{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:15:50Z","timestamp":1760141750836,"version":"build-2065373602"},"reference-count":42,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T00:00:00Z","timestamp":1760054400000},"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><jats:title>Background<\/jats:title><jats:p>Gout is a chronic inflammatory condition increasingly recognized as a risk factor for cardiovascular events (CVE). Early identification of high-risk individuals is crucial for targeted prevention and management. However, conventional risk stratification approaches often fall short in accuracy and clinical utility. This study aimed to develop and validate a robust, interpretable machine learning (ML)-based model for predicting CVE in patients with gout.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>This retrospective cohort study included 686 hospitalized gout patients at Xiyuan Hospital (Beijing, China) between January 1, 2013, and December 31, 2023. We applied Synthetic Minority Oversampling Technique (SMOTE) combined with random undersampling of the majority class. Then, patients were randomly divided into training (70%) and testing (30%) sets. A comprehensive set of clinical and biochemical variables (n = 39) was collected. Feature selection was performed using Boruta algorithms and Lasso to identify the most predictive variables. Multiple ML algorithms\u2014including Decision Tree Learner, LightGBM Learner, K Nearest Neighbors Learner, CatBoost Learner, Gradient Boosting Desicion Tree Learner\u2014were implemented to construct predictive models. SHAP values were used to assess model interpretability, and robustness was evaluated through 10-fold bootstrap resampling with enhanced standard error estimation.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Of the 686 patients, 263 experienced cardiovascular events during follow-up (incidence rate: 38.3%). A logistic regression model was constructed based on eight variables selected using the Boruta feature selection algorithm: sex, age, PLT, EOS, LYM, CO2, GLU and APO-B. Among the five models evaluated, the CatBoost classifier achieved the best performance, with the highest area under the ROC curve (AUC) of 0.976 and the recall of 0.971. Furthermore, SHAP (SHapley Additive exPlanations) values were employed to provide both global and individual-level interpretability of the CatBoost model. To assess the model\u2019s generalization performance, bootstrap resampling was performed 10 times. Based on these results, the standard error was improved using machine learning-based enhancement methods, thereby optimizing the model\u2019s robustness and predictive stability.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>The logistic regression analysis revealed that age (OR=1.351, p&amp;lt;0.001), CO2 (OR=0.603, p=0.004), eosinophil count (OR=2.128, p=0.001), and platelet count (OR=0.961, p&amp;lt;0.001) were significantly associated with the outcome, indicating their potential roles as independent predictors. Notably, while APO_B (p=0.138) and sex (p=0.132) showed no significant association, glucose levels (OR=2.1, p=0.066) exhibited a marginal trend toward significance, warranting further investigation. This tool may support clinicians in identifying high-risk individuals, enabling early interventions and optimized management strategies.<\/jats:p><\/jats:sec><jats:sec><jats:title>Limitations<\/jats:title><jats:p>This study has several limitations. First, the analysis was based on a single-center dataset, which may limit the generalizability of the findings. External validation in multi-center and prospective cohorts, along with an expanded sample size, is warranted to confirm these results. Second, key confounding factors such as medication use, lifestyle habits, and gout flare frequency were not included in the analysis; future studies should incorporate these variables to provide a more comprehensive assessment.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fendo.2025.1599028","type":"journal-article","created":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T04:17:54Z","timestamp":1760069874000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Establishment and evaluation of a model for clinical feature selection and prediction in gout patients with cardiovascular diseases: a retrospective cohort study"],"prefix":"10.3389","volume":"16","author":[{"given":"Bingbing","family":"Fan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuqing","family":"Ye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zihan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanyuan","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meishan","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weihong","family":"Cong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fang","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,10,10]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(21)00569-9","article-title":"Gout","volume":"397","author":"Dalbeth","year":"2021","journal-title":"Lancet"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.3389\/fimmu.2023.1151782","article-title":"Presence of tophi and carotid plaque were risk factors of MACE in subclinical artherosclerosis patients with gout: a longitudinal cohort study","volume":"14","author":"Wang","year":"2023","journal-title":"Front Immunol"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(20)30752-2","article-title":"Global burden of 87 risk factors in 204 countries and territories, 1990-2019: a systematic analysis for the Global Burden of Disease Study 2019","volume":"396","year":"2020","journal-title":"Lancet"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1038\/s41584-020-0441-1","article-title":"Global