{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,19]],"date-time":"2026-10-19T20:26:34Z","timestamp":1792441594459,"version":"4.5.0"},"reference-count":33,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,11,24]],"date-time":"2023-11-24T00:00:00Z","timestamp":1700784000000},"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. Public Health"],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Infectious keratitis (IK) is a sight-threatening condition requiring immediate definite treatment. The need for prompt treatment heavily depends on timely diagnosis. The diagnosis of IK, however, is challenged by the drawbacks of the current \u201cgold standard.\u201d The poorly differentiated clinical features, the possibility of low microbial culture yield, and the duration for culture are the culprits of delayed IK treatment. Deep learning (DL) is a recent artificial intelligence (AI) advancement that has been demonstrated to be highly promising in making automated diagnosis in IK with high accuracy. However, its exact accuracy is not yet elucidated. This article is the first systematic review and meta-analysis that aims to assess the accuracy of available DL models to correctly classify IK based on etiology compared to the current gold standards.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A systematic search was carried out in PubMed, Google Scholars, Proquest, ScienceDirect, Cochrane and Scopus. The used keywords are: \u201cKeratitis,\u201d \u201cCorneal ulcer,\u201d \u201cCorneal diseases,\u201d \u201cCorneal lesions,\u201d \u201cArtificial intelligence,\u201d \u201cDeep learning,\u201d and \u201cMachine learning.\u201d Studies including slit lamp photography of the cornea and validity study on DL performance were considered. The primary outcomes reviewed were the accuracy and classification capability of the AI machine learning\/DL algorithm. We analyzed the extracted data with the MetaXL 5.2 Software.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>A total of eleven articles from 2002 to 2022 were included with a total dataset of 34,070 images. All studies used convolutional neural networks (CNNs), with ResNet and DenseNet models being the most used models across studies. Most AI models outperform the human counterparts with a pooled area under the curve (AUC) of 0.851 and accuracy of 96.6% in differentiating IK vs. non-IK and pooled AUC 0.895 and accuracy of 64.38% for classifying bacterial keratitis (BK) vs. fungal keratitis (FK).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This study demonstrated that DL algorithms have high potential in diagnosing and classifying IK with accuracy that, if not better, is comparable to trained corneal experts. However, various factors, such as the unique architecture of DL model, the problem with overfitting, image quality of the datasets, and the complex nature of IK itself, still hamper the universal applicability of DL in daily clinical practice.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fpubh.2023.1239231","type":"journal-article","created":{"date-parts":[[2023,11,24]],"date-time":"2023-11-24T03:08:26Z","timestamp":1700795306000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":26,"title":["Accuracy of artificial intelligence model for infectious keratitis classification: a systematic review and meta-analysis"],"prefix":"10.3389","volume":"11","author":[{"given":"Randy","family":"Sarayar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yeni Dwi","family":"Lestari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arnaud A. A.","family":"Setio","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ratna","family":"Sitompul","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2023,11,24]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"1084","DOI":"10.1038\/s41433-020-01339-3","article-title":"Infectious keratitis: an update on epidemiology, causative microorganisms, risk factors, and antimicrobial resistance","volume":"35","author":"Ting","year":"2021","journal-title":"Eye"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"e1221","DOI":"10.1016\/S2214-109X(17)30393-5","article-title":"Global causes of blindness and distance vision impairment 1990\u20132020: a systematic review and meta-analysis","volume":"5","author":"Flaxman","year":"2017","journal-title":"Lancet Glob Health"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1136\/bjophthalmol-2020-316128","article-title":"12-year analysis of incidence, microbiological profiles and in vitro antimicrobial susceptibility of infectious keratitis: the Nottingham infectious keratitis study","volume":"105","author":"Ting","year":"2021","journal-title":"Br J Ophthalmol"},{"key":"ref4","first-page":"1027","article-title":"Centers for Disease Control and Prevention (CDC). Estimated burden of keratitis--United States, 2010","volume":"63","author":"Collier","year":"2014","journal-title":"MMWR Morb Mortal Wkly Rep"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"273","DOI":"10.4103\/0301-4738.53051","article-title":"Review of epidemiological features, microbiological diagnosis and treatment outcome of microbial keratitis: experience of over a decade","volume":"57","author":"Gopinathan","year":"2009","journal-title":"Indian J Ophthalmol"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"715118","DOI":"10.3389\/fmed.2021.715118","article-title":"Risk factors, clinical outcomes, and prognostic factors of bacterial keratitis: the Nottingham infectious keratitis study","volume":"8","author":"Ting","year":"2021","journal-title":"Front Med (Lausanne)"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"1787","DOI":"10.1167\/iovs.11-8478","article-title":"The clinical differentiation of bacterial and fungal keratitis: a photographic survey","volume":"53","author":"Dalmon","year":"2012","journal-title":"Invest Ophthalmol Vis Sci"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"1002","DOI":"10.1016\/j.eng.2020.04.012","article-title":"Deep sequential feature learning in clinical image classification of infectious keratitis","volume":"7","author":"Xu","year":"2021","journal-title":"Engineering"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"1342","DOI":"10.1038\/s41591-018-0107-6","article-title":"Clinically applicable deep learning for diagnosis and referral in retinal disease","volume":"24","author":"De Fauw","year":"2018","journal-title":"Nat Med"},{"key":"ref10","doi-asserted-by":"publisher","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":"Ting","year":"2017","journal-title":"JAMA"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"1029","DOI":"10.1097\/IJG.0000000000001319","article-title":"Evaluation