{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,1,25]],"date-time":"2026-01-25T13:24:26Z","timestamp":1769347466664,"version":"3.49.0"},"posted":{"date-parts":[[2026,1,22]]},"group-title":"Ophthalmology","reference-count":24,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T00:00:00Z","timestamp":1769040000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,1,22]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:sec>\n                  <jats:title>Purpose<\/jats:title>\n                  <jats:p>Glaucoma, a leading cause of irreversible vision loss, often remains undiagnosed due to its asymptomatic progression and the limitations of existing screening methods. This study aimed to validate an artificial intelligence machine learning algorithm for the camera-agnostic detection of glaucomatous optic neuropathy using macula-centered fundus images.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Methods<\/jats:title>\n                  <jats:p>Data were collected from EyePACS, a teleretinal screening system, comprising 25,000 macula-centered fundus images from 12,500 patients at U.S. primary care centers. A secondary dataset from the Philadelphia Telemedicine Glaucoma Follow-up Study was used for independent validation. A convolutional neural network was developed to detect glaucomatous optic neuropathy. Expert-graded fundus images served as the ground truth. Images underwent quality filtering to ensure the visibility of the optic nerve. Bilateral images were analyzed to produce patient-level diagnoses. Validation involved a secondary dataset of fundus images.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>The sensitivity and specificity of the algorithm in detecting glaucomatous optic neuropathy is calculated in comparison to expert grading. From the EyePACS dataset, 21,792 images (10,986 subjects) met quality standards. The algorithm demonstrated a sensitivity of 90.6% and specificity of 90.5%. Validation on the secondary dataset (200 fundus images from 100 subjects) resulted in a sensitivity of 96.4% and specificity of 85.3%.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Conclusions<\/jats:title>\n                  <jats:p>The algorithm achieved high sensitivity and specificity in detecting glaucomatous optic neuropathy using macula-centered fundus images, demonstrating its potential for integration into diverse clinical settings. Its camera-agnostic design and robust performance offer a scalable solution for improving glaucoma screening pathways, making them more accessible and efficient.<\/jats:p>\n                <\/jats:sec>","DOI":"10.64898\/2026.01.20.26344470","type":"posted-content","created":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T18:50:24Z","timestamp":1769107824000},"source":"Crossref","is-referenced-by-count":0,"title":["Camera-Agnostic Autonomous Diagnosis of Glaucomatous Optic Neuropathy using Macular Fundus Imaging and Machine Learning"],"prefix":"10.64898","author":[{"given":"Zack","family":"Dvey-Aharon","sequence":"first","affiliation":[{"name":"AEYE Health Inc., New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Catherine","family":"Lalman","sequence":"additional","affiliation":[{"name":"Wills Eye Hospital, Philadelphia, PA, USA"},{"name":"Sidney Kimmel Medical College at Thomas Jefferson University, Philadelphia, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tsontcho","family":"Ianchulev","sequence":"additional","affiliation":[{"name":"AEYE Health Inc., New York, NY, USA"},{"name":"New York Eye and Ear of Mount Sinai, Icahn School of Medicine, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Moshe","family":"Livne","sequence":"additional","affiliation":[{"name":"AEYE Health Inc., New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dan","family":"Margalit","sequence":"additional","affiliation":[{"name":"AEYE Health Inc., New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rachelle","family":"Aviv","sequence":"additional","affiliation":[{"name":"AEYE Health Inc., New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kristen Ann V.","family":"Mendoza","sequence":"additional","affiliation":[{"name":"New York Eye and Ear of Mount Sinai, Icahn School of Medicine, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joel S.","family":"Schuman","sequence":"additional","affiliation":[{"name":"Wills Eye Hospital, Philadelphia, PA, USA"},{"name":"Sidney Kimmel Medical College at Thomas Jefferson University, Philadelphia, PA, USA"},{"name":"Drexel University School of Biomedical Engineering, Science and Health Studies, Philadelphia, PA, USA"},{"name":"Vickie and Jack Farber Vision Research Center, Wills Eye Hospital, Philadelphia, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"54368","reference":[{"key":"2026012406100566000_2026.01.20.26344470v1.1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2013.01.043"},{"key":"2026012406100566000_2026.01.20.26344470v1.2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2014.05.013"},{"key":"2026012406100566000_2026.01.20.26344470v1.3","first-page":"611","article-title":"Strategies for improving early detection of glaucoma: the combined structure-function index","volume":"8","year":"2014","journal-title":"Clin