{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T17:55:28Z","timestamp":1782237328755,"version":"3.54.5"},"reference-count":51,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Ophthalmol."],"abstract":"Introduction<\/jats:title>Artificial intelligence (AI) shows promise in ophthalmology, but its potential in tertiary care settings in Latin America remains understudied. We present a Mexican AI-powered screening tool and evaluate it against first-year ophthalmology residents in a tertiary care setting in Mexico City.<\/jats:p><\/jats:sec>Methods<\/jats:title>We analyzed data from 435 adult patients undergoing their first ophthalmic evaluation using an AI-based platform and first-year ophthalmology residents. The platform employs an Inception V3\u2013based multi-output classification model with 512 \u00d7 512 input resolution to capture small lesions when detecting retinal disease. To evaluate glaucoma suspects, the system uses U-Net models that segment the optic disc and cup to calculate cup-to-disc ratio (CDR) from their vertical heights. The AI and resident evaluations were compared with expert annotations for retinal disease, CDR measurements, and glaucoma suspect classification. In addition, we evaluated a synergistic approach combining AI and resident assessments.<\/jats:p><\/jats:sec>Results<\/jats:title>For glaucoma suspect classification, AI outperformed residents in accuracy (88.6% vs. 82.9%, p<\/jats:italic> = 0.016), sensitivity (63.0% vs. 50.0%, p<\/jats:italic> = 0.116), and specificity (94.5% vs. 90.5%, p<\/jats:italic> = 0.062). The synergistic approach achieved a higher sensitivity (80.4%) than ophthalmic residents alone or AI alone (p &lt;<\/jats:italic> 0.001). AI\u2019s CDR estimates showed lower mean absolute error (0.056 vs. 0.105, p &lt;<\/jats:italic> 0.001) and higher correlation with expert measurements (r<\/jats:italic> = 0.728 vs. r<\/jats:italic> = 0.538). In the retinal disease assessment, AI demonstrated higher sensitivity (90.1% vs. 63.0% for medium\/high risk, p &lt;<\/jats:italic> 0.001) and specificity (95.8% vs. 90.4%, p &lt;<\/jats:italic> 0.001). Furthermore, differences between AI and residents were statistically significant across all metrics. The synergistic approach achieved the highest sensitivity for retinal disease (92.6% for medium\/high risk, 100% for high risk).<\/jats:p><\/jats:sec>Discussion<\/jats:title>AI outperformed first-year residents in key ophthalmic assessments. The synergistic use of AI and resident assessments showed potential for optimizing diagnostic accuracy, highlighting the value of AI as a supportive tool in ophthalmic practice, especially for early career clinicians.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fopht.2025.1581212","type":"journal-article","created":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T04:10:43Z","timestamp":1747627843000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Synergistic AI-resident approach achieves superior diagnostic accuracy in tertiary ophthalmic care for glaucoma and retinal disease"],"prefix":"10.3389","volume":"5","author":[{"given":"Dalia","family":"Camacho-Garc\u00eda-Forment\u00ed","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gabriela","family":"Bayl\u00f3n-V\u00e1zquez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karen","family":"Arriozola-Rodr\u00edguez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Enrique","family":"Avalos-Ramirez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Curt","family":"Hartleben-Matkin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hugo","family":"Valdez-Flores","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Damaris","family":"Hodelin-Fuentes","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alejandro","family":"Noriega","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,5,19]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1016\/j.optom.2016.02.003","article-title":"Glaucoma history and risk factors","volume":"10","author":"McMonnies","year":"2017","journal-title":"J Optometry"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2022.1079217","article-title":"Classification of diabetic retinopathy: Past, present and future","volume":"13","author":"Yang","year":"2022","journal-title":"Front Endocrinol (Lausanne)"},{"key":"B3","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1111\/ceo.12905","article-title":"Hypertensive eye disease: a review","volume":"45","author":"Fraser-Bell","year":"2017","journal-title":"Clin Exp Ophthalmol"},{"key":"B4","doi-asserted-by":"publisher","first-page":"P1","DOI":"10.1016\/j.ophtha.2019.09.024","article-title":"Age-related macular degeneration preferred practice pattern\u00ae","volume":"127","author":"Flaxel","year":"2020","journal-title":"Ophthalmology"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1016\/j.pop.2015.05.012","article-title":"Cataracts","volume":"42","author":"Thompson","year":"2015","journal-title":"Primary Care"},{"key":"B6","unstructured":"Mexico City, Mexico\n Consejo Mexicano de Oftalmolog\u00eda\n Listado de M\u00e9dicos\n \n 2024"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.21149\/14832","article-title":"Prevalencia de prediabetes y diabetes en M\u00e9xico: Ensanut 2022","volume":"65","author":"Basto-Abreu","year":"2023","journal-title":"Salud