{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T18:45:34Z","timestamp":1790621134344,"version":"4.1.0"},"reference-count":57,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T00:00:00Z","timestamp":1772582400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Endocrinol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Vision-threatening diabetic retinopathy (VTDR) is a severe complication of type 2 diabetes mellitus (T2DM), particularly prevalent in patients with prolonged disease duration, poor glycemic control, and systemic comorbidities. This condition frequently progresses asymptomatically toward irreversible blindness without timely intervention. The early identification of VTDR is challenging due to the lack of validated biomarkers and a reliance on subjective clinical assessments. This study aimed to develop and validate an interpretable machine learning (ML) model to detect VTDR among patients with diabetic retinopathy (DR).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Retrospective clinical data from T2DM patients with DR were extracted from the electronic medical records at our hospital and categorized into VTDR and non-VTDR (defined as mild-to-moderate non-proliferative diabetic retinopathy) groups. The dataset was partitioned into training and testing sets (7:3 ratio). Eight ML models were trained and evaluated using metrics such as Area Under the Curve (AUC), accuracy, and recall. Model performance was evaluated using a comprehensive scoring system (total score = 64). Shapley Additive Explanations (SHAP) were used to interpret the best-performing model. A web-based application was developed to demonstrate potential clinical utility.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Among 1,124 enrolled patients, the prevalence of VTDR was 36.9%. Key associated factors included diabetic treatment, T2DM duration, glycated hemoglobin levels, albuminuria, and anemia. The Support Vector Machine (SVM) model demonstrated superior performance, with an AUC of 0.879, accuracy of 0.837, precision of 0.833, Brier score of 0.129, and an F1 score of 0.756, outperforming the other ML models. The SVM model achieved the highest total score (57\/64) in the testing cohort. Furthermore, decision curve analysis and calibration curves confirmed the robustness and reliability of the models. A simplified calculator derived from the SHAP feature importance rankings maintained strong diagnostic capacity.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The interpretable SVM model effectively detected VTDR among patients with DR using routine clinical data. While requiring external validation, this study serves as a proof-of-concept for a cost-effective screening tool that could assist clinicians in prioritizing high-risk patients and facilitating early intervention to prevent irreversible vision impairment.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fendo.2026.1776188","type":"journal-article","created":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T11:21:10Z","timestamp":1772623270000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["An interpretable machine learning model for detecting vision-threatening diabetic retinopathy among patients with diabetic retinopathy: a web-based cross-sectional study"],"prefix":"10.3389","volume":"17","author":[{"given":"Mingyang","family":"Song","sequence":"first","affiliation":[{"name":"Department of General Practice, The First Affiliated Hospital of China Medical University","place":["Shenyang, Liaoning, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yimeng","family":"Shi","sequence":"additional","affiliation":[{"name":"Department of Surgery, The First Affiliated Hospital of China Medical University","place":["Shenyang, Liaoning, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,3,4]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1016\/j.apjo.2024.100109","article-title":"Current research and future strategies for the management of vision-threatening diabetic retinopathy","volume":"13","author":"Li","year":"2024","journal-title":"Asia Pac J Ophthalmol (Phila)"},{"key":"B2","doi-asserted-by":"publisher","first-page":"4296","DOI":"10.1038\/s41467-023-39864-w","article-title":"Prevalence of diabetic retinopathy and vision-threatening diabetic retinopathy in adults with diabetes in China","volume":"14","author":"Hou","year":"2023","journal-title":"Nat Commun"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1016\/S0161-6420(03)00475-5","article-title":"Proposed international clinical diabetic retinopathy and diabetic macular edema disease severity scales","volume":"110","author":"Wilkinson","year":"2003","journal-title":"Ophthalmology"},{"key":"B4","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1186\/s40662-015-0026-2","article-title":"Epidemiology of diabetic retinopathy, diabetic macular edema and related vision loss","volume":"2","author":"Lee","year":"2015","journal-title":"Eye Vis (Lond)"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1038\/s41433-021-01572-4","article-title":"Recently updated global