epidemiology of gout: prevalence, incidence, treatment patterns and risk factors","volume":"16","author":"Dehlin","year":"2020","journal-title":"Nat Rev Rheumatol"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1016\/S2665-9913(24)00117-6","article-title":"Global, regional, and national burden of gout, 1990-2020, and projections to 2050: a systematic analysis of the Global Burden of Disease Study 2021","volume":"6","year":"2024","journal-title":"Lancet Rheumatol"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1007\/s11136-024-03777-y","article-title":"Exploration of the association between new \u201cLife\u2019s Essential 8\u201d with hyperuricemia and gout among US adults","volume":"33","author":"Han","year":"2024","journal-title":"Qual Life Res"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1002\/advs.202404047","article-title":"Multimodal machine learning-based marker enables early detection and prognosis prediction for hyperuricemia","author":"Zeng","year":"2024","journal-title":"Advanced Sci"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1038\/s41584-025-01228-7","article-title":"Hyperuricaemia and gout in the Pacific","volume":"21","author":"G\u00e9rard","year":"2025","journal-title":"Nat Rev Rheumatol"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1002\/art.40807","article-title":"Contemporary prevalence of gout and hyperuricemia in the United States and decadal trends: the national health and nutrition examination survey, 2007\u20132016","volume":"71","author":"Chen-Xu","year":"2019","journal-title":"Arthritis Rheumatol"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.3389\/fphar.2020.582680","article-title":"Uric acid and cardiovascular disease: an update from molecular mechanism to clinical perspective","volume":"11","author":"Yu","year":"2020","journal-title":"Front Pharmacol"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvir.2017.11.026","article-title":"Multisociety consensus quality improvement revised consensus statement for endovascular therapy of acute ischemic stroke","volume":"13","author":"Sacks","year":"2018","journal-title":"Int J Stroke"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2022.11390","article-title":"Association between gout flare and subsequent cardiovascular events among patients with gout","volume":"328","author":"Cipolletta","year":"2022","journal-title":"JAMA"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1016\/j.semarthrit.2020.04.008","article-title":"Gout epidemiology and comorbidities","volume":"50","author":"Singh","year":"2020","journal-title":"Semin Arthritis Rheumatism"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.3390\/gucdd1030014","article-title":"Gout and cardiovascular disease: mechanisms, risk estimations, and the impact of therapies","volume":"1","author":"Andr\u00e9s","year":"2023","journal-title":"Gout Urate Crystal Deposition Disease"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1002\/art.41008","article-title":"Cause-specific mortality in gout: novel findings of elevated risk of non-cardiovascular-related deaths","volume":"71","author":"Vargas-Santos","year":"2019","journal-title":"Arthritis Rheumatol"},{"key":"B16","volume-title":"DecisionLinnc is a platform that integrates multiple programming language environments and enables data processing, data analysis, and machine learning through a visual interface","year":"2023"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3071603","article-title":"Adaptive data structure regularized multiclass discriminative feature selection","volume":"33","author":"Fan","year":"2022","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1002\/acr.24881","article-title":"Cause-specific mortality in patients with gout in the US veterans health administration: A matched cohort study","volume":"75","author":"Helget","year":"2022","journal-title":"Arthritis Care Res"},{"key":"B19","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1007\/s11739-016-1423-9","article-title":"Cardiovascular disease and hypertension in sub-Saharan Africa: burden, risk and interventions","volume":"11","author":"Cappuccio","year":"2016","journal-title":"Internal Emergency Med"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1038\/nrrheum.2014.124","article-title":"Improving cardiovascular and renal outcomes in gout: what should we target","volume":"10","author":"Richette","year":"2014","journal-title":"Nat Rev Rheumatol"},{"key":"B21","doi-asserted-by":"publisher","first-page":"894","DOI":"10.1161\/CIRCULATIONAHA.107.703389","article-title":"Independent impact of gout on mortality and risk for coronary heart disease","volume":"116","author":"Choi","year":"2007","journal-title":"Circulation"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1136\/annrheumdis-2014-205252","article-title":"Increased risk of vascular disease associated with gout: a retrospective, matched cohort study in the UK Clinical Practice Research Datalink","volume":"74","author":"Clarson","year":"2015","journal-title":"Ann Rheumatic Diseases"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.3390\/jcm11082124","article-title":"Cardiovascular risks in Korean patients with gout: analysis using a national health insurance service database","volume":"11","author":"Moon","year":"2022","journal-title":"J Clin Med"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1016\/S2665-9913(23)00338-7","article-title":"Gout and incidence of 12 cardiovascular diseases: a case\u2013control study including 152\u2008663 individuals with gout and 709\u2008981 matched controls","volume":"6","author":"Ferguson","year":"2024","journal-title":"Lancet Rheumatol"},{"key":"B25","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1186\/s12916-020-01688-6","article-title":"Insulin: