{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T18:22:01Z","timestamp":1792002121775,"version":"4.4.0"},"reference-count":33,"publisher":"Public Library of Science (PLoS)","issue":"6","license":[{"start":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T00:00:00Z","timestamp":1750896000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Philanthropic grant \u2013 Late Dr Usha Kumar and Hyderabad Eye Research Foundation, Hyderabad, India"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:sec>\n<jats:title>Purpose<\/jats:title>\n<jats:p>Leveraging an artificial intelligence system (AI) for glaucoma screening can mitigate the current challenges and provide prompt detection and management crucial in averting irreversible blindness. The study reports the real-world performance of a glaucoma AI system deployed on a smartphone-based fundus camera across various severities of glaucoma.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title>Methods<\/jats:title>\n<jats:p>In this prospective comparative study at a tertiary care glaucoma clinic, consecutive patients were evaluated by a glaucoma specialist using clinical assessment, visual field tests, and SD-OCT, and categorized as definite glaucoma, glaucoma suspect, or no glaucoma. For glaucoma patients, severity was determined using Hoddap-Parrish-Anderson criteria based on visual field mean deviation (MD). A disc-centered image per eye was captured using a validated portable non-mydriatic fundus camera. The AI tool\u2019s ability to detect referral-warranted glaucoma (glaucoma and glaucoma suspects) versus no glaucoma was compared to the specialist\u2019s diagnosis.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title>Results<\/jats:title>\n<jats:p>We included 213 participants with a mean age of 55\u2009\u00b1\u200914.7 years (18, 88). The glaucoma specialist diagnosed 129 subjects as definite glaucoma (early-23, moderate-31, severe-75), 33-disc suspects and 51 as no-glaucoma. The automated AI system based on fundus images achieved an overall diagnostic accuracy of 92.02%, sensitivity of 91.36% (95%CI 85.93% to 95.19%) and specificity of 94.12% (83.76% to 98.77%) for referral warranted glaucoma. The 14 false negatives included 5-disc suspects and 9 definite glaucoma (3-early, 3-moderate and 3-advanced glaucoma). The sensitivity of AI for detecting early, moderate and advanced glaucoma was 86.9% (95%CI 66.4\u201397.2), 90.3% (95%CI 74.3\u201397.96), and 96% (88.75% to 99.17%) respectively.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title>Conclusion<\/jats:title>\n<jats:p>In a real-world setting, the AI-based offline tool integrated on a smartphone fundus camera showed a promising performance in detecting referral-warranted glaucoma compared to a glaucoma specialist\u2019s diagnosis. The AI showed higher accuracy in detecting advanced glaucoma followed by moderate and early glaucoma.<\/jats:p>\n<\/jats:sec>","DOI":"10.1371\/journal.pone.0324883","type":"journal-article","created":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T17:40:56Z","timestamp":1750959656000},"page":"e0324883","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":11,"title":["Evaluating real-world performance of an automated offline glaucoma AI on a smartphone fundus camera across glaucoma severity stages"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1748-8850","authenticated-orcid":true,"given":"Sirisha","family":"Senthil","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Divya Parthasarathy","family":"Rao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8093-6228","authenticated-orcid":true,"given":"Florian M.","family":"Savoy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kalpa","family":"Negiloni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shreya","family":"Bhandary","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Raghava","family":"Chary","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Garudadri","family":"Chandrashekar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,6,26]]},"reference":[{"issue":"2","key":"pone.0324883.ref001","doi-asserted-by":"crossref","first-page":"164","DOI":"10.1001\/jama.2020.21899","article-title":"Glaucoma in Adults-Screening, Diagnosis, and Management: A Review","volume":"325","author":"JD Stein","year":"2021","journal-title":"JAMA"},{"issue":"11","key":"pone.0324883.ref002","doi-asserted-by":"crossref","first-page":"2081","DOI":"10.1016\/j.ophtha.2014.05.013","article-title":"Global prevalence of glaucoma and projections of glaucoma burden through 2040: a systematic review and meta-analysis","volume":"121","author":"YC Tham","year":"2014","journal-title":"Ophthalmology"},{"issue":"1","key":"pone.0324883.ref003","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1136\/bjophthalmol-2014-306102","article-title":"Glaucoma in Asia: regional prevalence variations and future