{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T23:19:30Z","timestamp":1788391170942,"version":"build-2803163510"},"reference-count":43,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"10","funder":[{"DOI":"10.13039\/100000053","name":"National Eye Institute","doi-asserted-by":"crossref","award":["UG1EY020522"],"award-info":[{"award-number":["UG1EY020522"]}],"id":[{"id":"10.13039\/100000053","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,10]]},"abstract":"<jats:sec>\n                    <jats:title>Purpose:<\/jats:title>\n                    <jats:p>To identify, appraise, and synthesize the performance of artificial intelligence\u2013based meibography reading as compared with human graders in diagnosing meibomian gland dysfunction.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods:<\/jats:title>\n                    <jats:p>We followed Cochrane methodology and reporting guidelines for diagnostic test accuracy reviews. To assess potential risk of bias and applicability, we used a modified Quality Assessment of Diagnostic Accuracy Studies-2 checklist. We applied bivariate logistic models to estimate summary sensitivity and specificity when appropriate and used the GRADE framework to rate the certainty of the evidence.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results:<\/jats:title>\n                    <jats:p>We identified 14 eligible studies involving 5511 predominantly middle-aged participants (average age: 27\u201355 years) who were primarily female (\u226554.5%). A total of 18,926 meibography images were obtained through noncontact infrared (11 studies) or in vivo confocal microscopy (three studies). Two studies reported external validation of deep learning models, 12 reported internally validated models, and one reported both. All but one study had high risk of bias in at least one domain; 12 studies raised high or intermediate concern about applicability. Based on three external evaluations, the summary sensitivity and specificity for diagnosing meibomian gland dysfunction from normal glands were 97.5% (95% confidence interval: 77.5%\u201399.8%) and 85.5% (95% confidence interval: 47.3%\u201397.5%). Sources of heterogeneity in internally validated models included study population, case mix, and others. The overall evidence was very low to low certainty because of imprecision, high risk of bias, and concerns about applicability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions:<\/jats:title>\n                    <jats:p>Artificial intelligence\u2013based meibography grading appears less accurate than human graders. Future studies should adopt rigorous designs, including a more diverse participant pool (or image set), and external validation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1097\/ico.0000000000004151","type":"journal-article","created":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T18:01:40Z","timestamp":1775239300000},"page":"1318-1331","update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":0,"title":["Artificial Intelligence for Diagnosing Meibomian Gland Dysfunction: A Systematic Review and Meta-Analysis of Diagnostic Test Accuracy Studies"],"prefix":"10.1097","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1151-7983","authenticated-orcid":false,"given":"Su-Hsun","family":"Liu","sequence":"first","affiliation":[{"name":"Department of Ophthalmology, School of Medicine, University of Colorado Anschutz Medical Campus, Aurora, CO;"},{"name":"Department of Epidemiology, Colorado School of Public Health, Aurora, CO;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Margi","family":"Shah","sequence":"additional","affiliation":[{"name":"Independent Researcher, Houston, TX;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Louis","family":"Leslie","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, School of Medicine, University of Colorado Anschutz Medical Campus, Aurora, CO;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jui-En","family":"Lo","sequence":"additional","affiliation":[{"name":"Department of Internal Medicine, Metrohealth Medical Center, Cleveland, OH;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Enoch","family":"Ansah-Asiedu","sequence":"additional","affiliation":[{"name":"College of Optometry, University of Houston, Houston, TX;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ben","family":"Harnke","sequence":"additional","affiliation":[{"name":"Strauss Health Sciences Library, University of Colorado Anschutz Medical Campus, Aurora, CO;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Scott G.","family":"Hauswirth","sequence":"additional","affiliation":[{"name":"Domp\u00e9 Farmaceutici, S.p.A., Milan, Italy;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gianni","family":"Virgili","sequence":"additional","affiliation":[{"name":"IRCCS-Fondazione Bietti, Rome, Italy; and"},{"name":"NEUROFARBA, University of Florence, Florence, Italy."