{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T08:43:17Z","timestamp":1769848997457,"version":"3.49.0"},"reference-count":37,"publisher":"Wiley","issue":"4","license":[{"start":{"date-parts":[[2018,11,15]],"date-time":"2018-11-15T00:00:00Z","timestamp":1542240000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Clinical Exper Ophthalmology"],"published-print":{"date-parts":[[2019,5]]},"abstract":"<jats:sec><jats:title>Importance<\/jats:title><jats:p>Artificial intelligence (AI) algorithms are under development for use in diabetic retinopathy photo screening pathways. To be clinically acceptable, such systems must also be able to classify other fundus abnormalities and clinical features at the point of care.<\/jats:p><\/jats:sec><jats:sec><jats:title>Background<\/jats:title><jats:p>We aimed to develop an AI system that can detect several fundus pathologies and report relevant clinical features.<\/jats:p><\/jats:sec><jats:sec><jats:title>Design<\/jats:title><jats:p>Convolutional neural network training with retrospective data set.<\/jats:p><\/jats:sec><jats:sec><jats:title>Participants<\/jats:title><jats:p>Colour fundus photos were obtained from publicly available fundus image databases.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>Images were uploaded to a web\u2010based AI platform for training and validation of AI classifiers. Separate classifiers were created for each fundus pathology and clinical feature.<\/jats:p><\/jats:sec><jats:sec><jats:title>Main Outcome Measures<\/jats:title><jats:p>Accuracy, sensitivity, specificity and area under receiver operating characteristic curve (AUC) for each classifier.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>We obtained 4435 images from publicly available fundus image databases. AI classifiers were developed for each disease state above. Although statistical performance was limited by the small sample size, average accuracy was 89%, average sensitivity was 75%, average specificity was 89% and average AUC was 0.58.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion and Relevance<\/jats:title><jats:p>This study is a proof\u2010of\u2010concept AI system that could be implemented within a diabetic photo\u2010screening pathway. Performance was promising but not yet at the level that would be required for clinical application. We have shown that it is possible for clinicians to develop AI classifiers with no previous programming or AI knowledge, using standard laptop computers.<\/jats:p><\/jats:sec>","DOI":"10.1111\/ceo.13433","type":"journal-article","created":{"date-parts":[[2018,10,29]],"date-time":"2018-10-29T07:03:48Z","timestamp":1540796628000},"page":"484-489","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":32,"title":["Development of an artificial intelligence system to classify pathology and clinical features on retinal fundus images"],"prefix":"10.1111","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5541-5460","authenticated-orcid":false,"given":"Clark H.","family":"Stevenson","sequence":"first","affiliation":[{"name":"Dunedin Hospital Eye Department  Dunedin New Zealand"},{"name":"University of Otago  Dunedin New Zealand"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8954-1433","authenticated-orcid":false,"given":"Sheng Chiong","family":"Hong","sequence":"additional","affiliation":[{"name":"Dunedin Hospital Eye Department  Dunedin New Zealand"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kelechi C.","family":"Ogbuehi","sequence":"additional","affiliation":[{"name":"University of Otago  Dunedin New Zealand"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2018,11,15]]},"reference":[{"key":"e_1_2_7_2_1","volume-title":"Grading, Monitoring and Referral Guidance","author":"Ministry of Health","year":"2016"},{"key":"e_1_2_7_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/S2213-8587(13)70112-8"},{"key":"e_1_2_7_4_1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2016.17216"},{"key":"e_1_2_7_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2017.08.050"},{"key":"e_1_2_7_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2017.02.008"},{"key":"e_1_2_7_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2017.10.017"},{"key":"e_1_2_7_8_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-017-17876-z"},{"key":"e_1_2_7_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2017.04.012"},{"key":"e_1_2_7_10_1","article-title":"Diabetic retinopathy screening using deep neural network","author":"Ramachandran N","year":"2017","journal-title":"Clin Experiment Ophthalmol"},{"key":"e_1_2_7_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2015.08.008"},{"key":"e_1_2_7_12_1","doi-asserted-by":"crossref","unstructured":"KarSS MaitySP.Automatic detection of retinal lesions for screening of diabetic retinopathy.2018;65:608\u2010618.","DOI":"10.1109\/TBME.2017.2707578"},{"key":"e_1_2_7_13_1","first-page":"2841","article-title":"Detection of hemorrhages in retinal images using hybrid approach for diagnosis of diabetic retinopathy","volume":"118","author":"Karkuzhali S","year":"2018","journal-title":"Int J Pure Appl Math"},{"key":"e_1_2_7_14_1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2017.18152"},{"key":"e_1_2_7_15_1","unstructured":"Szegedy C. Vanhoucke V. Shlens J.