{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T18:06:03Z","timestamp":1779991563046,"version":"3.53.1"},"reference-count":48,"publisher":"Public Library of Science (PLoS)","issue":"5","license":[{"start":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T00:00:00Z","timestamp":1779926400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:sec id=\"sec001\">\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>To evaluate the diagnostic accuracy of two commercially available artificial intelligence (AI) systems based on color fundus photography (CFP), the Laguna ONhE and VUNO Med-Fundus AI, for glaucoma detection, both independently and in combination.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This retrospective cross-sectional study included 370 eyes from 193 patients (248 eyes with primary open-angle glaucoma and 122 healthy eyes). All eyes underwent structural evaluation with swept-source optical coherence tomography (Triton, Topcon) and visual field testing (Octopus 900, Haag-Streit AG). Fundus photographs were analyzed using Laguna ONhE and VUNO Med-Fundus AI systems. Diagnostic accuracy was evaluated.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Both AI systems demonstrated high diagnostic accuracy. Laguna achieved an AUC of 0.879 using Glaucoma Discriminant Function (GDF), and VUNO showed an AUC of 0.857. When combined, GDF\u2009+\u2009VUNO achieved an AUC of 0.903. The Global Mean Deviation (GMD) reached the highest diagnostic accuracy (AUC\u2009=\u20090.916), which was not significantly different from GDF\u2009+\u2009VUNO (p\u2009=\u20090.146).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec004\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Laguna ONhE and VUNO Med-Fundus AI had high diagnostic accuracy in detecting glaucoma using only CFP. Their combined use improved further, achieving accuracy comparable to the GMD. This represents a practical approach for glaucoma screening, particularly in settings without access to OCT or automated perimetry.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pone.0349878","type":"journal-article","created":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T17:34:21Z","timestamp":1779989661000},"page":"e0349878","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Combined diagnostic accuracy of two artificial intelligence systems for glaucoma diagnosis using color fundus photography"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4982-8859","authenticated-orcid":true,"given":"Gilvan Vilarinho","family":"da Silva Filho","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gustavo Coelho","family":"Caiado","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Felipe Zocatelli","family":"Yamamoto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sergio Henrique","family":"Teixeira","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tiago dos Santos","family":"Prata","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carolina Pelegrini Barbosa","family":"Gracitelli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6266-6922","authenticated-orcid":true,"given":"Augusto","family":"Paranhos Jr","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,5,28]]},"reference":[{"issue":"9422","key":"pone.0349878.ref001","doi-asserted-by":"crossref","first-page":"1711","DOI":"10.1016\/S0140-6736(04)16257-0","article-title":"Primary open-angle glaucoma","volume":"363","author":"RN Weinreb","year":"2004","journal-title":"Lancet"},{"issue":"11","key":"pone.0349878.