{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T12:28:26Z","timestamp":1787315306585,"version":"build-2736575974"},"reference-count":33,"publisher":"BMJ","issue":"7","content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["Br J Ophthalmol"],"accepted":{"date-parts":[[2023,9,3]]},"published-print":{"date-parts":[[2024,7]]},"abstract":"<jats:sec>\n                    <jats:title>Background\/aims<\/jats:title>\n                    <jats:p>To assess the performance of deep-learning (DL) models for prediction of conversion to normal-tension glaucoma (NTG) in normotensive glaucoma suspect (GS) patients.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Datasets of 12\u2009458 GS eyes were reviewed. Two hundred and ten eyes (105 eyes showing NTG conversion and 105 without conversion), followed up for a minimum of 7 years during which intraocular pressure (IOP) was lower than 21\u2009mm Hg, were included. The features of two fundus images (optic disc photography and red-free retinal nerve fibre layer (RNFL) photography) were extracted by convolutional auto encoder. The extracted features as well as 15 clinical features including age, sex, IOP, spherical equivalent, central corneal thickness, axial length, average circumpapillary RNFL thickness, systolic\/diastolic blood pressure and body mass index were used to predict NTG conversion. Prediction was performed using three machine-learning classifiers (ie, XGBoost, Random Forest, Gradient Boosting) with different feature combinations.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>All three algorithms achieved high diagnostic accuracy for NTG conversion prediction. The AUCs ranged from 0.987 (95% CI 0.978 to 1.000; Random Forest trained with both fundus images and clinical features) and 0.994 (95% CI 0.984 to 1.000; XGBoost trained with both fundus images and clinical features). XGBoost showed the best prediction performance for time to NTG conversion (mean squared error, 2.24). The top three important clinical features for time-to-conversion prediction were baseline IOP, diastolic blood pressure and average circumpapillary RNFL thickness.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>DL models, trained with both fundus images and clinical data, showed the potential to predict whether and when normotensive GS patients will show conversion to NTG.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bjo-2022-323167","type":"journal-article","created":{"date-parts":[[2023,11,2]],"date-time":"2023-11-02T20:00:41Z","timestamp":1698955241000},"page":"927-932","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":8,"title":["Deep-learning-based prediction of glaucoma conversion in normotensive glaucoma suspects"],"prefix":"10.1136","volume":"108","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4211-7971","authenticated-orcid":false,"given":"Ahnul","family":"Ha","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sukkyu","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6037-8449","authenticated-orcid":false,"given":"Young Kook","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1690-1239","authenticated-orcid":false,"given":"Jin Wook","family":"Jeoung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hee Chan","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8137-8843","authenticated-orcid":false,"given":"Ki Ho","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2023,11,2]]},"reference":[{"key":"2024062002150797000_108.7.927.1","doi-asserted-by":"crossref","first-page":"P112","DOI":"10.1016\/j.ophtha.2015.10.055","article-title":"Primary open-angle glaucoma suspect preferred practice pattern(\u00ae) guidelines","volume":"123","author":"Prum","year":"2016","journal-title":"Ophthalmology"},{"key":"2024062002150797000_108.7.927.2","doi-asserted-by":"publisher","DOI":"10.1001\/archopht.1977.04450070078004"},{"key":"2024062002150797000_108.7.927.3","doi-asserted-by":"publisher","DOI":"10.1001\/archopht.120.6.714"},{"key":"2024062002150797000_108.7.927.4","doi-asserted-by":"publisher","DOI":"10.1016\/S0161-6420(03)00101-5"},{"key":"2024062002150797000_108.7.927.5","doi-asserted-by":"publisher","DOI":"10.1097\/01.ijg.0000151683.04410.f3"},{"key":"2024062002150797000_108.7.927.6","doi-asserted-by":"publisher","DOI":"10.1001\/archopht.120.6.701"},{"key":"2024062002150797000_108.7.927.7","first-page":"100036","article-title":"Role of ocular blood flow in normal tension glaucoma","volume":"2","author":"Wu","year":"2022","journal-title":"AOPR"},{"key":"2024062002150797000_108.7.927.8","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1167\/tvst.9.2.55","article-title":"Artificial intelligence algorithms to diagnose glaucoma and detect glaucoma progression: translation to clinical practice","volume":"9","author":"Mursch-Edlmayr","year":"2020","journal-title":"Transl Vis Sci Technol"},{"key":"2024062002150797000_108.7.927.9","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1016\/bs.pbr.2020.07.002","article-title":"Artificial intelligence and deep learning in glaucoma: current state and future