Publica Mex"},{"key":"B8","unstructured":"Aguascalientes, Mexico\n Instituto Nacional de Estad\u00edstica y Geograf\u00eda\n Poblaci\u00f3n\n \n 2021"},{"key":"B9","doi-asserted-by":"publisher","first-page":"692","DOI":"10.21149\/12851","article-title":"Epidemiolog\u00eda de la hipertensi\u00f3n arterial en adultos mexicanos: diagn\u00f3stico, control y tendencias. Ensanut 2020","volume":"63","author":"Campos-Nonato","year":"2021","journal-title":"Salud p\u00fablica M\u00e9xico"},{"key":"B10","first-page":"1","volume-title":"Estad\u00edsticas a prop\u00f3sito del d\u00eda internacional de las personas adultas mayores","year":"2022"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1089\/dia.2019.0164","article-title":"The value of automated diabetic retinopathy screening with the EyeArt system: A study of more than 100,000 consecutive encounters from people with diabetes","volume":"21","author":"Bhaskaranand","year":"2019","journal-title":"Diabetes Technol Ther"},{"key":"B12","article-title":"Advanced retinal image analysis for AMD screening applications","volume":"56","author":"Ramachandra","year":"2015","journal-title":"Invest Ophthalmol Visual Sci"},{"key":"B13","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1109\/MC.2020.3004392","article-title":"Artificial intelligence-based referral system for patients with diabetic retinopathy","volume":"53","author":"Gonzalez-Briceno","year":"2020","journal-title":"Computer"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1038\/s41433-020-0927-8","article-title":"Evaluation of an ai system for the detection of diabetic retinopathy from images captured with a handheld portable fundus camera: the mailor ai study","volume":"35","author":"Rogers","year":"2021","journal-title":"Eye (Lond)"},{"key":"B15","doi-asserted-by":"publisher","first-page":"4828","DOI":"10.1038\/s41467-021-25138-w","article-title":"Automatic detection of 39 fundus diseases and conditions in retinal photographs using deep neural networks","volume":"12","author":"Cen","year":"2021","journal-title":"Nat Commun"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1016\/S2589-7500(21)00086-8","article-title":"Application of comprehensive artificial intelligence retinal expert (CARE) system: a national real-world evidence study","volume":"3","author":"Lin","year":"2021","journal-title":"Lancet Digital Health"},{"key":"B17","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1038\/s41433-020-01366-0","article-title":"Clinical validation of an artificial intelligence-based diabetic retinopathy screening tool for a national health system","volume":"36","author":"Arenas-Cavalli","year":"2022","journal-title":"Eye (Lond)"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2022.9960","article-title":"Artificial intelligence for screening of multiple retinal and optic nerve diseases","volume":"5","author":"Dong","year":"2022","journal-title":"JAMA Network Open"},{"key":"B19","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1016\/j.compmedimag.2019.02.005","article-title":"Robust optic disc and cup segmentation with deep learning for glaucoma detection","volume":"74","author":"Yu","year":"2019","journal-title":"Computerized Med Imaging Graphics"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1007\/s42452-022-04984-3","article-title":"ODGNet: a deep learning model for automated optic disc localization and glaucoma classification using fundus images","volume":"4","author":"Latif","year":"2022","journal-title":"SN Appl Sci"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.3390\/s22041449","article-title":"Evaluations of deep learning approaches for glaucoma screening using retinal images from mobile device","volume":"22","author":"Neto","year":"2022","journal-title":"Sensors (Basel)"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.2196\/37532","article-title":"Emerging trends and research foci in artificial intelligence for retinal diseases: Bibliometric and visualization study","volume":"24","author":"Zhao","year":"2022","journal-title":"J Med Internet Res"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1007\/s10792-016-0329-x","article-title":"Agreement among ophthalmologists in marking the optic disc and optic cup in fundus images","volume":"37","author":"Almazroa","year":"2017","journal-title":"Int Ophthalmol"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1109\/Access.6287639","article-title":"Feasibility of diagnosing both severity and features of diabetic retinopathy in fundus photography","volume":"7","author":"Wang","year":"2019","journal-title":"IEEE Access"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2005.11.021","article-title":"Interobserver agreement in the interpretation of single-field digital fundus images for diabetic retinopathy screening","volume":"113","author":"Ruamviboonsuk","year":"2006","journal-title":"Ophthalmol"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.2196\/25290","article-title":"Screening diabetic retinopathy using an automated retinal image analysis system in independent and assistive use cases in Mexico: Randomized controlled trial","volume":"5","author":"Noriega","year":"2021","journal-title":"JMIR Formative Res"},{"key":"B27","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1186\/s12909-022-03272-3","article-title":"Using artificial intelligence