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":"Y-C Tham","year":"2014","journal-title":"Ophthalmology"},{"key":"pone.0349878.ref003","volume-title":"The clinical effectiveness and cost-effectiveness of screening for open angle glaucoma: a systematic review and economic evaluation. NIHR Health Technology Assessment programme: Executive Summaries","author":"JM Burr","year":"2007"},{"issue":"6","key":"pone.0349878.ref004","doi-asserted-by":"crossref","first-page":"688","DOI":"10.1016\/j.preteyeres.2007.08.001","article-title":"A framework for comparing structural and functional measures of glaucomatous damage","volume":"26","author":"DC Hood","year":"2007","journal-title":"Prog Retin Eye Res"},{"issue":"4","key":"pone.0349878.ref005","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1097\/IJG.0b013e31826a9707","article-title":"Detection of early glaucomatous progression with different parameters of the RTVue optical coherence tomograph","volume":"23","author":"F Naghizadeh","year":"2014","journal-title":"J Glaucoma"},{"issue":"11","key":"pone.0349878.ref006","doi-asserted-by":"crossref","first-page":"1889","DOI":"10.1016\/S0161-6420(96)30410-7","article-title":"Reproducibility of nerve fiber layer thickness measurements using optical coherence tomography","volume":"103","author":"JS Schuman","year":"1996","journal-title":"Ophthalmology"},{"issue":"12","key":"pone.0349878.ref007","doi-asserted-by":"crossref","first-page":"5741","DOI":"10.1167\/iovs.09-3715","article-title":"Detection of glaucoma progression with stratus OCT retinal nerve fiber layer, optic nerve head, and macular thickness measurements","volume":"50","author":"FA Medeiros","year":"2009","journal-title":"Invest Ophthalmol Vis Sci"},{"issue":"7","key":"pone.0349878.ref008","doi-asserted-by":"crossref","first-page":"1388","DOI":"10.1016\/j.ophtha.2012.12.014","article-title":"Detection of glaucomatous progression by spectral-domain optical coherence tomography","volume":"120","author":"JH Na","year":"2013","journal-title":"Ophthalmology"},{"issue":"7","key":"pone.0349878.ref009","doi-asserted-by":"crossref","first-page":"498","DOI":"10.1097\/IJG.0b013e318220dbb7","article-title":"Glaucoma diagnostic capabilities of optic nerve head parameters as determined by Cirrus HD optical coherence tomography","volume":"21","author":"KR Sung","year":"2012","journal-title":"J Glaucoma"},{"issue":"51","key":"pone.0349878.ref010","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3310\/hta17510","article-title":"Improving the economic value of photographic screening for optical coherence tomography-detectable macular oedema: a prospective, multicentre, UK study","volume":"17","author":"J Olson","year":"2013","journal-title":"Health Technol Assess"},{"issue":"7","key":"pone.0349878.ref011","doi-asserted-by":"crossref","first-page":"525","DOI":"10.1002\/jbio.201200243","article-title":"Optical coherence tomography for advanced screening in the primary care office","volume":"7","author":"RL Shelton","year":"2014","journal-title":"J Biophotonics"},{"issue":"3","key":"pone.0349878.ref012","doi-asserted-by":"crossref","first-page":"193","DOI":"10.4274\/tjo.galenos.2021.29726","article-title":"Investigation of the Role of Convolutional Neural Network Architectures in the Diagnosis of Glaucoma using Color Fundus Photography","volume":"52","author":"E Atalay","year":"2022","journal-title":"Turk J Ophthalmol"},{"key":"pone.0349878.ref013","doi-asserted-by":"crossref","first-page":"2180","DOI":"10.3390\/diagnostics13132180","article-title":"Automated glaucoma screening and diagnosis based on retinal fundus images using deep learning approaches: A comprehensive review","volume":"13","author":"MJM Zedan","year":"2023","journal-title":"Diagnostics"},{"issue":"9","key":"pone.0349878.ref014","doi-asserted-by":"crossref","first-page":"1317","DOI":"10.1016\/j.jval.2025.06.006","article-title":"The Cost-Effectiveness of an Artificial Intelligence-Based Population-Wide Screening Program for Primary Open-Angle Glaucoma in The Netherlands","volume":"28","author":"B-J Boverhof","year":"2025","journal-title":"Value