of a deep learning system for identifying glaucomatous optic neuropathy based on color fundus photographs","volume":"28","author":"Al-Aswad","year":"2019","journal-title":"J Glaucoma"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"962","DOI":"10.1016\/j.ophtha.2017.02.008","article-title":"Automated identification of diabetic retinopathy using deep learning","volume":"124","author":"Gargeya","year":"2017","journal-title":"Ophthalmology"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1177\/1932296816629491","article-title":"Retinal imaging techniques for diabetic retinopathy screening","volume":"10","author":"Goh","year":"2016","journal-title":"J Diabetes Sci Technol"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"635","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":"ref15","doi-asserted-by":"publisher","first-page":"3738","DOI":"10.1038\/s41467-021-24116-6","article-title":"Preventing corneal blindness caused by keratitis using artificial intelligence","volume":"12","author":"Li","year":"2021","journal-title":"Nat Commun"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"22642","DOI":"10.1038\/s41598-021-02138-w","article-title":"Determination of probability of causative pathogen in infectious keratitis using deep learning algorithm of slit-lamp images","volume":"11","author":"Koyama","year":"2021","journal-title":"Sci Rep"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1016\/j.ophtha.2021.07.033","article-title":"Differentiation of active corneal infections from healed scars using deep learning","volume":"129","author":"Tiwari","year":"2022","journal-title":"Ophthalmology"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"1246","DOI":"10.3390\/diagnostics11071246","article-title":"Using slit-lamp images for deep learning-based identification of bacterial and fungal keratitis: model development and validation with different convolutional neural networks","volume":"11","author":"Hung","year":"2021","journal-title":"Diagnostics"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"767","DOI":"10.1038\/s41551-020-0577-y","article-title":"Dense anatomical annotation of slit-lamp images improves the performance of deep learning for the diagnosis of ophthalmic disorders","volume":"4","author":"Li","year":"2020","journal-title":"Nat Biomed Eng"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1076\/ceyr.27.2.111.15949","article-title":"Neural network approach to classify infective keratitis","volume":"27","author":"Saini","year":"2003","journal-title":"Curr Eye Res"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"100119","DOI":"10.1016\/j.xops.2022.100119","article-title":"Image-based differentiation of bacterial and fungal keratitis using deep convolutional neural networks","volume":"2","author":"Redd","year":"2022","journal-title":"Ophthalmol Sci"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"204062232211360","DOI":"10.1177\/20406223221136071","article-title":"Deep learning-based classification of infectious keratitis on slit-lamp images","volume":"13","author":"Zhang","year":"2022","journal-title":"Ther Adv Chronic Dis"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"616","DOI":"10.1097\/ICO.0000000000002830","article-title":"Deep learning for discrimination between fungal keratitis and bacterial keratitis: DeepKeratitis","volume":"41","author":"Ghosh","year":"2022","journal-title":"Cornea"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.1145\/3437378.3437388","article-title":"Classifying infective keratitis using a deep learning approach","author":"Sajeev","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"17851","DOI":"10.1038\/s41598-020-75027-3","article-title":"Deep learning for identifying corneal diseases from ocular surface slit-lamp photographs","volume":"10","author":"Gu","year":"2020","journal-title":"Sci Rep"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"14424","DOI":"10.1038\/s41598-020-71425-9","article-title":"A deep learning approach in diagnosing fungal keratitis based on corneal photographs","volume":"10","author":"Kuo","year":"2020","journal-title":"Sci Rep"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1080\/08820538.2021.1893763","article-title":"Application of artificial intelligence in the diagnosis and Management of Corneal Diseases","volume":"36","author":"Tahvildari","year":"2021","journal-title":"Semin Ophthalmol"},{"key":"ref28","first-page":"1","volume-title":"Ensemble methods in machine learning","author":"Dietterich","year":"2000"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"260","DOI":"10.1186\/s12913-022-07655-6","article-title":"Cost-effectiveness of artificial intelligence screening for diabetic retinopathy in rural China","volume":"22","author":"Huang","year":"2022","journal-title":"BMC Health Serv Res"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1097\/APO.0000000000000403","article-title":"Economic evaluations of artificial intelligence in ophthalmology","volume":"10","author":"Ruamviboonsuk","year":"2021","journal-title":"Asia Pac J Ophthalmol"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","article-title":"Grad-CAM: visual explanations from deep networks via gradient-based localization","volume":"128","author":"Selvaraju","year":"2019","journal-title":"Int J Comput Vis"},{"key":"ref32","doi-asserted-by":"crossref","DOI":"10.1109\/WACV.2018.00097","article-title":"Grad-CAM++: generalized gradient-based visual explanations for deep convolutional networks","author":"Chattopadhay","year":"2018"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1016\/j.ajo.2014.09.021","article-title":"The corneal ulcer one-touch study: a simplified microbiological specimen collection method","volume":"159","author":"Pakzad-Vaezi","year":"2015","journal-title":"Am J Ophthalmol"}],"container-title":["Frontiers in Public Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2023.1239231\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,24]],"date-time":"2023-11-24T03:08:30Z","timestamp":1700795310000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2023.1239231\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,24]]},"references-count":33,"alternative-id":["10.3389\/fpubh.2023.1239231"],"URL":"https:\/\/doi.org\/10.3389\/fpubh.2023.1239231","relation":{},"ISSN":["2296-2565"],"issn-type":[{"value":"2296-2565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,24]]},"article-number":"1239231"}}