diabetic retinopathy screening guidelines: commonalities, differences, and future possibilities","volume":"35","author":"Das","year":"2021","journal-title":"Eye (Lond)"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3310\/hta19740","article-title":"Development of a cost-effectiveness model for optimisation of the screening interval in diabetic retinopathy screening","volume":"19","author":"Scanlon","year":"2015","journal-title":"Health Technol Assess"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1038\/s41433-020-0776-5","article-title":"Do we have enough ophthalmologists to manage vision-threatening diabetic retinopathy? A global perspective","volume":"34","author":"Teo","year":"2020","journal-title":"Eye (Lond)"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1136\/bmjdrc-2016-000333","article-title":"Non-adherence to eye care in people with diabetes","volume":"5","author":"Murchison","year":"2017","journal-title":"BMJ Open Diabetes Res Care"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2021.34254","article-title":"Pivotal evaluation of an artificial intelligence system for autonomous detection of referrable and vision-threatening diabetic retinopathy","volume":"4","author":"Ipp","year":"2021","journal-title":"JAMA Netw Open"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2024.1484197","article-title":"Factors related to type 2 diabetic retinopathy and their clinical application value","volume":"15","author":"Lian","year":"2024","journal-title":"Front Endocrinol (Lausanne)"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2023.105228","article-title":"Comparison of machine learning and conventional logistic regression-based prediction models for gestational diabetes in an ethnically diverse population; the Monash GDM Machine learning model","volume":"179","author":"Belsti","year":"2023","journal-title":"Int J Med Inform"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1093\/aje\/kwz189","article-title":"What is machine learning? A primer for the epidemiologist","volume":"188","author":"Bi","year":"2019","journal-title":"Am J Epidemiol"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1177\/20552076241272657","article-title":"The application of explainable artificial intelligence (XAI) in electronic health record research: A scoping review","volume":"10","author":"Caterson","year":"2024","journal-title":"Digit Health"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2023.102616","article-title":"How does the model make predictions? A systematic literature review on the explainability power of machine learning in healthcare","volume":"143","author":"Allgaier","year":"2023","journal-title":"Artif Intell Med"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-14305-w","article-title":"Machine learning and deep learning approach for medical image analysis: diagnosis to detection","volume":"82","author":"Rana","year":"2023","journal-title":"Multimed Tools Appl"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.4097\/kjae.2013.64.5.402","article-title":"The prevention and handling of the missing data","volume":"64","author":"Kang","year":"2013","journal-title":"Korean J Anesthesiol"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btr597","article-title":"MissForest--non-parametric missing value imputation for mixed-type data","volume":"28","author":"Stekhoven","year":"2012","journal-title":"Bioinformatics"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.32604\/csse.2023.033927","article-title":"Brain tumor identification using data augmentation and transfer learning approach","volume":"46","author":"Kumar","year":"2023","journal-title":"Comput Syst Sci Eng"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.3233\/FI-2010-288","article-title":"Boruta-a system for feature selection","volume":"101","author":"Kursa","year":"2010","journal-title":"Fundamenta informaticae"},{"key":"B20","doi-asserted-by":"publisher","first-page":"1311","DOI":"10.1186\/s12885-025-14664-1","article-title":"Identification of optimal biomarkers associated with distant metastasis in breast cancer using Boruta and Lasso machine learning algorithms","volume":"25","author":"Qin","year":"2025","journal-title":"BMC Cancer"},{"key":"B21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v033.i01","article-title":"Regularization paths for generalized linear models via coordinate descent","volume":"33","author":"Friedman","year":"2010","journal-title":"J Stat Softw"},{"key":"B22","doi-asserted-by":"publisher","first-page":"10434","DOI":"10.1038\/s41598-025-95287-1","article-title":"Development of an early prediction model for vomiting during hemodialysis using LASSO regression and Boruta feature selection","volume":"15","author":"Chen","year":"2025","journal-title":"Sci Rep"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2025.1626529","article-title":"The risk prediction model for acute urine retention after perineal prostate biopsy based on the LASSO approach and Boruta feature selection","volume":"15","author":"Shen","year":"2025","journal-title":"Front