Health"},{"issue":"1","key":"pone.0349878.ref015","doi-asserted-by":"crossref","first-page":"482","DOI":"10.1167\/iovs.12-10761","article-title":"Measuring hemoglobin levels in the optic nerve head: comparisons with other structural and functional parameters of glaucoma","volume":"54","author":"M Gonzalez de la Rosa","year":"2013","journal-title":"Invest Ophthalmol Vis Sci"},{"issue":"3","key":"pone.0349878.ref016","doi-asserted-by":"crossref","first-page":"1562","DOI":"10.1167\/iovs.14-15592","article-title":"Estimation of the relative amount of hemoglobin in the cup and neuroretinal rim using stereoscopic color fundus images","volume":"56","author":"C Pena-Betancor","year":"2015","journal-title":"Invest Ophthalmol Vis Sci"},{"key":"pone.0349878.ref017","doi-asserted-by":"crossref","first-page":"1","DOI":"10.4172\/2155-9570.1000760","article-title":"Segmentation of the optic nerve head based on deep learning to determine its hemoglobin content in normal and glaucomatous subjects","volume":"9","author":"D Gonzalez-Hernandez","year":"2018","journal-title":"J Clin Exp Ophthalmol"},{"issue":"1","key":"pone.0349878.ref018","doi-asserted-by":"crossref","DOI":"10.1136\/bmjophth-2022-000972","article-title":"Optic disc area frequency distribution in a large sample of retinographic images","volume":"7","author":"M Gonzalez-Hernandez","year":"2022","journal-title":"BMJ Open Ophthalmol"},{"issue":"17","key":"pone.0349878.ref019","doi-asserted-by":"crossref","first-page":"5485","DOI":"10.3390\/jcm12175485","article-title":"Agreement between Five Experts and the Laguna ONhE Automatic Colourimetric Application Interpreting the Glaucomatous Aspect of the Optic Nerve","volume":"12","author":"C Mendez-Hernandez","year":"2023","journal-title":"J Clin Med"},{"issue":"7","key":"pone.0349878.ref020","doi-asserted-by":"crossref","first-page":"567","DOI":"10.1097\/IJG.0000000000002026","article-title":"Discrimination Between Healthy Eyes and Those With Mild Glaucoma Damage Using Hemoglobin Measurements of the Optic Nerve Head","volume":"31","author":"LSd Meneses","year":"2022","journal-title":"J Glaucoma"},{"key":"pone.0349878.ref021","doi-asserted-by":"crossref","first-page":"348","DOI":"10.1097\/IJG.0000000000000160","article-title":"Reproducibility of Optic Nerve Head Hemoglobin Measures","volume":"25","author":"C Mendez-Hernandez","year":"2016","journal-title":"J Glaucoma"},{"issue":"6","key":"pone.0349878.ref022","doi-asserted-by":"crossref","first-page":"798","DOI":"10.3109\/02713683.2015.1062112","article-title":"Estimating the Amount of Hemoglobin in the Neuroretinal Rim Using Color Images and OCT","volume":"41","author":"E Medina-Mesa","year":"2016","journal-title":"Curr Eye Res"},{"key":"pone.0349878.ref023","first-page":"2340236","article-title":"Relationship between Retinal Nerve Fiber Layer Thickness and Hemoglobin Present in the Optic Nerve Head in Glaucoma","volume":"2017","author":"M Gonzalez-Hernandez","year":"2017","journal-title":"J Ophthalmol"},{"key":"pone.0349878.ref024","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1007\/978-3-319-18959-8_10","article-title":"Measuring Hemoglobin Levels in the Optic Nerve Head for Glaucoma Management.","author":"M Gonzalez-de-la-Rosa","year":"2016","journal-title":"Glaucoma Imaging. Springer International Publishing"},{"issue":"43","key":"pone.0349878.ref025","article-title":"A Novel Fundus Image Reading Tool for Efficient Generation of a Multi-dimensional Categorical Image Database for Machine Learning Algorithm Training","volume":"33","author":"SJ Park","year":"2018","journal-title":"J Korean Med Sci"},{"key":"pone.0349878.ref026"},{"key":"pone.0349878.ref027","first-page":"176","article-title":"Classification of Findings with Localized Lesions in Fundoscopic Images Using a Regionally Guided CNN: 1st International Workshop on Computational Pathology, COMPAY 