{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T04:56:49Z","timestamp":1781672209287,"version":"3.54.5"},"reference-count":42,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T00:00:00Z","timestamp":1781654400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["NO.82571194"],"award-info":[{"award-number":["NO.82571194"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20251839"],"award-info":[{"award-number":["BK20251839"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Endocrinol."],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study aimed to develop and externally validate an interpretable machine learning (ML) model for diabetic retinopathy (DR) risk stratification using routine clinical biomarkers, and to explore potential probabilistic dependencies and interactive pathways between clinical biomarkers and DR pathogenesis through Bayesian network modeling.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We integrated clinical data from the National Health and Nutrition Examination Survey (NHANES) with an independent hospital cohort (Nantong First People\u2019s Hospital). A multi-stage feature selection pipeline (Boruta algorithm and LASSO regression) was utilized to identify core predictors. Eight ML algorithms were benchmarked. To transcend conventional \u201cblack-box\u201d predictions, we coupled SHAP (SHapley Additive exPlanations) for personalized interpretability with a Bayesian Network Directed Acyclic Graph (DAG) to map the probabilistic dependency structure among the selected systemic biomarkers.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The LightGBM algorithm outperformed other classifiers, yielding a robust external validation AUC of 0.841 (95% CI: 0.809-0.862). Fourteen key routine predictors were identified, spanning glycemic control, renal function, and lipid metabolism. Crucially, probabilistic dependency structure via the Bayesian Network revealed a hierarchical pathogenetic topology: rather than parallel associations, latent renal impairment markers (urine protein, BUN, and urine creatinine) and chronic glycemic toxicity (HbA1c) emerged as direct upstream dependency drivers of DR. This structural evidence suggests a probabilistic dependency consistent with the \u2018kidney-eye crosstalk\u2019 hypothesis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>We successfully deployed a high-performing, non-invasive LightGBM model for early DR screening. By integrating predictive ML with probabilistic dependency structure, this framework not only delivers an accessible, web-based clinical decision support system (CDSS) for resource-constrained settings but also provides preliminary insights into the potential systemic microvascular interplay driving diabetic retinopathy.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fendo.2026.1843412","type":"journal-article","created":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T04:43:47Z","timestamp":1781671427000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A machine learning model for diabetic retinopathy risk stratification using routine blood and urine parameters: insights into kidney-eye crosstalk"],"prefix":"10.3389","volume":"17","author":[{"given":"Yong","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Ophthalmology, Affiliated Nantong Clinical College of Nantong University, Nantong First People\u2019s Hospital","place":["Nantong, Jiangsu, China"]},{"name":"Department of Ophthalmology, Nantong First People\u2019s Hospital","place":["Nantong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ling","family":"Yao","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Affiliated Nantong Clinical College of Nantong University, Nantong First People\u2019s Hospital","place":["Nantong, Jiangsu, China"]},{"name":"Department of Ophthalmology, Nantong First People\u2019s Hospital","place":["Nantong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianpeng","family":"Chen","sequence":"additional","affiliation":[{"name":"Medical Research Center, Nantong First People\u2019s Hospital","place":["Nantong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qianyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Affiliated Nantong Clinical College of Nantong University, Nantong First People\u2019s Hospital","place":["Nantong, Jiangsu, China"]},{"name":"Department of Ophthalmology, Nantong First People\u2019s Hospital","place":["Nantong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Cao","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Nantong First People\u2019s Hospital","place":["Nantong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiayi","family":"Gu","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Nantong First People\u2019s Hospital","place":["Nantong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sijie","family":"Bao","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Nantong First People\u2019s Hospital","place":["Nantong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaojuan","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Nantong First People\u2019s Hospital","place":["Nantong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng","family":"Cao","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Nantong First People\u2019s Hospital","place":["Nantong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,6,17]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2021.04.027","article-title":"Global prevalence of diabetic retinopathy and projection of burden through 2045: Systematic review and meta-analysis","volume":"128","author":"Teo","year":"2021","journal-title":"Ophthalmology"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.2337\/dc11-1909","article-title":"Global prevalence and major risk factors of diabetic retinopathy","volume":"35","author":"Yau","year":"2012","journal-title":"Diabetes