reading label system in diabetic retinopathy grading training of junior ophthalmology residents and medical students","volume":"22","author":"Han","year":"2022","journal-title":"BMC Med Educ"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.3389\/fcell.2022.1053079","article-title":"Artificial intelligence-based pathologic myopia identification system in the ophthalmology residency training program","volume":"10","author":"Fang","year":"2022","journal-title":"Front Cell Dev Biol"},{"key":"B29","unstructured":"LinkedAI platform\n \n \n \n 2024"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1001\/archopht.124.11.1579","article-title":"The ISNT rule and differentiation of normal from glaucomatous eyes","volume":"124","author":"Harizman","year":"2006","journal-title":"Arch Ophthalmol (Chicago Ill.: 1960)"},{"key":"B31","unstructured":"Televal\n \n \n \n 2024"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1016\/S0161-6420(03)00475-5","article-title":"Proposed international clinical diabetic retinopathy and diabetic macular edema disease severity scales","volume":"110","author":"Wilkinson","year":"2003","journal-title":"Ophthalmology"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1097\/OPX.0000000000000205","article-title":"Utility of hard exudates for the screening of macular edema","volume":"91","author":"Litvin","year":"2014","journal-title":"Optometry Vision Sci"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajo.2015.01.022","article-title":"International photographic classification and grading system for myopic maculopathy","volume":"159","author":"Ohno-Matsui","year":"2015","journal-title":"Am J Ophthalmol"},{"key":"B35","first-page":"1","volume-title":"Detecci\u00f3n de retinopat\u00eda diab\u00e9tica en primer nivel de atenci\u00f3n","year":"2014"},{"key":"B36","unstructured":"retinIA\n \n \n \n 2024"},{"key":"B37","doi-asserted-by":"publisher","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":"Ting","year":"2017","journal-title":"Jama"},{"key":"B38","doi-asserted-by":"publisher","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":"Mendez-Hernandez","year":"2023","journal-title":"J Clin Med"},{"key":"B39","doi-asserted-by":"publisher","first-page":"1128","DOI":"10.3390\/jpm13071128","article-title":"Performance of a support vector machine learning tool for diagnosing diabetic retinopathy in clinical practice","volume":"13","author":"Nissen","year":"2023","journal-title":"J Personalized Med"},{"key":"B40","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2016.308","article-title":"Rethinking the inception architecture for computer vision","author":"Szegedy","year":"2016"},{"key":"B41","volume-title":"Kaggle diabetic retinopathy detection competition report","author":"Graham","year":"2015"},{"key":"B42","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","author":"Tan","year":"2019"},{"key":"B43","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"B44","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06555-x","article-title":"A foundation model for generalizable disease detection from retinal images","volume":"622","author":"Zhou","year":"2023","journal-title":"Nature"},{"key":"B45","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV.2017.74","article-title":"Grad-cam: Visual explanations from deep networks via gradient-based localization","author":"Selvaraju","year":"2017"},{"key":"B46","volume-title":"Smoothgrad: removing noise by adding noise","author":"Smilkov","year":"2017"},{"key":"B47","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-24574-4_28","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"B48","doi-asserted-by":"publisher","DOI":"10.11613\/issn.1846-7482","article-title":"Interrater reliability: the kappa statistic","volume":"22","author":"McHugh","year":"2012","journal-title":"Biochemia Med (Zagreb)"},{"key":"B49","doi-asserted-by":"publisher","DOI":"10.1007\/BF00944008","article-title":"Cup-disc ratio in early open-angle glaucoma","volume":"26","author":"Armaly","year":"1969","journal-title":"Documenta Ophthalmologica"},{"key":"B50","doi-asserted-by":"publisher","DOI":"10.1001\/archopht.1995.01100050054031","article-title":"Quantification of nerve fiber layer thickness in normal and glaucomatous eyes using optical coherence tomography: A pilot study","volume":"113","author":"Schuman","year":"1995","journal-title":"Arch Ophthalmol"},{"key":"B51","doi-asserted-by":"publisher","DOI":"10.1101\/2024.08.26.24311677","article-title":"Comparative performance of an ai tool and first-year residents for retinal disease and glaucoma assessments: A study in a mexican tertiary care setting","author":"Camacho-Garc\u00eda-Forment\u00ed","year":"2024","journal-title":"medRxiv"}],"container-title":["Frontiers in Ophthalmology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fopht.2025.1581212\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T04:10:47Z","timestamp":1747627847000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fopht.2025.1581212\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":51,"alternative-id":["10.3389\/fopht.2025.1581212"],"URL":"https:\/\/doi.org\/10.3389\/fopht.2025.1581212","relation":{},"ISSN":["2674-0826"],"issn-type":[{"value":"2674-0826","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,19]]},"article-number":"1581212"}}