projections","volume":"100","author":"EW Chan","year":"2016","journal-title":"Br J Ophthalmol"},{"issue":"10","key":"pone.0324883.ref004","doi-asserted-by":"crossref","first-page":"1393","DOI":"10.1016\/j.ophtha.2021.04.009","article-title":"The Global Extent of Undetected Glaucoma in Adults: A Systematic Review and Meta-analysis","volume":"128","author":"Z Soh","year":"2021","journal-title":"Ophthalmology"},{"issue":"2","key":"pone.0324883.ref005","article-title":"Factors influencing vision\u2010related quality of life according to glaucoma severity","volume":"97","author":"YS Chun","year":"2019","journal-title":"Acta Ophthalmologica"},{"issue":"10","key":"pone.0324883.ref006","doi-asserted-by":"crossref","first-page":"860","DOI":"10.1097\/IJG.0000000000002276","article-title":"Impact of Monocular and Binocular Visual Function Parameters on Vision-Related Quality of Life in Glaucoma","volume":"32","author":"S Nagarajan","year":"2023","journal-title":"J Glaucoma"},{"issue":"12","key":"pone.0324883.ref007","doi-asserted-by":"crossref","first-page":"3318","DOI":"10.1038\/s41433-021-01395-3","article-title":"Comparison of vertical cup-to-disc ratio estimates using stereoscopic and monoscopic cameras","volume":"35","author":"R Shrestha","year":"2021","journal-title":"Eye"},{"key":"pone.0324883.ref008","doi-asserted-by":"crossref","first-page":"990611","DOI":"10.3389\/fmed.2022.990611","article-title":"Stereoscopic vs. monoscopic photographs on optic disc evaluation and glaucoma diagnosis among general ophthalmologists: A cloud-based real-world multicenter study","volume":"9","author":"J Yang","year":"2022","journal-title":"Front Med (Lausanne)"},{"issue":"2","key":"pone.0324883.ref009","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1097\/01.APO.0000656984.56467.2c","article-title":"Artificial Intelligence in Ophthalmology in 2020: A Technology on the Cusp for Translation and Implementation","volume":"9","author":"DV Gunasekeran","year":"2020","journal-title":"Asia Pac J Ophthalmol (Phila)"},{"issue":"7","key":"pone.0324883.ref010","article-title":"Artificial intelligence in ophthalmology: The path to the real-world clinic","volume":"4","author":"Z Li","year":"2023","journal-title":"Cell Rep Med"},{"issue":"3","key":"pone.0324883.ref011","doi-asserted-by":"crossref","first-page":"276","DOI":"10.1007\/s10384-019-00659-6","article-title":"Evaluation of deep convolutional neural networks for glaucoma detection","volume":"63","author":"S Phan","year":"2019","journal-title":"Jpn J Ophthalmol"},{"issue":"12","key":"pone.0324883.ref012","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","author":"H Liu","year":"2019","journal-title":"JAMA Ophthalmol"},{"issue":"1","key":"pone.0324883.ref013","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1016\/j.ogla.2018.04.002","article-title":"A Deep Learning-Based Algorithm Identifies Glaucomatous Discs Using Monoscopic Fundus Photographs","volume":"1","author":"S Liu","year":"2018","journal-title":"Ophthalmol Glaucoma"},{"issue":"1","key":"pone.0324883.ref014","article-title":"Performance of deep learning architectures and transfer learning for detecting glaucomatous optic neuropathy in fundus photographs","volume":"8","author":"S Liu","year":"2018","journal-title":"Sci Rep"},{"issue":"1","key":"pone.0324883.ref015","doi-asserted-by":"crossref","first-page":"14665","DOI":"10.1038\/s41598-018-33013-w","article-title":"Development of a deep residual learning algorithm to screen for glaucoma from fundus photography","volume":"8","author":"N Shibata","year":"2018","journal-title":"Sci Rep"},{"issue":"8","key":"pone.0324883.ref016","doi-asserted-by":"crossref","first-page":"1199","DOI":"10.1016\/j.ophtha.2018.01.023","article-title":"Efficacy of a deep learning system for detecting glaucomatous optic neuropathy based on color fundus photographs","volume":"125","author":"Z Li","year":"2018","journal-title":"Ophthalmology"},{"issue":"22","key":"pone.0324883.ref017","doi-asserted-by":"crossref","first-page":"2211","DOI":"10.1001\/jama.2017.18152","article-title":"Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes","volume":"318","author":"DSW Ting","year":"2017","journal-title":"JAMA"},{"issue":"7","key":"pone.0324883.ref018","doi-asserted-by":"crossref","first-page":"590","DOI":"10.1097\/IJG.0000000000000354","article-title":"Automated Detection of Glaucoma From Topographic Features of the Optic Nerve Head in Color Fundus Photographs","volume":"25","author":"L Chakrabarty","year":"2016","journal-title":"J Glaucoma"},{"issue":"2","key":"pone.0324883.ref019","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1016\/j.cmpb.2015.08.002","article-title":"An adaptive threshold based image processing technique for improved glaucoma detection and classification","volume":"122","author":"A Issac","year":"2015","journal-title":"Comput Methods Programs