María C Ibañez-Bruron, Andrea Cruzat, Gonzalo Ordenes-Caviere, Marcelo Coria
{"title":"[人工智能在糖尿病视网膜病变筛查中的应用：智利圣地亚哥卫生服务的经验]。","authors":"María C Ibañez-Bruron, Andrea Cruzat, Gonzalo Ordenes-Caviere, Marcelo Coria","doi":"10.4067/s0034-98872024001101148","DOIUrl":null,"url":null,"abstract":"<p><p>Early detection of diabetic retinopathy is critical for preventing vision loss.</p><p><strong>Aim: </strong>To evaluate the use of artificial intelligence (AI) for screening sight threatening diabetic retinopathy (DR) in a public Hospital in Chile.</p><p><strong>Material and methods: </strong>The mydriatic retinal photographs of 366 participants were uploaded for analysis by EyeArt, a cloud-based AI software developed by Eyenuk (Los Ángeles, USA). Diagnostic accuracy was calculated by comparing its results with the clinical evaluation of the fundus by an ophthalmologist. Participants with severe non-proliferative DR or worse were considered as positive cases.</p><p><strong>Results: </strong>Twenty four percent of participants had DR, including 33 (9%) who had sight threatening DR in at least one eye. The sensitivity and specificity of EyeArt were 100% (95% confidence intervals (CI): 89-100%) and 84% (95% CI: 80-88%), respectively.</p><p><strong>Conclusions: </strong>EyeArt was highly sensitive for sight threatening DR and it may be a cost-effective method to improve DR screening in the Chilean public health system.</p>","PeriodicalId":101370,"journal":{"name":"Revista medica de Chile","volume":"152 11","pages":"1148-1153"},"PeriodicalIF":0.0000,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"[Use of Artificial Intelligence in Diabetic Retinopathy Screening: Experience in a Health Service in Santiago, Chile].\",\"authors\":\"María C Ibañez-Bruron, Andrea Cruzat, Gonzalo Ordenes-Caviere, Marcelo Coria\",\"doi\":\"10.4067/s0034-98872024001101148\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Early detection of diabetic retinopathy is critical for preventing vision loss.</p><p><strong>Aim: </strong>To evaluate the use of artificial intelligence (AI) for screening sight threatening diabetic retinopathy (DR) in a public Hospital in Chile.</p><p><strong>Material and methods: </strong>The mydriatic retinal photographs of 366 participants were uploaded for analysis by EyeArt, a cloud-based AI software developed by Eyenuk (Los Ángeles, USA). Diagnostic accuracy was calculated by comparing its results with the clinical evaluation of the fundus by an ophthalmologist. Participants with severe non-proliferative DR or worse were considered as positive cases.</p><p><strong>Results: </strong>Twenty four percent of participants had DR, including 33 (9%) who had sight threatening DR in at least one eye. The sensitivity and specificity of EyeArt were 100% (95% confidence intervals (CI): 89-100%) and 84% (95% CI: 80-88%), respectively.</p><p><strong>Conclusions: </strong>EyeArt was highly sensitive for sight threatening DR and it may be a cost-effective method to improve DR screening in the Chilean public health system.</p>\",\"PeriodicalId\":101370,\"journal\":{\"name\":\"Revista medica de Chile\",\"volume\":\"152 11\",\"pages\":\"1148-1153\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Revista medica de Chile\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.4067/s0034-98872024001101148\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2025/2/3 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Revista medica de Chile","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.4067/s0034-98872024001101148","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/2/3 0:00:00","PubModel":"Epub","JCR":"","JCRName":"","Score":null,"Total":0}
[Use of Artificial Intelligence in Diabetic Retinopathy Screening: Experience in a Health Service in Santiago, Chile].
Early detection of diabetic retinopathy is critical for preventing vision loss.
Aim: To evaluate the use of artificial intelligence (AI) for screening sight threatening diabetic retinopathy (DR) in a public Hospital in Chile.
Material and methods: The mydriatic retinal photographs of 366 participants were uploaded for analysis by EyeArt, a cloud-based AI software developed by Eyenuk (Los Ángeles, USA). Diagnostic accuracy was calculated by comparing its results with the clinical evaluation of the fundus by an ophthalmologist. Participants with severe non-proliferative DR or worse were considered as positive cases.
Results: Twenty four percent of participants had DR, including 33 (9%) who had sight threatening DR in at least one eye. The sensitivity and specificity of EyeArt were 100% (95% confidence intervals (CI): 89-100%) and 84% (95% CI: 80-88%), respectively.
Conclusions: EyeArt was highly sensitive for sight threatening DR and it may be a cost-effective method to improve DR screening in the Chilean public health system.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