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianjing","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, School of Medicine, University of Colorado Anschutz Medical Campus, Aurora, CO;"},{"name":"Department of Epidemiology, Colorado School of Public Health, Aurora, CO;"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","published-online":{"date-parts":[[2026,3,18]]},"reference":[{"key":"R1-20260902","doi-asserted-by":"crossref","first-page":"1181","DOI":"10.1001\/jamaophthalmol.2022.4394","article-title":"Prevalence and incidence of dry eye and Meibomian gland dysfunction in the United States: a systematic review and meta-analysis","volume":"140","author":"McCann","year":"2022","journal-title":"JAMA Ophthalmol"},{"key":"R2-20260902","doi-asserted-by":"crossref","first-page":"298","DOI":"10.1016\/j.jtos.2023.11.003","article-title":"Recent advances in age-related meibomian gland dysfunction (ARMGD)","volume":"30","author":"Moreno","year":"2023","journal-title":"Ocul Surf."},{"key":"R3-20260902","doi-asserted-by":"crossref","first-page":"2006","DOI":"10.1167\/iovs.10-6997f","article-title":"The international workshop on meibomian gland dysfunction: report of the diagnosis subcommittee","volume":"52","author":"Tomlinson","year":"2011","journal-title":"Invest Ophthalmol Vis Sci."},{"key":"R4-20260902","doi-asserted-by":"crossref","first-page":"2601","DOI":"10.1167\/iovs.11-9228","article-title":"Prevalence of asymptomatic and symptomatic meibomian gland dysfunction in the general population of Spain","volume":"53","author":"Viso","year":"2012","journal-title":"Invest Ophthalmol Vis Sci."},{"key":"R5-20260902","doi-asserted-by":"crossref","first-page":"1994","DOI":"10.1167\/iovs.10-6997e","article-title":"The international workshop on meibomian gland dysfunction: report of the subcommittee on the epidemiology of, and associated risk factors for, MGD","volume":"52","author":"Schaumberg","year":"2011","journal-title":"Invest Ophthalmol Vis Sci."},{"key":"R6-20260902","doi-asserted-by":"crossref","first-page":"100334","DOI":"10.1016\/j.xops.2023.100334","article-title":"A deep learning approach for Meibomian gland appearance evaluation","volume":"3","author":"Swiderska","year":"2023","journal-title":"Ophthalmol Sci."},{"key":"R7-20260902","doi-asserted-by":"crossref","first-page":"911","DOI":"10.1016\/j.ophtha.2007.06.031","article-title":"Noncontact infrared meibography to document age-related changes of the meibomian glands in a normal population","volume":"115","author":"Arita","year":"2008","journal-title":"Ophthalmology"},{"key":"R8-20260902","doi-asserted-by":"crossref","first-page":"1099","DOI":"10.1016\/j.ajo.2013.01.017","article-title":"Meibomian gland morphology in Japanese infants, children, and adults observed using a mobile pen-shaped infrared meibography device","volume":"155","author":"Shirakawa","year":"2013","journal-title":"Am J Ophthalmol."},{"key":"R9-20260902","doi-asserted-by":"crossref","first-page":"e0165558","DOI":"10.1371\/journal.pone.0165558","article-title":"A simple novel technique of infrared meibography by means of spectral-domain optical coherence tomography: a cross-sectional clinical study","volume":"11","author":"Napoli","year":"2016","journal-title":"PLoS One"},{"key":"R10-20260902","doi-asserted-by":"crossref","first-page":"7432131","DOI":"10.1155\/2016\/7432131","article-title":"In vivo laser scanning confocal microscopy of human meibomian glands in aging and ocular surface diseases","volume":"2016","author":"Fasanella","year":"2016","journal-title":"Biomed Res Int."},{"key":"R11-20260902","first-page":"268","article-title":"In vivo confocal microscopy evaluation of ocular and cutaneous alterations in patients with rosacea","volume":"101","author":"Liang","year":"2017","journal-title":"Br J Ophthalmol."},{"key":"R12-20260902","article-title":"Artificial intelligence for meibomian gland dysfunction: a diagnostic test accuracy review (protocol)","author":"Liu","year":"2024","journal-title":"Open Sci Forum"},{"key":"R14-20260902","doi-asserted-by":"crossref","first-page":"m2632","DOI":"10.1136\/bmj.m2632","article-title":"Preferred reporting items for systematic review and meta-analysis of diagnostic test accuracy studies (PRISMA-DTA): explanation, elaboration, and checklist","volume":"370","author":"Salameh","year":"2020","journal-title":"BMJ"},{"key":"R15-20260902","doi-asserted-by":"crossref","first-page":"1930","DOI":"10.1167\/iovs.10-6997b","article-title":"The international workshop on meibomian gland dysfunction: report of the definition and classification subcommittee","volume":"52","author":"Nelson","year":"2011","journal-title":"Invest Ophthalmol Vis Sci."