Oncol"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1142\/S0218348X23401023","article-title":"DCNNBT: A novel deep convolution neural network-based brain tumor classification model","volume":"31","author":"Haq","year":"2023","journal-title":"Fractals"},{"key":"B25","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":"Haq","year":"2025","journal-title":"Expert Syst Appl"},{"key":"B26","doi-asserted-by":"publisher","first-page":"27699","DOI":"10.1038\/s41598-025-06576-8","article-title":"An artificial intelligence model to predict mortality among hemodialysis patients: A retrospective validated cohort study","volume":"15","author":"Peng","year":"2025","journal-title":"Sci Rep"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1016\/j.gloepi.2025.100242","article-title":"On misconceptions about the Brier score in binary prediction models","volume":"11","author":"Hoessly","year":"2026","journal-title":"Glob Epidemiol"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare11162244","article-title":"Optimizing clinical decision making with decision curve analysis: insights for clinical investigators","volume":"11","author":"Piovani","year":"2023","journal-title":"Healthcare (Basel)"},{"key":"B29","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":"B30","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2022.1099302","article-title":"Predictive model for diabetic retinopathy under limited medical resources: A multicenter diagnostic study","volume":"13","author":"Yang","year":"2023","journal-title":"Front Endocrinol (Lausanne)"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1016\/S2213-8587(19)30411-5","article-title":"Screening for diabetic retinopathy: new perspectives and challenges","volume":"8","author":"Vujosevic","year":"2020","journal-title":"Lancet Diabetes Endocrinol"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.3760\/cma.j.cn112137-20200825-02468","article-title":"Vision 2020: the progress of blindness prevention and eye health in China","volume":"100","author":"Mayinuer","year":"2020","journal-title":"Zhonghua Yi Xue Za Zhi"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.2147\/DMSO.S394607","article-title":"A nomogram for predicting vision-threatening diabetic retinopathy among mild diabetic retinopathy patients: A case-control and prospective study of type 2 diabetes","volume":"16","author":"Ke","year":"2023","journal-title":"Diabetes Metab Syndr Obes"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1016\/j.eclinm.2022.101578","article-title":"Development and validation of predictive risk models for sight threatening diabetic retinopathy in patients with type 2 diabetes to be applied as triage tools in resource limited settings","volume":"51","author":"Nugawela","year":"2022","journal-title":"EClinicalMedicine"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2023.1244601","article-title":"Development and evaluation of a risk prediction model for diabetes mellitus type 2 patients with vision-threatening diabetic retinopathy","volume":"14","author":"Gong","year":"2023","journal-title":"Front Endocrinol (Lausanne)"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.3390\/s25165019","article-title":"RetinoDeep: leveraging deep learning models for advanced retinopathy diagnostics","volume":"25","author":"Kansal","year":"2025","journal-title":"Sensors (Basel)"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1016\/S2589-7500(19)30004-4","article-title":"Artificial intelligence using deep learning to screen for referable and vision-threatening diabetic retinopathy in Africa: a clinical validation study","volume":"1","author":"Bellemo","year":"2019","journal-title":"Lancet Digit Health"},{"key":"B38","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1038\/s41746-019-0172-3","article-title":"Deep learning algorithm predicts diabetic retinopathy progression in individual patients","volume":"2","author":"Arcadu","year":"2019","journal-title":"NPJ Digit Med"},{"key":"B39","doi-asserted-by":"publisher","first-page":"81","DOI":"10.48161\/qaj.v1n2a50","article-title":"Machine learning applications based on SVM classification a review","volume":"1","author":"Abdullah","year":"2021","journal-title":"Qubahan Acad J"},{"key":"B40","doi-asserted-by":"publisher","first-page":"8476","DOI":"10.1038\/s41598-022-12369-0","article-title":"Long-term prediction models for vision-threatening diabetic retinopathy using medical features from data warehouse","volume":"12","author":"Jo","year":"2022","journal-title":"Sci Rep"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.1155\/2023\/8831609","article-title":"A prediction model for sight-threatening diabetic retinopathy based on plasma adipokines among patients with mild diabetic retinopathy","volume":"2023","author":"An","year":"2023","journal-title":"J Diabetes Res"},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.1159\/000541294","article-title":"Comparison of machine learning algorithms and nomogram construction for diabetic retinopathy prediction in type 2 diabetes mellitus patients","volume":"67","author":"Jiang","year":"2024","journal-title":"Ophthalmic