2018 and 5th International Workshop on Ophthalmic Medical Image Analysis, OMIA 2018 Held in Conjunction with MICCAI 2018.","author":"J Son","year":"2018","journal-title":"Comput Pathol Ophthalmic Med Image Anal - First Int Workshop COMPAY 2018 5th Int Workshop OMIA 2018 Held Conjunction MICCAI 2018 Proc"},{"issue":"6","key":"pone.0349878.ref028","doi-asserted-by":"crossref","first-page":"923","DOI":"10.1007\/s10278-018-0099-2","article-title":"Laterality Classification of Fundus Images Using Interpretable Deep Neural Network","volume":"31","author":"Y Jang","year":"2018","journal-title":"J Digit Imaging"},{"issue":"3","key":"pone.0349878.ref029","doi-asserted-by":"crossref","first-page":"499","DOI":"10.1007\/s10278-018-0126-3","article-title":"Towards Accurate Segmentation of Retinal Vessels and the Optic Disc in Fundoscopic Images with Generative Adversarial Networks","volume":"32","author":"J Son","year":"2019","journal-title":"J Digit Imaging"},{"issue":"1","key":"pone.0349878.ref030","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.ophtha.2019.05.029","article-title":"Development and Validation of Deep Learning Models for Screening Multiple Abnormal Findings in Retinal Fundus Images","volume":"127","author":"J Son","year":"2020","journal-title":"Ophthalmology"},{"issue":"15","key":"pone.0349878.ref031","doi-asserted-by":"crossref","first-page":"3231","DOI":"10.3390\/jcm10153231","article-title":"Fully Automated Colorimetric Analysis of the Optic Nerve Aided by Deep Learning and Its Association with Perimetry and OCT for the Study of Glaucoma","volume":"10","author":"M Gonzalez-Hernandez","year":"2021","journal-title":"J Clin Med"},{"issue":"24","key":"pone.0349878.ref032","doi-asserted-by":"crossref","first-page":"7294","DOI":"10.3390\/jcm11247294","article-title":"Glaucoma Incidence and Progression in Diabetics: The Canary Islands Study Using the Laguna ONhE Application","volume":"11","author":"M Gonzalez-Hernandez","year":"2022","journal-title":"J Clin Med"},{"key":"pone.0349878.ref033","first-page":"1828","article-title":"New gip index for progression analysis, using the laguna onhE method for the optic nerve head hemoglobin evaluation","volume":"62","author":"M Gonzalez-Hernandez","year":"2021","journal-title":"Investigative Ophthalmology & Visual Science"},{"key":"pone.0349878.ref034","doi-asserted-by":"crossref","first-page":"101561","DOI":"10.1016\/j.media.2019.101561","article-title":"IDRiD: Diabetic retinopathy - segmentation and grading challenge","volume":"59","author":"P Porwal","year":"2020","journal-title":"Med Image Anal"},{"key":"pone.0349878.ref035","doi-asserted-by":"crossref","first-page":"101570","DOI":"10.1016\/j.media.2019.101570","article-title":"REFUGE Challenge: A unified framework for evaluating automated methods for glaucoma assessment from fundus photographs","volume":"59","author":"JI Orlando","year":"2020","journal-title":"Med Image Anal"},{"issue":"3","key":"pone.0349878.ref036","doi-asserted-by":"crossref","first-page":"159","DOI":"10.3109\/09286586.2012.674614","article-title":"Regression methods when the eye is the unit of analysis","volume":"19","author":"RJ Glynn","year":"2012","journal-title":"Ophthalmic Epidemiol"},{"issue":"4","key":"pone.0349878.ref037","doi-asserted-by":"crossref","first-page":"525","DOI":"10.1002\/(SICI)1097-0258(20000229)19:4<525::AID-SIM354>3.0.CO;2-O","article-title":"Statistical methods for the evaluation of diagnostic measurements concerning paired organs","volume":"19","author":"P Martus","year":"2000","journal-title":"Stat Med"},{"issue":"2065","key":"pone.0349878.ref038","first-page":"20150202","article-title":"Principal component analysis: a review and recent developments","volume":"374","author":"IT Jolliffe","year":"2016","journal-title":"Philos Trans A Math Phys Eng