prospects","volume":"257","author":"Girard","year":"2020","journal-title":"Prog Brain Res"},{"key":"2024062002150797000_108.7.927.10","doi-asserted-by":"crossref","first-page":"365","DOI":"10.1167\/iovs.18-25568","article-title":"An artificial intelligence approach to detect visual field progression in glaucoma based on spatial pattern analysis","volume":"60","author":"Wang","year":"2019","journal-title":"Invest Ophthalmol Vis Sci"},{"key":"2024062002150797000_108.7.927.11","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1007\/s10384-019-00706-2","article-title":"Machine learning classifiers-based prediction of normal-tension glaucoma progression in young myopic patients","volume":"64","author":"Lee","year":"2020","journal-title":"Jpn J Ophthalmol"},{"key":"2024062002150797000_108.7.927.12","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-40055-1"},{"key":"2024062002150797000_108.7.927.13","doi-asserted-by":"publisher","DOI":"10.1167\/iovs.14-14625"},{"key":"2024062002150797000_108.7.927.14","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2005.03.028"},{"key":"2024062002150797000_108.7.927.15","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajo.2007.02.022"},{"key":"2024062002150797000_108.7.927.16","doi-asserted-by":"publisher","DOI":"10.1001\/archopht.124.11.1579"},{"key":"2024062002150797000_108.7.927.17","doi-asserted-by":"publisher","DOI":"10.1001\/archopht.118.8.1105"},{"key":"2024062002150797000_108.7.927.18","doi-asserted-by":"crossref","unstructured":"Chen T , Guestrin C . Xgboost: A Scalable tree boosting system. Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining; 2016","DOI":"10.1145\/2939672.2939785"},{"key":"2024062002150797000_108.7.927.19","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"2024062002150797000_108.7.927.20","doi-asserted-by":"crossref","first-page":"1189","DOI":"10.1214\/aos\/1013203451","article-title":"Greedy function approximation: a gradient boosting machine","volume":"29","author":"Friedman","year":"2001","journal-title":"Ann Statist"},{"key":"2024062002150797000_108.7.927.21","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2010.04.018"},{"key":"2024062002150797000_108.7.927.22","doi-asserted-by":"crossref","unstructured":"Yen S-J , Lee Y-S . Under-sampling approaches for improving prediction of the minority class in an imbalanced Dataset. In: Intelligent Control and Automation. Springer, 2006: 731\u201340. doi:10.1007\/978-3-540-37256-1","DOI":"10.1007\/978-3-540-37256-1_89"},{"key":"2024062002150797000_108.7.927.23","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2020.12.020"},{"key":"2024062002150797000_108.7.927.24","doi-asserted-by":"publisher","DOI":"10.1167\/iovs.03-0077"},{"key":"2024062002150797000_108.7.927.25","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2006.03.063"},{"key":"2024062002150797000_108.7.927.26","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2007.03.047"},{"key":"2024062002150797000_108.7.927.27","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2007.03.017"},{"key":"2024062002150797000_108.7.927.28","doi-asserted-by":"crossref","first-page":"276","DOI":"10.1016\/j.ophtha.2021.10.018","article-title":"The association among blood pressure, blood pressure medications, and glaucoma in a nationwide electronic health records database","volume":"129","author":"Lee","year":"2022","journal-title":"Ophthalmology"},{"key":"2024062002150797000_108.7.927.29","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1016\/j.ophtha.2021.08.021","article-title":"Blood pressure and glaucomatous progression in a large clinical population","volume":"129","author":"Jammal","year":"2022","journal-title":"Ophthalmology"},{"key":"2024062002150797000_108.7.927.30","doi-asserted-by":"crossref","DOI":"10.1155\/2015\/308505","article-title":"Ocular blood flow and normal tension glaucoma","volume":"2015","author":"Fan","year":"2015","journal-title":"Biomed Res Int"},{"key":"2024062002150797000_108.7.927.31","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajo.2006.02.055"},{"key":"2024062002150797000_108.7.927.32","doi-asserted-by":"publisher","DOI":"10.3341\/kjo.2010.24.1.23"},{"key":"2024062002150797000_108.7.927.33","doi-asserted-by":"publisher","DOI":"10.1159\/000335978"}],"container-title":["British Journal of Ophthalmology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bjo-2022-323167","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,20]],"date-time":"2024-06-20T14:26:56Z","timestamp":1718893616000},"score":1,"resource":{"primary":{"URL":"https:\/\/bjo.bmj.com\/lookup\/doi\/10.1136\/bjo-2022-323167"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,2]]},"references-count":33,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2024,6,20]]},"published-print":{"date-parts":[[2024,7]]}},"alternative-id":["10.1136\/bjo-2022-323167"],"URL":"https:\/\/doi.org\/10.1136\/bjo-2022-323167","relation":{},"ISSN":["0007-1161","1468-2079"],"issn-type":[{"value":"0007-1161","type":"print"},{"value":"1468-2079","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,2]]}}}