2024072308350685000_108.8.1107.26","doi-asserted-by":"publisher","DOI":"10.1001\/archopht.1980.01020030486010"},{"key":"2024072308350685000_108.8.1107.27","doi-asserted-by":"publisher","DOI":"10.1016\/S0161-6420(92)31990-6"},{"key":"2024072308350685000_108.8.1107.28","doi-asserted-by":"crossref","first-page":"562","DOI":"10.1001\/archophthalmol.2011.72","article-title":"Risk factors for visual field progression in treated glaucoma","volume":"129","author":"De Moraes","year":"2011","journal-title":"Arch Ophthalmol"},{"key":"2024072308350685000_108.8.1107.29","doi-asserted-by":"crossref","first-page":"780","DOI":"10.1001\/jamaophthalmol.2020.1902","article-title":"Evaluation of a primary open-angle glaucoma prediction model using long-term intraocular pressure variability data: a secondary analysis of 2 randomized clinical trials","volume":"138","author":"Gordon","year":"2020","journal-title":"JAMA Ophthalmol"},{"key":"2024072308350685000_108.8.1107.30","doi-asserted-by":"publisher","DOI":"10.1136\/bjophthalmol-2013-303622"},{"key":"2024072308350685000_108.8.1107.31","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1167\/iovs.18-25391","article-title":"Comparison of rates of fast and catastrophic visual field loss in three glaucoma subtypes","volume":"60","author":"Anderson","year":"2019","journal-title":"Invest Ophthalmol Vis Sci"},{"key":"2024072308350685000_108.8.1107.32","doi-asserted-by":"publisher","DOI":"10.1001\/archopht.1994.01090180121046"},{"key":"2024072308350685000_108.8.1107.33","first-page":"40","article-title":"Prevalence of glaucoma in a rural East African population","volume":"41","author":"Buhrmann","year":"2000","journal-title":"Invest Ophthalmol Vis Sci"},{"key":"2024072308350685000_108.8.1107.34","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1016\/j.ophtha.2022.12.025","article-title":"Validation of rates of mean deviation change as clinically relevant end points for glaucoma progression","volume":"130","author":"Medeiros","year":"2023","journal-title":"Ophthalmology"}],"container-title":["British Journal of Ophthalmology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bjo-2023-324277","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,23]],"date-time":"2024-07-23T15:37:22Z","timestamp":1721749042000},"score":1,"resource":{"primary":{"URL":"https:\/\/bjo.bmj.com\/lookup\/doi\/10.1136\/bjo-2023-324277"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,13]]},"references-count":34,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2024,7,23]]},"published-print":{"date-parts":[[2024,8]]}},"alternative-id":["10.1136\/bjo-2023-324277"],"URL":"https:\/\/doi.org\/10.1136\/bjo-2023-324277","relation":{},"ISSN":["0007-1161","1468-2079"],"issn-type":[{"value":"0007-1161","type":"print"},{"value":"1468-2079","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10,13]]}}}