Sci"},{"key":"pone.0349878.ref039","doi-asserted-by":"crossref","first-page":"212","DOI":"10.1016\/j.oftal.2014.09.007","article-title":"Correlaci\u00f3n de la relaci\u00f3n excavaci\u00f3n\/papila \u00f3ptica medida mediante HRT-III, SD-OCT y el dispositivo de colorimetr\u00eda fotogr\u00e1fica Laguna OnhE\u22c6","volume":"90","author":"I Rodr\u00edguez U\u00f1a","year":"2015","journal-title":"Arch Soc Esp Oftalmol"},{"issue":"7","key":"pone.0349878.ref040","doi-asserted-by":"crossref","first-page":"697","DOI":"10.1111\/aos.13050","article-title":"Glaucoma diagnostic capacity of optic nerve head haemoglobin measures compared with spectral domain OCT and HRT III confocal tomography","volume":"94","author":"C Mendez-Hernandez","year":"2016","journal-title":"Acta Ophthalmol"},{"key":"pone.0349878.ref041","first-page":"9916102","article-title":"Optic Nerve Head Hemoglobin Levels in Glaucoma: A Structural and Functional Correlation Study","volume":"2021","author":"JAG Rocha","year":"2021","journal-title":"J Ophthalmol"},{"issue":"6","key":"pone.0349878.ref042","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1097\/IJG.0000000000002542","article-title":"Diagnostic Capacity and Correlation of Optic Nerve Colorimetry With Structural Parameters in Primary Open Angle Glaucoma","volume":"34","author":"L Salazar-Qui\u00f1ones","year":"2025","journal-title":"J Glaucoma"},{"key":"pone.0349878.ref043","doi-asserted-by":"crossref","first-page":"328","DOI":"10.2478\/jee-2023-0040","article-title":"Detecting glaucoma from fundus images using ensemble learning","volume":"74","author":"V Kurilov\u00e1","year":"2023","journal-title":"J Electr Eng"},{"issue":"10","key":"pone.0349878.ref044","doi-asserted-by":"crossref","first-page":"1516","DOI":"10.1080\/02713683.2021.1900268","article-title":"Deep Learning Ensemble Method for Classifying Glaucoma Stages Using Fundus Photographs and Convolutional Neural Networks","volume":"46","author":"H Cho","year":"2021","journal-title":"Curr Eye Res"},{"issue":"1","key":"pone.0349878.ref045","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1038\/s41746-025-01473-w","article-title":"A hybrid multi model artificial intelligence approach for glaucoma screening using fundus images","volume":"8","author":"P Sharma","year":"2025","journal-title":"NPJ Digit Med"},{"issue":"8","key":"pone.0349878.ref046","doi-asserted-by":"crossref","first-page":"4104","DOI":"10.1167\/iovs.09-4716","article-title":"Effect of disease severity on the performance of Cirrus spectral-domain OCT for glaucoma diagnosis","volume":"51","author":"MT Leite","year":"2010","journal-title":"Invest Ophthalmol Vis Sci"},{"issue":"1","key":"pone.0349878.ref047","doi-asserted-by":"crossref","first-page":"26151","DOI":"10.1038\/s41598-025-11697-1","article-title":"Machine learning technology in the classification of glaucoma severity using fundus photographs","volume":"15","author":"S Thanapaisal","year":"2025","journal-title":"Sci Rep"},{"issue":"6","key":"pone.0349878.ref048","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0324883","article-title":"Evaluating real-world performance of an automated offline glaucoma AI on a smartphone fundus camera across glaucoma severity stages","volume":"20","author":"S Senthil","year":"2025","journal-title":"PLoS One"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0349878","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T17:34:29Z","timestamp":1779989669000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0349878"}},"subtitle":[],"editor":[{"given":"Abdel-Razzak M.","family":"Al-Hinnawi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,5,28]]},"references-count":48,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5,28]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0349878","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,28]]}}}