biostudies-literatureWu QNational Natural Science Foundation of China (National Science Foundation of China)6962https://www.ebi.ac.uk/biostudies/studies/S-EPMC12307705biostudies-literatureUnknown16(1)Chronic kidney disease (CKD) is a global health challenge, but invasive renal biopsies, the gold standard for diagnosis and prognosis, are often clinically constrained. To address this, we developed the kidney intelligent diagnosis system (KIDS), a noninvasive model for renal biopsy prediction using 13,144 retinal images from 6773 participants. The KIDS achieves an area under the receiver operating characteristic curve (AUC) of 0.839-0.993 for CKD screening and accurately identifies the five most common pathological types (AUC: 0.790-0.932) in a multicenter and multi-ethnic validation, outperforming nephrologists by 26.98% in accuracy. Additionally, the KIDS further predicts disease progression based on pathological classification. Given its flexible strategy, the KIDS can be adapted to loNature communicationsA noninvasive model for chronic kidney disease screening and common pathological type identification from retinal images.PMC12307705823711118237070792368205Fu RMa RJiang LWan PNur AHFeng JJWu QHuang NLiu QYu JDai ZWang JIao WCLiu XKe YZhao LWen JGuo JTing DSWChen WSabanayagam CWang YXie CLi JLing JOCHong HZhou SXiao YChen GRashid Hassan MHCheng KKLi RZhang WZhu MYe QLin DLin HYin PLiu DYang SYe HKong YfalseA noninvasive model for chronic kidney disease screening and common pathological type identification from retinal images.Chronic kidney disease (CKD) is a global health challenge, but invasive renal biopsies, the gold standard for diagnosis and prognosis, are often clinically constrained. To address this, we developed the kidney intelligent diagnosis system (KIDS), a noninvasive model for renal biopsy prediction using 13,144 retinal images from 6773 participants. The KIDS achieves an area under the receiver operating characteristic curve (AUC) of 0.839-0.993 for CKD screening and accurately identifies the five most common pathological types (AUC: 0.790-0.932) in a multicenter and multi-ethnic validation, outperforming nephrologists by 26.98% in accuracy. Additionally, the KIDS further predicts disease progression based on pathological classification. Given its flexible strategy, the KIDS can be adapted to lo2025-01-01T00:00:00Z2025 Jul2026-07-15T09:48:43.906Z2025-08-17T03:06:07.628ZS-EPMC123077054073055610.1038/s41467-025-62273-0