{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,18]],"date-time":"2026-11-18T17:47:06Z","timestamp":1795024026073,"version":"4.10.2"},"reference-count":15,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T00:00:00Z","timestamp":1764633600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Medicina"],"abstract":"<jats:p>Background and Objectives: Arteriovenous fistula (AVF) occlusion remains a major cause of vascular access failure in hemodialysis patients. Early identification of high-risk patients may help prevent complications and improve outcomes. Materials and Methods: This retrospective cohort study included 1498 adult patients who underwent AVF creation between 2015 and 2025 at Daegu Catholic University Medical Center. Clinical, surgical, and laboratory variables were used to develop machine learning (ML) models for predicting AVF occlusion. Five algorithms\u2014LightGBM, CatBoost, XGBoost, Random Forest, and Logistic Regression\u2014were trained and evaluated using stratified five-fold cross-validation. Model performance was assessed using area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, and calibration. SHAP (Shapley Additive Explanations) analysis was used to interpret variable importance. Results: Among the 1498 patients, 381 (25.4%) experienced AVF occlusion. LightGBM achieved the best performance (AUC = 0.887, accuracy = 0.858, specificity = 0.950), followed by CatBoost (AUC = 0.882) and XGBoost (AUC = 0.879). Calibration analysis demonstrated strong agreement between predicted and observed outcomes. SHAP analysis identified ferritin, hemoglobin, neutrophil percentage, and C-reactive protein as the most influential predictors, highlighting the role of inflammation and hematologic status in AVF failure. Conclusions: Gradient boosting-based ML models, particularly LightGBM and CatBoost, accurately predict AVF occlusion using routine clinical data. Explainable AI methods enhance interpretability, enabling early identification of high-risk patients and supporting precision vascular access management in hemodialysis care.<\/jats:p>","DOI":"10.3390\/medicina61122150","type":"journal-article","created":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T12:39:43Z","timestamp":1764679183000},"page":"2150","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Development of a Machine Learning-Based Predictive Model for Arteriovenous Fistula Occlusion After Surgery: A Retrospective Cohort Study from 2015 to 2025"],"prefix":"10.3390","volume":"61","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0906-5236","authenticated-orcid":false,"given":"Jae Hoon","family":"Lee","sequence":"first","affiliation":[{"name":"Division of Vascular and Endovascular Surgery, Department of Surgery, School of Medicine, Daegu Catholic University, Duryugongwon-Ro 17-Gil 33, Nam-Gu, Daegu 42472, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0398-5514","authenticated-orcid":false,"given":"Sang Gyu","family":"Kwak","sequence":"additional","affiliation":[{"name":"Department of Medical Statistics, School of Medicine, Daegu Catholic University, Duryugongwon-Ro 17-Gil 33, Nam-Gu, Daegu 42472, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,2]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"320","DOI":"10.1159\/000502507","article-title":"Costs Attributable to Arteriovenous Fistula and Arteriovenous Graft Placements in Hemodialysis Patients with Medicare coverage","volume":"50","author":"Nordyke","year":"2019","journal-title":"Am. J. Nephrol."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1053\/j.ajkd.2018.01.034","article-title":"Medicare Costs Associated with Arteriovenous Fistulas Among US Hemodialysis Patients","volume":"72","author":"Thamer","year":"2018","journal-title":"Am. J. Kidney Dis."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1213","DOI":"10.2215\/CJN.01690213","article-title":"Vascular access morbidity and mortality: Trends of the last decade","volume":"8","author":"Lok","year":"2013","journal-title":"Clin. J. Am. Soc. Nephrol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1038\/s41746-022-00710-w","article-title":"Predicting radiocephalic arteriovenous fistula success with machine learning","volume":"5","author":"Heindel","year":"2022","journal-title":"npj Digit. Med."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"643","DOI":"10.1159\/000526768","article-title":"Risk Factors for Arteriovenous Fistula Thrombus Development: A Systematic Review and Meta-Analysis","volume":"47","author":"Zhang","year":"2022","journal-title":"Kidney Blood Press. Res."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"244","DOI":"10.1111\/sdi.12658","article-title":"The pathogenesis of hemodialysis vascular access failure and systemic therapies for its prevention: Optimism unfulfilled","volume":"31","author":"Viecelli","year":"2018","journal-title":"Semin. Dial."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"813","DOI":"10.1159\/000540543","article-title":"Construction of Risk-Prediction Models for Autogenous Arteriovenous Fistula Thrombosis in Patients on Maintenance Hemodialysis","volume":"53","author":"Jin","year":"2024","journal-title":"Blood Purif."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"286","DOI":"10.1016\/j.avsg.2022.01.023","article-title":"Hemodialysis Arteriovenous Fistula Dysfunction: Retrospective Comparison of Post-thrombotic Percutaneous Endovascular Interventions with Pre-emptive Angioplasty","volume":"84","author":"Hu","year":"2022","journal-title":"Ann. Vasc. Surg."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"6919979","DOI":"10.1155\/2021\/6919979","article-title":"Application Value and Relevance Analysis of the Risk Evaluation System for Arteriovenous Fistula Puncture in Thrombosis after Puncture","volume":"2021","author":"Li","year":"2021","journal-title":"J. Healthc. Eng."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"735","DOI":"10.1177\/11297298241237830","article-title":"A systematic review of prediction models on arteriovenous fistula: Risk scores and machine learning approaches","volume":"26","author":"Meng","year":"2025","journal-title":"J. Vasc. Access"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"683","DOI":"10.1177\/1129729819838795","article-title":"A systematic follow-up protocol achieving a low hemodialysis graft thrombosis rate","volume":"20","author":"Marchante","year":"2019","journal-title":"J. Vasc. Access"},{"key":"ref_12","first-page":"36","article-title":"On the Tractability of SHAP Explanations","volume":"74","author":"Broeck","year":"2022","journal-title":"J. Artif. Intell. Res."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1878","DOI":"10.1177\/11297298241304467","article-title":"A machine learning approach for identification of vascular access patency in hemodialysis patients using photoplethysmography: A pilot study","volume":"26","author":"Yang","year":"2025","journal-title":"J. Vasc. Access"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Shu, P., Huang, L., Wang, X., Wen, Z., Luo, Y., and Xu, F. (2025). Machine learning-based prediction model for arteriovenous fistula thrombosis risk: A retrospective cohort study from 2017 to 2024. BMC Nephrol., 26.","DOI":"10.1186\/s12882-025-04201-4"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1093\/ckj\/sfz048","article-title":"Arteriovenous fistula thrombosis is associated with increased all-cause and cardiovascular mortality in haemodialysis patients from the AURORA trial","volume":"13","author":"Girerd","year":"2020","journal-title":"Clin. Kidney J."}],"container-title":["Medicina"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1648-9144\/61\/12\/2150\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T13:19:43Z","timestamp":1764681583000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1648-9144\/61\/12\/2150"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,2]]},"references-count":15,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["medicina61122150"],"URL":"https:\/\/doi.org\/10.3390\/medicina61122150","relation":{},"ISSN":["1648-9144"],"issn-type":[{"value":"1648-9144","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,2]]}}}