Ophthalmol. Auckl NZ"},{"key":"2026012406100566000_2026.01.20.26344470v1.4","first-page":"1819","article-title":"The prevalence of glaucoma in a population-based study of Hispanic subjects: Proyecto VER","volume":"119","year":"1960","journal-title":"Arch Ophthalmol. Chic Ill"},{"key":"2026012406100566000_2026.01.20.26344470v1.5","doi-asserted-by":"crossref","first-page":"2566","DOI":"10.4103\/ijo.IJO_2294_21","article-title":"The many challenges in automated glaucoma diagnosis based on fundus imaging","volume":"69","year":"2021","journal-title":"Indian J Ophthalmol"},{"key":"2026012406100566000_2026.01.20.26344470v1.6","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2009.09.026"},{"key":"2026012406100566000_2026.01.20.26344470v1.7","doi-asserted-by":"publisher","DOI":"10.1177\/193229680900300315"},{"key":"2026012406100566000_2026.01.20.26344470v1.8","doi-asserted-by":"crossref","first-page":"114","DOI":"10.1016\/j.ajo.2017.06.024","article-title":"Philadelphia Telemedicine Glaucoma Detection and Follow-up Study: Methods and Screening Results","volume":"181","year":"2017","journal-title":"Am J Ophthalmol"},{"key":"2026012406100566000_2026.01.20.26344470v1.9","doi-asserted-by":"crossref","first-page":"4737","DOI":"10.3390\/s23104737","article-title":"Analysis of the Asymmetry between Both Eyes in Early Diagnosis of Glaucoma Combining Features Extracted from Retinal Images and OCTs into Classification Models","volume":"23","year":"2023","journal-title":"Sensors"},{"key":"2026012406100566000_2026.01.20.26344470v1.10","doi-asserted-by":"crossref","first-page":"1046","DOI":"10.1001\/jamaophthalmol.2024.3884","article-title":"Prevalence of Glaucoma Among US Adults in 2022","volume":"142","year":"2024","journal-title":"JAMA Ophthalmol"},{"key":"2026012406100566000_2026.01.20.26344470v1.11","doi-asserted-by":"publisher","DOI":"10.1136\/bjophthalmol-2018-313173"},{"key":"2026012406100566000_2026.01.20.26344470v1.12","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2017.18152"},{"key":"2026012406100566000_2026.01.20.26344470v1.13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2018.01.023"},{"key":"2026012406100566000_2026.01.20.26344470v1.14","doi-asserted-by":"crossref","first-page":"1353","DOI":"10.1001\/jamaophthalmol.2019.3501","article-title":"Development and Validation of a Deep Learning System to Detect Glaucomatous Optic Neuropathy Using Fundus Photographs","volume":"137","year":"2019","journal-title":"JAMA Ophthalmol"},{"key":"2026012406100566000_2026.01.20.26344470v1.15","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2019.07.024"},{"key":"2026012406100566000_2026.01.20.26344470v1.16","doi-asserted-by":"publisher","DOI":"10.1136\/bjophthalmol-2019-315016"},{"key":"2026012406100566000_2026.01.20.26344470v1.17","doi-asserted-by":"crossref","first-page":"304","DOI":"10.1080\/08820538.2021.1896756","article-title":"Artificial Intelligence (AI) Applications for Age-Related Macular Degeneration (AMD) and Other Retinal Dystrophies","volume":"36","year":"2021","journal-title":"Semin Ophthalmol"},{"key":"2026012406100566000_2026.01.20.26344470v1.18","doi-asserted-by":"publisher","DOI":"10.1136\/bjo-2023-323376"},{"key":"2026012406100566000_2026.01.20.26344470v1.19","doi-asserted-by":"crossref","unstructured":"Rom Y , Aviv R , Cohen GY , et al. detection from non-diabetic retinopathy fundus images using deep learning methodology. Heliyon 2024;10. Available at: https:\/\/www.cell.com\/heliyon\/abstract\/S2405-8440(24)12623-0","DOI":"10.1016\/j.heliyon.2024.e36592"},{"key":"2026012406100566000_2026.01.20.26344470v1.20","doi-asserted-by":"crossref","unstructured":"Bressler I , Dollberg D , Aviv R , et al. Non-Contact Optical Blood Pressure Biometry Using AI-Based Analysis of Non-Mydriatic Fundus Imaging. 2025. Available at: http:\/\/www.medrxiv.org\/content\/10.1101\/2025.01.06.25320084v1","DOI":"10.1101\/2025.01.06.25320084"},{"key":"2026012406100566000_2026.01.20.26344470v1.21","unstructured":"Bressler I , Aviv R , Margalit D , et al. Autonomous Screening for Diabetic Macular Edema Using Deep Learning Processing of Retinal Images. Ophthalmol Sci 2025;0. Available at: http:\/\/www.ophthalmologyscience.org\/article\/S2666-9145(25)00020-X\/fulltext"},{"key":"2026012406100566000_2026.01.20.26344470v1.22","doi-asserted-by":"publisher","DOI":"10.1136\/bmjdrc-2019-000892"},{"key":"2026012406100566000_2026.01.20.26344470v1.23","doi-asserted-by":"publisher","DOI":"10.1136\/bmjophth-2022-001140"},{"key":"2026012406100566000_2026.01.20.26344470v1.24","doi-asserted-by":"crossref","first-page":"413","DOI":"10.1097\/ICU.0000000000000791","article-title":"Artificial intelligence in myopia: current and future trends","volume":"32","year":"2021","journal-title":"Curr Opin Ophthalmol"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.01.20.26344470","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T14:10:16Z","timestamp":1769263816000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.64898\/2026.01.20.26344470"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,22]]},"references-count":24,"URL":"https:\/\/doi.org\/10.64898\/2026.01.20.26344470","relation":{},"subject":[],"published":{"date-parts":[[2026,1,22]]},"subtype":"preprint"}}