},{"key":"R16-20260902","doi-asserted-by":"crossref","first-page":"e074819","DOI":"10.1136\/bmj-2023-074819","article-title":"Evaluation of clinical prediction models (part 1): from development to external validation","volume":"384","author":"Collins","year":"2024","journal-title":"BMJ"},{"key":"R17-20260902","doi-asserted-by":"crossref","first-page":"106742","DOI":"10.1016\/j.cmpb.2022.106742","article-title":"Health classification of Meibomian gland images using keratography 5M based on AlexNet model","volume":"219","author":"Luo","year":"2022","journal-title":"Comput Methods Programs Biomed."},{"key":"R18-20260902","doi-asserted-by":"crossref","first-page":"3275","DOI":"10.1007\/s10792-022-02262-0","article-title":"Automatic identification of meibomian gland dysfunction with meibography images using deep learning","volume":"42","author":"Yu","year":"2022","journal-title":"Int Ophthalmol."},{"key":"R19-20260902","doi-asserted-by":"crossref","first-page":"142","DOI":"10.1016\/j.jclinepi.2019.12.021","article-title":"GRADE guidelines: 21 part 2. Test accuracy: inconsistency, imprecision, publication bias, and other domains for rating the certainty of evidence and presenting it in evidence profiles and summary of findings tables","volume":"122","author":"Sch\u00fcnemann","year":"2020","journal-title":"J Clin Epidemiol."},{"key":"R20-20260902","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1016\/j.jclinepi.2019.12.020","article-title":"GRADE guidelines: 21 part 1. Study design, risk of bias, and indirectness in rating the certainty across a body of evidence for test accuracy","volume":"122","author":"Sch\u00fcnemann","year":"2020","journal-title":"J Clin Epidemiol."},{"key":"R23-20260902","first-page":"27","article-title":"In vivo confocal microscopy for automated detection of meibomian gland dysfunction: a study based on deep convolutional neural networks","volume":"27","author":"Ge","year":"2025","journal-title":"J Imaging Inform Med."},{"key":"R24-20260902","doi-asserted-by":"crossref","first-page":"216","DOI":"10.1007\/s10792-025-03587-2","article-title":"Performance of a novel multimodal large language model in interpreting meibomian glands quantitatively and qualitatively","volume":"45","author":"Kiyat","year":"2025","journal-title":"Int Ophthalmol."},{"key":"R25-20260902","doi-asserted-by":"crossref","first-page":"086008","DOI":"10.1117\/1.JBO.17.8.086008","article-title":"Detection of meibomian glands and classification of meibography images","volume":"17","author":"Koh","year":"2012","journal-title":"J Biomed Opt."},{"key":"R26-20260902","doi-asserted-by":"crossref","first-page":"e000436","DOI":"10.1136\/bmjophth-2020-000436","article-title":"Image based analysis of meibomian gland dysfunction using conditional generative adversarial neural network","volume":"6","author":"Khan","year":"2021","journal-title":"BMJ Open Ophthalmol."},{"key":"R27-20260902","doi-asserted-by":"crossref","first-page":"403","DOI":"10.1038\/s41746-025-01753-5","article-title":"Development and multicenter validation of an AI driven model for quantitative meibomian gland evaluation","volume":"8","author":"Li","year":"2025","journal-title":"NPJ Digit Med."},{"key":"R28-20260902","doi-asserted-by":"crossref","first-page":"720","DOI":"10.1097\/ICO.0000000000002279","article-title":"Deep neural network-based method for detecting obstructive Meibomian gland dysfunction with in vivo laser confocal microscopy","volume":"39","author":"Maruoka","year":"2020","journal-title":"Cornea"},{"key":"R29-20260902","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1016\/j.jtos.2022.06.006","article-title":"Automated quantification of meibomian gland dropout in infrared meibography using deep learning","volume":"26","author":"Saha","year":"2022","journal-title":"Ocul Surf."},{"key":"R30-20260902","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1097\/OPX.0000000000002208","article-title":"Internal validation of a convolutional neural network pipeline for assessing meibomian gland structure from meibography","volume":"102","author":"Scales","year":"2025","journal-title":"Optom Vis Sci."},{"key":"R31-20260902","doi-asserted-by":"crossref","first-page":"1094","DOI":"10.1097\/OPX.0000000000001767","article-title":"Quantifying meibomian gland morphology using artificial intelligence","volume":"98","author":"Wang","year":"2021","journal-title":"Optom Vis Sci."