too much of a good thing is bad","volume":"18","author":"Kolb","year":"2020","journal-title":"BMC Med"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.2337\/diabetes.54.4.959","article-title":"S-nitrosation of the insulin receptor, insulin receptor substrate 1, and protein kinase B\/Akt: A novel mechanism of insulin resistance","volume":"54","author":"Carvalho-Filho","year":"2005","journal-title":"Diabetes"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1177\/0003319719887655","article-title":"Fasting blood glucose and HbA1c correlate with severity of coronary artery disease in elective PCI patients with HbA1c 5.7% to 6.4%","volume":"71","author":"Yang","year":"2019","journal-title":"Angiology"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1016\/j.diabres.2012.04.021","article-title":"Association between blood glucose levels and high-sensitivity cardiac troponin T in an overt cardiovascular disease-free community-based study","volume":"97","author":"Zheng","year":"2012","journal-title":"Diabetes Res Clin Practice"},{"key":"B29","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1016\/j.atherosclerosis.2022.03.015","article-title":"Quality of life and coping in Dutch homozygous familial hypercholesterolemia patients: A qualitative study","volume":"348","author":"Mulder","year":"2022","journal-title":"Atherosclerosis"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1093\/eurheartj\/ehx144","article-title":"Low-density lipoproteins cause atherosclerotic cardiovascular disease. 1. Evidence from genetic, epidemiologic, and clinical studies. A consensus statement from the European Atherosclerosis Society Consensus Panel","volume":"38","author":"Ference","year":"2017","journal-title":"Eur Heart J"},{"key":"B31","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1016\/j.addr.2020.07.019","article-title":"Lipoproteins and lipids in cardiovascular disease: from mechanistic insights to therapeutic targeting","volume":"159","author":"Soppert","year":"2020","journal-title":"Advanced Drug Delivery Rev"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1002\/ptr.7002","article-title":"Natural products: The role and mechanism in low-density lipoprotein oxidation and atherosclerosis","volume":"35","author":"Zhang","year":"2020","journal-title":"Phytotherapy Res"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1117765109","article-title":"Critical role for calcium mobilization in activation of the NLRP3 inflammasome","volume":"109","author":"Murakami","year":"2012","journal-title":"Proc Natl Acad Sci U.S.A"},{"key":"B34","doi-asserted-by":"publisher","first-page":"8179","DOI":"10.1038\/s41467-024-52543-8","article-title":"Activation of osmo-sensitive LRRC8 anion channels in macrophages is important for micro-crystallin joint inflammation","volume":"15","author":"Chirayath","year":"2024","journal-title":"Nat Commun"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1161\/ATVBAHA.120.315697","article-title":"Calciprotein particles: balancing mineral homeostasis and vascular pathology","volume":"41","author":"Kutikhin","year":"2021","journal-title":"Arterioscler Thromb Vasc Biol"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1093\/toxsci\/kfac073","article-title":"Febuxostat increases\u00a0ventricular arrhythmogenesis through calcium handling dysregulation in human-induced pluripotent stem cell-derived cardiomyocytes","volume":"189","author":"Zhu","year":"2022","journal-title":"Toxicol Sci"},{"key":"B37","doi-asserted-by":"publisher","first-page":"e23012","DOI":"10.1096\/fj.202300393R","article-title":"Hyperuricemia: A key\u00a0contributor to endothelial dysfunction in cardiovascular diseases","volume":"37","author":"Wei","year":"2023","journal-title":"FASEB J"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.3389\/fimmu.2023.1282890","article-title":"The dysregulation of immune cells induced by uric acid: mechanisms of inflammation associated with hyperuricemia and its complications","volume":"14","author":"Li","year":"2023","journal-title":"Front Immunol"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.3390\/biom14070753","article-title":"The role of hyperuricemia in cardiac diseases: evidence, controversies, and therapeutic strategies","volume":"14","author":"Zheng","year":"2024","journal-title":"Biomolecules"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.1172\/JCI175972","article-title":"TRIB3 mediates vascular calcification by facilitating self-ubiquitination and dissociation of Smurf1 in chronic kidney disease","volume":"135","author":"Li","year":"2025","journal-title":"J Clin Invest"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.1016\/j.yjmcc.2025.07.002","article-title":"Smooth muscle-specific HuR knockout attenuates vascular calcification","volume":"205","author":"Chen","year":"2025","journal-title":"J Mol Cell Cardiol"},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.1161\/STROKEAHA.120.032964","article-title":"Carotid plaques from symptomatic patients are characterized by local increase in xanthine oxidase expression","volume":"52","author":"Ganji","year":"2021","journal-title":"Stroke"}],"container-title":["Frontiers in Endocrinology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2025.1599028\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T04:17:55Z","timestamp":1760069875000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2025.1599028\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,10]]},"references-count":42,"alternative-id":["10.3389\/fendo.2025.1599028"],"URL":"https:\/\/doi.org\/10.3389\/fendo.2025.1599028","relation":{},"ISSN":["1664-2392"],"issn-type":[{"value":"1664-2392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,10]]},"article-number":"1599028"}}