Biomed"},{"key":"pone.0324883.ref020","doi-asserted-by":"crossref","first-page":"6694784","DOI":"10.1155\/2021\/6694784","article-title":"An Artificial-Intelligence- and Telemedicine-Based Screening Tool to Identify Glaucoma Suspects from Color Fundus Imaging","volume":"2021","author":"A Bhuiyan","year":"2021","journal-title":"J Ophthalmol"},{"issue":"4","key":"pone.0324883.ref021","doi-asserted-by":"crossref","first-page":"280","DOI":"10.1097\/IJG.0000000000002147","article-title":"Agreement of a Novel Artificial Intelligence Software With Optical Coherence Tomography and Manual Grading of the Optic Disc in Glaucoma","volume":"32","author":"S Shroff","year":"2023","journal-title":"J Glaucoma"},{"issue":"6","key":"pone.0324883.ref022","first-page":"1104","article-title":"Evaluation of an offline, artificial intelligence system for referable glaucoma screening using a smartphone-based fundus camera: a prospective study","volume":"38","author":"DP Rao","year":"2023","journal-title":"Eye (Lond)"},{"issue":"1","key":"pone.0324883.ref023","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1016\/j.ogla.2024.09.002","article-title":"Diagnostic Performance of the Offline Medios Artificial Intelligence for Glaucoma Detection in a Rural Tele-Ophthalmology Setting","volume":"8","author":"S Upadhyaya","year":"2025","journal-title":"Ophthalmol Glaucoma"},{"issue":"6","key":"pone.0324883.ref024","doi-asserted-by":"crossref","first-page":"831","DOI":"10.1001\/archopht.1993.01090060119035","article-title":"The Lens Opacities Classification System III. The Longitudinal Study of Cataract Study Group","volume":"111","author":"Jr Chylack LT","year":"1993","journal-title":"Arch Ophthalmol"},{"key":"pone.0324883.ref025","first-page":"52","article-title":"Clinical decisions in glaucoma","volume-title":"CV Mosby","author":"E Hodapp","year":"1993"},{"issue":"4","key":"pone.0324883.ref026","doi-asserted-by":"crossref","first-page":"724","DOI":"10.1016\/j.ajo.2013.05.027","article-title":"Lifetime risk of blindness in open-angle glaucoma","volume":"156","author":"D Peters","year":"2013","journal-title":"Am J Ophthalmol"},{"issue":"7","key":"pone.0324883.ref027","doi-asserted-by":"crossref","DOI":"10.1016\/S2214-109X(19)30201-3","article-title":"Cost-effectiveness and cost-utility of population-based glaucoma screening in China: a decision-analytic Markov model","volume":"7","author":"J Tang","year":"2019","journal-title":"Lancet Global Health"},{"issue":"1","key":"pone.0324883.ref028","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1097\/IJG.0b013e318182ee0b","article-title":"Reducing the visual burden of glaucoma in Asia: what we know and what we need to know","volume":"18","author":"N Congdon","year":"2009","journal-title":"J Glaucoma"},{"issue":"9","key":"pone.0324883.ref029","doi-asserted-by":"crossref","first-page":"1702","DOI":"10.1016\/S0161-6420(00)00275-X","article-title":"Open-angle glaucoma in an urban population in southern India: the Andhra Pradesh eye disease study","volume":"107","author":"L Dandona","year":"2000","journal-title":"Ophthalmology"},{"issue":"8","key":"pone.0324883.ref030","doi-asserted-by":"crossref","first-page":"1484","DOI":"10.1016\/S0161-6420(03)00564-5","article-title":"Glaucoma in a rural population of southern India: the Aravind comprehensive eye survey","volume":"110","author":"R Ramakrishnan","year":"2003","journal-title":"Ophthalmology"},{"issue":"12","key":"pone.0324883.ref031","doi-asserted-by":"crossref","first-page":"4461","DOI":"10.1167\/iovs.04-1529","article-title":"Prevalence of open-angle glaucoma in a rural south Indian population","volume":"46","author":"L Vijaya","year":"2005","journal-title":"Invest Ophthalmol Vis Sci"},{"issue":"20","key":"pone.0324883.ref032","doi-asserted-by":"crossref","first-page":"1992","DOI":"10.1001\/jama.2022.7013","article-title":"Screening for primary open-angle glaucoma: us preventive services task force recommendation statement","volume":"327","author":"Force US Preventive Services Task","year":"2022","journal-title":"JAMA"},{"issue":"3","key":"pone.0324883.ref033","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1097\/IJG.0000000000000154","article-title":"Differences in Optic Disc Characteristics of Primary Congenital Glaucoma, Juvenile, and Adult Onset Open Angle Glaucoma Patients","volume":"25","author":"V Gupta","year":"2016","journal-title":"J Glaucoma"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0324883","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T17:41:18Z","timestamp":1750959678000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0324883"}},"subtitle":[],"editor":[{"given":"Nader Hussien Lotfy","family":"Bayoumi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,6,26]]},"references-count":33,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,6,26]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0324883","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,26]]}}}