{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Wu Q"],"funding":["National Natural Science Foundation of China (National Science Foundation of China)"],"pagination":["6962"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC12307705"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["16(1)"],"pubmed_abstract":["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 lo"],"journal":["Nature communications"],"pubmed_title":["A noninvasive model for chronic kidney disease screening and common pathological type identification from retinal images."],"pmcid":["PMC12307705"],"funding_grant_id":["82371111","82370707","92368205"],"pubmed_authors":["Fu R","Ma R","Jiang L","Wan P","Nur AH","Feng JJ","Wu Q","Huang N","Liu Q","Yu J","Dai Z","Wang J","Iao WC","Liu X","Ke Y","Zhao L","Wen J","Guo J","Ting DSW","Chen W","Sabanayagam C","Wang Y","Xie C","Li J","Ling JOC","Hong H","Zhou S","Xiao Y","Chen G","Rashid Hassan MH","Cheng KK","Li R","Zhang W","Zhu M","Ye Q","Lin D","Lin H","Yin P","Liu D","Yang S","Ye H","Kong Y"],"additional_accession":[]},"is_claimable":false,"name":"A noninvasive model for chronic kidney disease screening and common pathological type identification from retinal images.","description":"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 lo","dates":{"release":"2025-01-01T00:00:00Z","publication":"2025 Jul","modification":"2026-07-15T09:48:43.906Z","creation":"2025-08-17T03:06:07.628Z"},"accession":"S-EPMC12307705","cross_references":{"pubmed":["40730556"],"doi":["10.1038/s41467-025-62273-0"]}}