Res"},{"key":"B43","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare11121808","article-title":"Ensemble learning for disease prediction: A review","volume":"11","author":"Mahajan","year":"2023","journal-title":"Healthcare (Basel)"},{"key":"B44","doi-asserted-by":"publisher","DOI":"10.1007\/s00125-014-3369-7","article-title":"Impact of age, age at diagnosis and duration of diabetes on the risk of macrovascular and microvascular complications and death in type 2 diabetes","volume":"57","author":"Zoungas","year":"2014","journal-title":"Diabetologia"},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2023.1305378","article-title":"Prevalence and predictors of developing vision-threatening diabetic retinopathy within the first three years of type 2 diabetes","volume":"14","author":"Yan","year":"2023","journal-title":"Front Endocrinol (Lausanne)"},{"key":"B46","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.76395","article-title":"Association between hbA1c levels and the severity of diabetic retinopathy","volume":"16","author":"Alswaina","year":"2024","journal-title":"Cureus"},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.1002\/14651858","article-title":"Should video laryngoscopy or direct laryngoscopy be used for adults undergoing endotracheal intubation in the pre-hospital setting? A critical appraisal of a systematic review","volume":"15","author":"Pennington","year":"2023","journal-title":"J Paramed Pract"},{"key":"B48","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2021-050989","article-title":"Predictive model and risk analysis for diabetic retinopathy using machine learning: a retrospective cohort study in China","volume":"11","author":"Li","year":"2021","journal-title":"BMJ Open"},{"key":"B49","doi-asserted-by":"publisher","DOI":"10.1038\/s41433-019-0617-6","article-title":"Anaemia and the risk of progression from non-proliferative diabetic retinopathy to vision threatening diabetic retinopathy","volume":"34","author":"Li","year":"2020","journal-title":"Eye (Lond)"},{"key":"B50","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1038\/s41572-025-00646-x","article-title":"Diabetic retinal disease","volume":"11","author":"Sivaprasad","year":"2025","journal-title":"Nat Rev Dis Primers"},{"key":"B51","doi-asserted-by":"publisher","first-page":"S1","DOI":"10.1016\/j.kint.2025.06.006","article-title":"KDIGO 2026 clinical practice guideline for the management of anemia in chronic kidney disease (CKD)","volume":"109","author":"Tonelli","year":"2026","journal-title":"Kidney Int"},{"key":"B52","doi-asserted-by":"publisher","DOI":"10.1167\/iovs.61.14.25","article-title":"Anemia and diabetic kidney disease had joint effect on diabetic retinopathy among patients with type 2 diabetes","volume":"61","author":"Wang","year":"2020","journal-title":"Invest Ophthalmol Vis Sci"},{"key":"B53","doi-asserted-by":"publisher","first-page":"13315","DOI":"10.1038\/s41598-025-97061-9","article-title":"Association of hemoglobin with decreased prevalence of diabetic retinopathy among Tibetan male patients","volume":"15","author":"Yin","year":"2025","journal-title":"Sci Rep"},{"key":"B54","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2022.816400","article-title":"Mechanistic pathogenesis of endothelial dysfunction in diabetic nephropathy and retinopathy","volume":"13","author":"Yang","year":"2022","journal-title":"Front Endocrinol (Lausanne)"},{"key":"B55","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2022.1064665","article-title":"Establishment and validation of the cut-off values of estimated glomerular filtration rate and urinary albumin-to-creatinine ratio for diabetic kidney disease: A multi-center, prospective cohort study","volume":"13","author":"Gao","year":"2022","journal-title":"Front Endocrinol (Lausanne)"},{"key":"B56","doi-asserted-by":"publisher","DOI":"10.1186\/1758-5996-3-9","article-title":"Albuminuria and diabetic retinopathy in type 2 diabetes mellitus sankara nethralaya diabetic retinopathy epidemiology and molecular genetic study (SN-DREAMS, report 12)","volume":"3","author":"Rani","year":"2011","journal-title":"Diabetol Metab Syndr"},{"key":"B57","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1007\/s10916-023-01976-7","article-title":"A feasibility study of diabetic retinopathy detection in type II diabetic patients based on explainable artificial intelligence","volume":"47","author":"Lalithadevi","year":"2023","journal-title":"J Med Syst"}],"container-title":["Frontiers in Endocrinology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2026.1776188\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T13:14:20Z","timestamp":1776172460000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2026.1776188\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,4]]},"references-count":57,"alternative-id":["10.3389\/fendo.2026.1776188"],"URL":"https:\/\/doi.org\/10.3389\/fendo.2026.1776188","relation":{},"ISSN":["1664-2392"],"issn-type":[{"value":"1664-2392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,4]]},"article-number":"1776188"}}