<HashMap><database>biostudies-literature</database><scores/><additional><omics_type>Unknown</omics_type><volume>6(7)</volume><submitter>Li T</submitter><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 </pubmed_abstract><journal>Cell reports. Medicine</journal><pagination>102203</pagination><full_dataset_link>https://www.ebi.ac.uk/biostudies/studies/S-EPMC12281353</full_dataset_link><repository>biostudies-literature</repository><pubmed_title>A deep learning system for detecting systemic lupus erythematosus from retinal images.</pubmed_title><pmcid>PMC12281353</pmcid><pubmed_authors>Shen J</pubmed_authors><pubmed_authors>Lin S</pubmed_authors><pubmed_authors>Yu S</pubmed_authors><pubmed_authors>Lu Y</pubmed_authors><pubmed_authors>Shu J</pubmed_authors><pubmed_authors>Wu C</pubmed_authors><pubmed_authors>Qin Y</pubmed_authors><pubmed_authors>Liu R</pubmed_authors><pubmed_authors>Sheng B</pubmed_authors><pubmed_authors>Zhang S</pubmed_authors><pubmed_authors>Wagner SK</pubmed_authors><pubmed_authors>Zheng YF</pubmed_authors><pubmed_authors>Sabanayagam C</pubmed_authors><pubmed_authors>Chen X</pubmed_authors><pubmed_authors>Wang Z</pubmed_authors><pubmed_authors>Wu Y</pubmed_authors><pubmed_authors>Chen T</pubmed_authors><pubmed_authors>Li H</pubmed_authors><pubmed_authors>Li J</pubmed_authors><pubmed_authors>Keane PA</pubmed_authors><pubmed_authors>Tham YC</pubmed_authors><pubmed_authors>Zhou Y</pubmed_authors><pubmed_authors>Wang YJ</pubmed_authors><pubmed_authors>Wong TY</pubmed_authors><pubmed_authors>Guan Z</pubmed_authors><pubmed_authors>Li T</pubmed_authors><pubmed_authors>Dai R</pubmed_authors><pubmed_authors>Fang P</pubmed_authors><pubmed_authors>Zeng D</pubmed_authors></additional><is_claimable>false</is_claimable><name>A deep learning system for detecting systemic lupus erythematosus from retinal images.</name><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 </description><dates><release>2025-01-01T00:00:00Z</release><publication>2025 Jul</publication><modification>2026-03-27T15:14:38.64Z</modification><creation>2025-08-23T03:09:02.118Z</creation></dates><accession>S-EPMC12281353</accession><cross_references><pubmed>40570853</pubmed><doi>10.1016/j.xcrm.2025.102203</doi></cross_references></HashMap>