Care"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.2337\/db05-1635","article-title":"Diabetic retinopathy: seeing beyond glucose-induced microvascular disease","volume":"55","author":"Antonetti","year":"2006","journal-title":"Diabetes"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1016\/j.gene.2024.149015","article-title":"Machine learning-based identification and validation of immune-related biomarkers for early diagnosis and targeted therapy in diabetic retinopathy","volume":"934","author":"Tao","year":"2025","journal-title":"Gene"},{"key":"B5","doi-asserted-by":"publisher","first-page":"16012","DOI":"10.1038\/nrdp.2016.12","article-title":"Diabetic retinopathy","volume":"2","author":"Wong","year":"2016","journal-title":"Nat Rev Dis Primers"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1016\/s0140-6736(09)62124-3","article-title":"Diabetic retinopathy","volume":"376","author":"Cheung","year":"2010","journal-title":"Lancet"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1038\/s41433-024-03101-5","article-title":"Global estimates on the number of people blind or visually impaired by diabetic retinopathy: a meta-analysis from 2000 to 2020","volume":"38","year":"2024","journal-title":"Eye (London England)"},{"key":"B8","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1186\/s40001-025-02442-5","article-title":"Predicting diabetic retinopathy based on routine laboratory tests by machine learning algorithms","volume":"30","author":"Wan","year":"2025","journal-title":"Eur J Med Res"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.2337\/dc16-2641","article-title":"Diabetic retinopathy: A position statement by the American Diabetes Association","volume":"40","author":"Solomon","year":"2017","journal-title":"Diabetes Care"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2022.946915","article-title":"Artificial intelligence promotes the diagnosis and screening of diabetic retinopathy","volume":"13","author":"Huang","year":"2022","journal-title":"Front Endocrinol (Lausanne)"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1016\/j.jdiacomp.2022.108313","article-title":"Nomogram for prediction of diabetic retinopathy in patients with type 2 diabetes mellitus: A retrospective study","volume":"36","author":"Yang","year":"2022","journal-title":"J Diabetes Its Complications"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.2196\/41065","article-title":"Development and external validation of machine learning models for diabetic microvascular complications: Cross-sectional study with metabolites","volume":"26","author":"He","year":"2024","journal-title":"J Med Internet Res"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2016.17216","article-title":"Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs","volume":"316","author":"Gulshan","year":"2016","journal-title":"Jama"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1177\/20552076241286140","article-title":"Brain tumor classification using fine-tuned transfer learning models on magnetic resonance imaging (MRI) images","volume":"10","author":"Rasa","year":"2024","journal-title":"Digital Health"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1002\/jemt.23281","article-title":"Deep learning model integrating features and novel classifiers fusion for brain tumor segmentation","volume":"82","author":"Iqbal","year":"2019","journal-title":"Microsc Res Tech"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.129372","article-title":"Tri-STANet: An advanced framework integrating dual axis transformer and morphological encoding for enhanced AS detection","volume":"297","author":"Anul Haq","year":"2026","journal-title":"Expert Syst Appl"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1177\/20552076241286140","article-title":"Brain tumor identification using data augmentation and transfer learning approach","volume":"46","author":"Kumar","year":"2023"},{"key":"B18","doi-asserted-by":"publisher","first-page":"4755","DOI":"10.3390\/ijms20194755","article-title":"Proteomic biomarkers of retinal inflammation in diabetic retinopathy","volume":"20","author":"Youngblood","year":"2019","journal-title":"Int J Mol Sci"},{"key":"B19","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1186\/s12014-024-09515-3","article-title":"Comparative proteomic analysis of human vitreous in rhegmatogenous retinal detachment and diabetic retinopathy reveals a common pathway and potential therapeutic target","volume":"21","author":"Brighenti","year":"2024","journal-title":"Clin Proteomics"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jproteome.5c00394","article-title":"Vitreous Olink proteomics uncovers novel inflammatory proteins in patients with proliferative diabetic retinopathy","volume":"24","author":"Zhang","year":"2025","journal-title":"J Proteome Res"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1038\/s41433-024-02938-0","article-title":"Multiplatform tear proteomic profiling reveals novel non-invasive biomarkers for diabetic retinopathy","volume":"38","author":"Fan","year":"2024","journal-title":"Eye (London England)"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2024.1440223","article-title":"Association between rest-activity rhythm and diabetic retinopathy among US middle-age and older diabetic adults","volume":"15","author":"Wang","year":"2024","journal-title":"Front Endocrinol (Lausanne)"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2025.1552772","article-title":"Association between neutrophil-percentage-to-albumin ratio and diabetic kidney disease in type 2 diabetes mellitus patients: a cross-sectional study from NHANES 2009-2018","volume":"16","author":"Li","year":"2025","journal-title":"Front Endocrinol (Lausanne)"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.3389\/fnut.2025.1602361","article-title":"Nutritional-inflammatory