{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"omics_type":["Unknown"],"volume":["6(7)"],"submitter":["Li T"],"pubmed_abstract":["Systemic lupus erythematosus (SLE) is a serious autoimmune disorder predominantly affecting women. However, screening for SLE and related complications poses significant challenges globally, due to complex diagnostic criteria and public unawareness. Since SLE-related retinal involvement could provide insights into disease activity and severity, we develop a deep learning system (DeepSLE) to detect SLE and its retinal and kidney complications from retinal images. In multi-ethnic validation datasets comprising 247,718 images from China and UK, DeepSLE achieves areas under the receiver operating characteristic curve of 0.822-0.969 for SLE. Additionally, DeepSLE demonstrates robust performance across subgroups stratified by gender, age, ethnicity, and socioeconomic status. To ensure DeepSLE's "],"journal":["Cell reports. Medicine"],"pagination":["102203"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC12281353"],"repository":["biostudies-literature"],"pubmed_title":["A deep learning system for detecting systemic lupus erythematosus from retinal images."],"pmcid":["PMC12281353"],"pubmed_authors":["Shen J","Lin S","Yu S","Lu Y","Shu J","Wu C","Qin Y","Liu R","Sheng B","Zhang S","Wagner SK","Zheng YF","Sabanayagam C","Chen X","Wang Z","Wu Y","Chen T","Li H","Li J","Keane PA","Tham YC","Zhou Y","Wang YJ","Wong TY","Guan Z","Li T","Dai R","Fang P","Zeng D"],"additional_accession":[]},"is_claimable":false,"name":"A deep learning system for detecting systemic lupus erythematosus from retinal images.","description":"Systemic lupus erythematosus (SLE) is a serious autoimmune disorder predominantly affecting women. However, screening for SLE and related complications poses significant challenges globally, due to complex diagnostic criteria and public unawareness. Since SLE-related retinal involvement could provide insights into disease activity and severity, we develop a deep learning system (DeepSLE) to detect SLE and its retinal and kidney complications from retinal images. In multi-ethnic validation datasets comprising 247,718 images from China and UK, DeepSLE achieves areas under the receiver operating characteristic curve of 0.822-0.969 for SLE. Additionally, DeepSLE demonstrates robust performance across subgroups stratified by gender, age, ethnicity, and socioeconomic status. To ensure DeepSLE's ","dates":{"release":"2025-01-01T00:00:00Z","publication":"2025 Jul","modification":"2026-03-27T15:14:38.64Z","creation":"2025-08-23T03:09:02.118Z"},"accession":"S-EPMC12281353","cross_references":{"pubmed":["40570853"],"doi":["10.1016/j.xcrm.2025.102203"]}}