&Wojna Z.Rethinking the inception architecture for computer vision arXiv (2014)."},{"key":"e_1_2_7_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2013.01.004"},{"key":"e_1_2_7_17_1","unstructured":"Kauppi T. Kalesnykiene V. Kamarainen J. Lensu L.&SorriI. DIARETDB0: evaluation database and methodology for diabetic retinopathy algorithms 2006."},{"key":"e_1_2_7_18_1","doi-asserted-by":"crossref","unstructured":"Kauppi T.et al. The DIARETDB1 diabetic retinopathy database. Paper presented at: Proceedings of British Machine Vision Conference;2007.","DOI":"10.5244\/C.21.15"},{"key":"e_1_2_7_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2008.04.005"},{"key":"e_1_2_7_20_1","first-page":"53","article-title":"Drishti\u2010GS: retinal image dataset for optic nerve head (ONH) segmentation","volume":"29","author":"Sivaswamy J","year":"2014","journal-title":"IEEE 11th Int Symp"},{"key":"e_1_2_7_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2004.825627"},{"key":"e_1_2_7_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.irbm.2013.01.010"},{"key":"e_1_2_7_23_1","first-page":"16","article-title":"FIRE: Fundus Image Registration dataset","volume":"4","author":"Hernandez\u2010Matas C","year":"2017","journal-title":"J Model Ophthalmol"},{"key":"e_1_2_7_24_1","doi-asserted-by":"publisher","DOI":"10.1155\/2013\/154860"},{"key":"e_1_2_7_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2011.2159619"},{"key":"e_1_2_7_26_1","article-title":"Comparison of macular OCTs in right and left eyes of normal people in medical imaging","author":"Mahmudi T","year":"2014","journal-title":"Biomed Appl Mol Struct Funct Imag"},{"key":"e_1_2_7_27_1","doi-asserted-by":"publisher","DOI":"10.5566\/ias.1155"},{"key":"e_1_2_7_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2003.823261"},{"key":"e_1_2_7_29_1","unstructured":"ZhangZ Yin F Liu J et al. Origa\u2010light: an online retinal fundus image database for glaucoma analysis and research. Paper presented at: Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC \u201810);2010."},{"key":"e_1_2_7_30_1","doi-asserted-by":"crossref","unstructured":"Al\u2010DiriB Hunter A Steel D Habib M Hudaib T Berry S. REVIEW \u2010 a reference data set for retinal vessel profiles. Paper presented at: 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society;2008.","DOI":"10.1109\/IEMBS.2008.4649647"},{"key":"e_1_2_7_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2009.2033909"},{"key":"e_1_2_7_32_1","doi-asserted-by":"publisher","DOI":"10.1167\/iovs.14-15949"},{"key":"e_1_2_7_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/42.845178"},{"key":"e_1_2_7_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-012-0442-4"},{"key":"e_1_2_7_35_1","first-page":"41","article-title":"Glaucoma\u2010deep: detection of glaucoma eye disease on retinal fundus images using deep learning","volume":"8","author":"Abbas Q","year":"2017","journal-title":"Int J Adv Comput Sci Appl"},{"key":"e_1_2_7_36_1","first-page":"669","volume-title":"Lecture Notes in Computer Science","author":"Chen X","year":"2015"},{"key":"e_1_2_7_37_1","doi-asserted-by":"crossref","unstructured":"Burlina P. Freund D. E. Joshi N. Wolfson Y.&Bressler N. M.Detection of age\u2010related macular degeneration via deep learning. Paper presented at: Biomedical Imaging (ISBI) 2016 I.E. 13th International Symposium;2016.","DOI":"10.1109\/ISBI.2016.7493240"},{"key":"e_1_2_7_38_1","unstructured":"PoplinR Varadarajan AV Blumer K et al. Predicting cardiovascular risk factors from retinal fundus photographs using deep learning arXiv Prepr. 2017."}],"container-title":["Clinical &amp; Experimental Ophthalmology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1111%2Fceo.13433","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/ceo.13433","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/ceo.13433","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/ceo.13433","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,10]],"date-time":"2023-09-10T17:51:14Z","timestamp":1694368274000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/ceo.13433"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11,15]]},"references-count":37,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2019,5]]}},"alternative-id":["10.1111\/ceo.13433"],"URL":"https:\/\/doi.org\/10.1111\/ceo.13433","archive":["Portico"],"relation":{},"ISSN":["1442-6404","1442-9071"],"issn-type":[{"value":"1442-6404","type":"print"},{"value":"1442-9071","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,11,15]]},"assertion":[{"value":"2018-07-15","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2018-10-05","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2018-11-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}