status and diabetic retinopathy: exploring the association between advanced lung cancer inflammation index and retinal complications in diabetes","volume":"12","author":"Peng","year":"2025","journal-title":"Front Nutr"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.3945\/an.115.009258","article-title":"Update on NHANES dietary data: Focus on collection, release, analytical considerations, and uses to inform public policy","volume":"7","author":"Ahluwalia","year":"2016","journal-title":"Adv Nutr (Bethesda Md)"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.108919","article-title":"Interpretable machine learning for dermatological disease detection: Bridging the gap between accuracy and explainability","volume":"179","author":"Nasir","year":"2024","journal-title":"Comput Biol Med"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.125461","article-title":"XAI-RACapsNet: Relevance aware capsule network-based breast cancer detection using mammography images via explainability O-net ROI segmentation","volume":"261","author":"Alhussen","year":"2025","journal-title":"Expert Syst Appl"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1016\/j.eclinm.2023.102409","article-title":"Identification and validation of an explainable prediction model of acute kidney injury with prognostic implications in critically ill children: a prospective multicenter cohort study","volume":"68","author":"Hu","year":"2024","journal-title":"EClinicalMedicine"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1016\/j.eclinm.2024.102820","article-title":"Machine-learning-derived online prediction models of outcomes for patients with cholelithiasis-induced acute cholangitis: development and validation in two retrospective cohorts","volume":"76","author":"Huang","year":"2024","journal-title":"EClinicalMedicine"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1136\/bjophthalmol-2018-313173","article-title":"Artificial intelligence and deep learning in ophthalmology","volume":"103","author":"Ting","year":"2019","journal-title":"Br J Ophthalmol"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2025.1591832","article-title":"Deep learning for enhanced prediction of diabetic retinopathy: a comparative study on the diabetes complications data set","volume":"12","author":"Gong","year":"2025","journal-title":"Front Med"},{"key":"B32","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1038\/s41574-020-00451-4","article-title":"Current understanding of the molecular and cellular pathology of diabetic retinopathy","volume":"17","author":"Antonetti","year":"2021","journal-title":"Nat Rev Endocrinol"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1038\/ki.2013.491","article-title":"Kidney and eye diseases: common risk factors, etiological mechanisms, and pathways","volume":"85","author":"Wong","year":"2014","journal-title":"Kidney Int"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1111\/1753-0407.12085","article-title":"Serum total bilirubin levels and prevalence of diabetic retinopathy in a Chinese population","volume":"6","author":"Najam","year":"2014","journal-title":"J Diabetes"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1038\/414813a","article-title":"Biochemistry and molecular cell biology of diabetic complications","volume":"414","author":"Brownlee","year":"2001","journal-title":"Nature"},{"key":"B36","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1186\/s12916-019-1426-2","article-title":"Key challenges for delivering clinical impact with artificial intelligence","volume":"17","author":"Kelly","year":"2019","journal-title":"BMC Med"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1186\/s13040-025-00505-1","article-title":"A fairness-aware machine learning framework for maternal health in Ghana: integrating explainability, bias mitigation, and causal inference for ethical AI deployment","volume":"19","author":"Osborne","year":"2025","journal-title":"Biodata Min"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.k601","article-title":"Reading Mendelian randomisation studies: a guide, glossary, and checklist for clinicians","volume":"362","author":"Davies","year":"2018","journal-title":"BMJ (Clinical Res Ed)"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1811744","article-title":"Canagliflozin and renal outcomes in type 2 diabetes and nephropathy","volume":"380","author":"Perkovic","year":"2019","journal-title":"N Engl J Med"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa2024816","article-title":"Dapagliflozin in patients with chronic kidney disease","volume":"383","author":"Heerspink","year":"2020","journal-title":"N Engl J Med"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.1111\/dom.13172","article-title":"Semaglutide, reduction in glycated haemoglobin and the risk of diabetic retinopathy","volume":"20","author":"Vilsb\u00f8ll","year":"2018","journal-title":"Diabetes Obes Metab"},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.1007\/s11892-015-0602-9","article-title":"\u03b2 cell dysfunction versus insulin resistance in the pathogenesis of type 2 diabetes in East Asians","volume":"15","author":"Yabe","year":"2015","journal-title":"Curr Diabetes Rep"}],"container-title":["Frontiers in Endocrinology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2026.1843412\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T04:43:55Z","timestamp":1781671435000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2026.1843412\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,17]]},"references-count":42,"alternative-id":["10.3389\/fendo.2026.1843412"],"URL":"https:\/\/doi.org\/10.3389\/fendo.2026.1843412","relation":{},"ISSN":["1664-2392"],"issn-type":[{"value":"1664-2392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,17]]},"article-number":"1843412"}}