},{"key":"R32-20260902","doi-asserted-by":"crossref","first-page":"1377","DOI":"10.1038\/s41433-022-02088-1","article-title":"A deep learning model established for evaluating lid margin signs with colour anterior segment photography","volume":"37","author":"Wang","year":"2023","journal-title":"Eye"},{"key":"R33-20260902","doi-asserted-by":"crossref","first-page":"110679","DOI":"10.1016\/j.compbiomed.2025.110679","article-title":"Evaluation of meibomian gland dysfunction with deep learning model considering different datasets and gland morphology","volume":"195","author":"Yesilirmak","year":"2025","journal-title":"Comput Biol Med."},{"key":"R34-20260902","doi-asserted-by":"crossref","first-page":"774344","DOI":"10.3389\/fmed.2021.774344","article-title":"Artificial intelligence to detect meibomian gland dysfunction from in-vivo laser confocal microscopy","volume":"8","author":"Zhang","year":"2021","journal-title":"Front Med."},{"key":"R35-20260902","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1167\/tvst.8.6.37","article-title":"A deep learning approach for meibomian gland atrophy evaluation in meibography images","volume":"8","author":"Wang","year":"2019","journal-title":"Transl Vis Sci Technol."},{"key":"R36-20260902","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1167\/tvst.10.2.4","article-title":"Meibography phenotyping and classification from unsupervised discriminative feature learning","volume":"10","author":"Yeh","year":"2021","journal-title":"Transl Vis Sci Technol."},{"key":"R37-20260902","doi-asserted-by":"crossref","first-page":"15701","DOI":"10.1038\/s41598-022-18933-y","article-title":"Predicting demographics from meibography using deep learning","volume":"12","author":"Wang","year":"2022","journal-title":"Sci Rep."},{"key":"R38-20260902","doi-asserted-by":"crossref","first-page":"e36021","DOI":"10.1016\/j.heliyon.2024.e36021","article-title":"A machine learning approach to predicting dry eye-related signs, symptoms and diagnoses from meibography images","volume":"10","author":"Graham","year":"2024","journal-title":"Heliyon"},{"key":"R39-20260902","first-page":"774","article-title":"An advanced imaging method for measuring and assessing meibomian glands based on deep learning","volume":"56","author":"Zhou","year":"2020","journal-title":"Zhonghua Yan Ke Za Zhi."},{"key":"R40-20260902","doi-asserted-by":"crossref","first-page":"1107689","DOI":"10.3389\/fcell.2022.1107689","article-title":"Advances in artificial intelligence applications for ocular surface diseases diagnosis","volume":"10","author":"Ji","year":"2022","journal-title":"Front Cell Dev Biol."},{"key":"R41-20260902","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1016\/j.jtos.2021.11.004","article-title":"Artificial intelligence in dry eye disease","volume":"23","author":"Storas","year":"2022","journal-title":"Ocul Surf."},{"key":"R42-20260902","doi-asserted-by":"crossref","first-page":"102284","DOI":"10.1016\/j.clae.2024.102284","article-title":"Artificial intelligence in corneal diseases: a narrative review","volume":"47","author":"Nguyen","year":"2024","journal-title":"Cont Lens Anterior Eye."},{"key":"R43-20260902","doi-asserted-by":"crossref","first-page":"23083","DOI":"10.1109\/ACCESS.2021.3056234","article-title":"A novel meibomian gland morphology analytic system based on a convolutional neural network","volume":"9","author":"Dai","year":"2021","journal-title":"IEEE Access."},{"key":"R44-20260902","doi-asserted-by":"crossref","first-page":"e5595","DOI":"10.1136\/bmj.e5595","article-title":"Prognosis research strategy (PROGRESS) 1: a framework for researching clinical outcomes","volume":"346","author":"Hemingway","year":"2013","journal-title":"BMJ"},{"key":"R45-20260902","doi-asserted-by":"crossref","first-page":"m441","DOI":"10.1136\/bmj.m441","article-title":"Calculating the sample size required for developing a clinical prediction model","volume":"368","author":"Riley","year":"2020","journal-title":"BMJ"},{"key":"R46-20260902","doi-asserted-by":"crossref","first-page":"872720","DOI":"10.3389\/frai.2022.872720","article-title":"A unified framework on generalizability of clinical prediction models","volume":"5","author":"Wan","year":"2022","journal-title":"Front Artif Intell."}],"container-title":["Cornea"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.ovid.com\/10.1097\/ICO.0000000000004151","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T23:00:35Z","timestamp":1788390035000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ovid.com\/10.1097\/ICO.0000000000004151"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,18]]},"references-count":43,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2026]]}},"URL":"https:\/\/doi.org\/10.1097\/ico.0000000000004151","relation":{},"ISSN":["0277-3740","1536-4798"],"issn-type":[{"value":"0277-3740","type":"print"},{"value":"1536-4798","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,18]]},"assertion":[{"value":"2025-09-10","name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-07","name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}}]}}